The Inference Report

Asynchronous monitoring, incident investigations, and compliance audits primarily rely on agent traces to reconstruct what happened. These analyses assume that LLM agents cannot tamper with their own execution traces. We show that local LLM agents such as Claude Code, Codex, Antigravity, Open Code and Grok Build fail to enforce this boundary. All tested harnesses, except Muse Code, allowed agents to delete their traces when asked, without triggering monitor guardrails. We also validate that external attackers can exploit this gap to induce trace deletion. Finally, we show that trace tampering behavior emerges naturally in frontier models, when agents try to improve their rewards. We advise practitioners to ensure trace logging happens through an independent interception mechanism outside of the agent's control, preserving trace integrity even in cases of full host compromise. Overall, our findings identify a concrete failure of trace integrity in agent infrastructure which can be used to conceal misaligned behaviors like scheming or sabotage.

Latent world models are typically trained to predict factual transitions, whereas model predictive control (MPC) must compare alternative actions from the same state. A model can therefore achieve low factual prediction error yet poorly distinguish candidate actions. We introduce AD-WM, an action-discriminative joint-embedding world model for counterfactual MPC. AD-WM combines residual latent dynamics with predictor-level action-recovery regularization, using inverse dynamics and a normalized recovery objective motivated by conditional mutual information. Both objectives encourage planning transitions to preserve action information; their auxiliary heads are discarded at test time, leaving MPC unchanged. On OGBench-Cube, AD-WM improves hard-start success from 3.7% to 52.0% over a matched LeWM baseline and improves mean success over the reproduced baseline in four of five simulation environments. Planning diagnostics show that factual prediction error and whole-bank action ranking do not follow the closed-loop success ordering, whereas CEM-aligned elite regret tracks success more closely. With a frozen V-JEPA 2 encoder and matched DROID post-training, AD-WM also improves zero-shot transfer to our Franka setup, increasing basic pick-and-place success from 42.2% to 71.1% without lab-specific adaptation. These results suggest that world models for planning should preserve action-dependent differences needed for counterfactual selection, rather than optimize factual prediction accuracy alone. More videos and code are available at https://ad-wm.github.io/.

Distributed learning in embodied reinforcement-learning agents offers a degree of privacy by retaining raw sensor data on-device and transmitting only policy gradients to the server. Yet temporal structure can amplify this leakage beyond single-frame attacks. We introduce Temporal Reconstruction Attack on Consecutive Encodings (TRACE), an amortized temporal gradient-inversion attack that autoregressively reconstructs the sequence of private observation-action trajectories from per-step policy-learning gradients. The attack exploits two structural signals ignored by prior single-frame methods: (i) cross-time correlation between successive embodied gradients, which we formalize via a conditional mutual-information bound, and (ii) closed-form action recovery from policy-head gradient structure, which we prove exact when standard entropy regularization is sufficiently small. On held-out embodied scenes, TRACE reaches $18.8$ dB PSNR with near-perfect action recovery at $3$-$4.5$ ms per reconstructed frame, dominating the learning-based baseline across all reconstruction metrics and exceeding optimization attacks while running orders of magnitude faster. Further evaluation demonstrates TRACE's broader applicability across recurrent, residual, and compact transformer victim architectures, multi-modal inputs, and larger discrete action spaces. Defense experiments suggest that protecting temporal gradient streams may require sequence-aware privacy mechanisms.

Conspiratorial discourse on social media is not always expressed through explicit claims or stable lexical markers. The same surface content may express endorsement, legitimate concerns, criticism, satire, or mockery. The main challenge is therefore not only recognizing conspiracy-related claims, but inferring the speaker's intent -- the utterance's illocutionary force. We argue that this can be achieved through the use of relevant social contexts and propose an agentic framework, equipped with a set of tools supporting social queries. We demonstrate the benefits of our approach on a unique dataset of Hebrew tweets, covering 80\%--90\% of the public Hebrew tweets published over a four-year span (late 2018-- early 2023), encompassing several election cycles as well as the COVID pandemic years and related vaccination campaigns. This extensive coverage can be used in recovering different social contexts. Evaluating our framework on a manually-annotated adversarial dataset, we find that context-aware workflows consistently outperform text-only classification and that the agentic framework performs significantly better than other frameworks and settings, including a non-agentic model exposed to the same contexts available to the agent. We further provide an analysis of the results, the errors and efficiency (token economy) tradeoffs. These findings support viewing the task of conspiracy detection as a socially embedded interpretation task, in which effective classification depends not only on access to contexts, but also on adaptive reasoning in which the agent uses tools on a per-case basis, asking only for evidence relevant to its current reasoning step.

Coding agents have demonstrated enormous success in solving complex programming problems. To leverage their potential for robot systems, this work introduces Robot Agentic Programming from Demonstrations (RAPID), which automatically generates, verifies, and refines robot programs, given a single visual human demonstration. The iterative agentic loop of code refinement requires several key ingredients: (i) a testable task specification, (ii) action primitives for robot execution, and (iii) an interactive environment for program execution and verification. RAPID infers all three from the demonstration automatically. To make the resulting program reusable beyond the demonstration setting, RAPID uses an object-centric relational program representation that focuses on the underlying structure of the demonstrated strategy rather than the specific motion per se: it expresses the action primitives as trajectory-optimization programs that realize object-level motion effects, while composing them through relational constraints that capture scene-specific geometry at run time. We evaluated RAPID in simulation on eight challenging contact-rich nonprehensile manipulation tasks as well as general prehensile manipulation tasks in the LIBERO-Pro benchmark. We also successfully deployed it on a real Franka arm and evaluated on all eight nonprehensile tasks. In all experiments, RAPID demonstrated strong performance, with generalization over object pose, shape, material, and environment. Website: https://yuyaoliu.me/projects/rapid.

World Action Models (WAMs) couple action generation with future visual prediction for robotic manipulation. However, completing the joint video-action denoising process at each replanning cycle incurs substantial latency, delaying action updates and limiting closed-loop responsiveness. We present Rolling-WAM, a formulation that distributes joint denoising across successive replanning cycles. Our method maintains a sliding window of video-action chunks at staggered noise levels. At each step, a rolling noise schedule fully denoises the imminent action chunk for execution, while partially refining farther-future chunks. As the window advances with new camera observations, the retained future chunks continue their denoising process. This distributes the computational cost over time while carrying an evolving visual-action context across chunk boundaries. Evaluations on LIBERO, RoboTwin, and a real-world Unitree G1 humanoid show that Rolling-WAM achieves competitive manipulation performance. By removing the need to denoise the entire prediction horizon from scratch, it delivers a 4.5x steady-state replanning speedup over standard joint WAMs.

Dedicated decision models such as Jev map unstructured language to probability distributions over finite choices, allowing their outputs to directly route requests, select tools, and trigger actions. Yet real-world inputs rarely arrive in isolation: they come with background details and surrounding context. We find that short additions that fit naturally into this context can nevertheless redirect an otherwise correct decision, even when the correct answer remains unchanged. To study this behavior, we fix a wrong target option for each initially correct item and use the model's option probabilities to refine fluent context additions while preserving the source, question, choices, and gold answer. Within 64 accepted target evaluations, the optimizer identifies contexts that redirect Jev on 312 of 508 initially correct decisions (61.4%); in 229 cases, Jev assigns at least 0.7 probability to the fixed wrong option. Across seven datasets, three additional decision systems show targeted flip rates of 64.9%-73.2% on decisions they initially answer correctly. Taken together, these results expose a pronounced fragility in current decision models: short, ordinary-looking context can shift a correct choice to a high-confidence wrong one. Because these models turn language directly into downstream choices, this sensitivity raises concerns about treating their probability outputs as reliable decision interfaces.

Recent research on Multimodal Sentiment Analysis (MSA) has focused on learning from language, visual, and acoustic modalities with incomplete data to infer human sentiment. Most studies typically compensate for missing information by reconstructing modality features or designing complicated fusion mechanisms. However, these methods still suffer from spurious generation and noisy guidance due to the lack of high-level semantic grounding in partially observed multimodal evidence. To address these issues, we propose SemMSA, a latent semantic-aided framework that constructs rich sentiment-relevant semantics with LLMs, fully integrating with all modalities via anchor-free spectral alignment. It mainly consists of Cross-modal Semantic Refinement (CSR) and Cross-modal Spectral Alignment (CSA). Specifically, CSR first adaptively extracts visual and acoustic representations by corresponding adapters to form a unified multimodal prefix with language in the frozen LLM embedding space. It then iteratively produces continuous discriminative semantic states through a token-efficient latent refinement process without decoding explicit text. Next, CSA simultaneously aligns the refined semantics with all modalities by enhancing the dominant spectral component of their kernel Gram matrix. This captures global nonlinear dependencies among all representations without relying on a predefined anchor modality. In addition, an instance-level spectral separation constraint preserves cross-sample discriminability and mitigates representation collapse. Extensive experiments on SIMS, MOSI, and MOSEI benchmarks demonstrate that SemMSA achieves state-of-the-art performance.

Task and motion planning (TAMP) problems remain difficult even with full observability and object-centric states because discrete decisions are tightly coupled to geometric, kinematic, and dynamic constraints. Generalized TAMP addresses this difficulty by exploiting regularities across problem instances to reduce planning effort on new instances. However, existing methods require substantial TAMP-specific engineering. We investigate whether coding agents can automate this process by synthesizing programs that generalize across instances. Given a task description and simulator access, each agent chooses how to interact with the environment while developing a program within a fixed synthesis budget. The program is then frozen and evaluated on unseen instances. We evaluate Claude Code (Opus 5) and Codex (GPT-5.6 Sol and GPT-6 Astra) on 28 simulated environments from KinDER and PDDLStream, with object counts beyond those evaluated in the original benchmark. Across all program synthesis methods, we evaluate 980 generated programs on 100 held-out instances each, 98,000 evaluation episodes in total. Overall, we find that coding agents are surprisingly effective at generalized TAMP: all three agent configurations outperform hand-engineered planners, one-shot generation, and an LLM-based generalized planning baseline in mean success (56% to 95% versus 47% for the planners, on the 16 environments where a planner is available). As object counts grow, the agents' programs maintain higher success than the planner, using an order of magnitude less computation per instance on average. Logs show agents using interaction to calibrate physical models, test edge cases, and refine strategies. We release all code, including the full prompts given to the agents. These findings suggest that coding agents are a strong baseline for generalized TAMP.

Online misinformation increasingly appears in spoken formats such as news clips, podcasts, interviews, political speeches, and social media videos, creating a need for fact-checking systems that can verify claims directly from speech. We introduce VeriSpeak, a probe benchmark for studying speech-based fact verification in Large Audio Language Models (LALMs). VeriSpeak contains 3,879 spoken claims spanning temporal, geographical, and relational facts, with balanced true and false labels. The benchmark is designed to examine whether factual verification ability transfers from text to speech, and whether retrieval-augmented LALMs can use textual evidence to correctly support or refute spoken claims. Our experiments reveal a consistent text-speech modality gap: LALMs that verify written claims reliably often fail on the same claims when spoken. Moreover, retrieval alone provides limited gains because models frequently conflate retrieved evidence with the spoken claim. In contrast, retrieval combined with explicit reasoning improves claim-evidence comparison, with a thinking-tuned LALM reaching 86.1% accuracy. VeriSpeak highlights that effective speech misinformation detection requires not only speech understanding, but also grounded reasoning over retrieved evidence. The dataset is publicly available via Hugging Face at https://huggingface.co/datasets/abhiram4572/VeriSpeak.

Foundation models are post-trained with reinforcement learning (RL) to maximize specific rewards, such as human alignment, correctness, or instruction following. This post-training process is computationally intensive, sometimes unstable, and has to be run from scratch every time the reward model changes or when we want to combine multiple rewards. We hence ask: given a new reward function, is it possible to predict the RL outcomes without actually running RL on it? We answer this in the affirmative by introducing PoEM, a framework to predict the outputs of RL on a new reward function using a set of models already post-trained on other rewards. First, we show that if the new reward function can be written as a linear combination of existing ones, then the new policy in log-space can be written as a linear combination of the existing log-policies. Surprisingly, even in cases where the rewards are not linearly connected, we observe that often log-policies from RL training span an approximately low-rank subspace across rewards. To our benefit, the weighting coefficients for this combination can be estimated using only the reward or basis policy outputs on the samples. We turn these observations into an algorithm that takes post-trained models and a new reward function, and approximates the target RL policy without actually running any additional RL training. We experimentally validate our approach across synthetic and real rewards, spanning both text and image modalities.

Existing point tracking models face a fundamental tradeoff: they can either track a sparse set of query points over long horizons, or track all points across only short clips. We introduce TrackEverything, a 3D point tracker that breaks this trade-off by representing videos as persistent 3D scene tracks in world coordinates. Grounded in the insight that videos are 2D projections of an underlying 3D world, TrackEverything decouples model complexity from video duration, allowing it to scale with unique physical scene geometry instead. Our approach introduces three key innovations. First, we employ a voxelization-based de-duplication mechanism at sliding-window boundaries to merge co-located tracks, preventing repeated observations of the same surface from redundantly accumulating. Second, we decompose tracking into an endpoint refiner that predicts each point's destination and static-versus-dynamic classification, followed by a lightweight trajectory refiner that decodes dense trajectories exclusively for dynamic points. Third, we propose 3D WAFT, replacing memory-prohibitive 4D correlation volumes with efficient feature sampling in the scene cloud. To the best of our knowledge, TrackEverything is the first 3D tracker capable of tracking all visible points across videos exceeding 1000 frames within 40 GB of GPU memory. On TAPVid-3D, TrackEverything outperforms all open-source all-frame dense 3D trackers by more than 20% APD on short clips, while remaining competitive with state-of-the-art sparse trackers on long sequences, despite tracking far more points.

An acceptance protocol is developed for sensor-coordinate and polarity binding in mechatronic commissioning. Candidate generation is separated from release authority. Requirements unsupported by a deterministic parser are routed to a frozen local language model with four billion parameters. Plans are released only when both facts can be derived by an external gate under a sealed grammar. One canonical answer is requested from a gold-standard user when eligible. The protocol was evaluated once under a criterion fixed before benchmark construction, on 144 tasks written by isolated agent contexts without access to the gate, grammar, or experimental plan. Three contributions are established. First, candidate generation and release decisions were measured separately. Fabricated ready plans were committed on 21 of 22 routed unanswerable tasks, and all were rejected. The same 83 releases were reproduced without model calls. Second, no false release was observed among 83 releases. A one-sided 95% Clopper-Pearson upper bound of 0.0354 was obtained as a diagnostic under an independent-and-identically-distributed assumption, below the sealed 5% threshold. However, one false release was subsequently recorded among 146 releases outside the benchmark at seed 0. Third, protection against incorrect user answers was characterized. Both facts were bound from the original text on 13 of 96 answerable tasks. Incorrect answers were released in 169 of 431 pairings on the remaining tasks, including failures involving coordinate exclusion. A deployable questioning policy was not tested because eligibility was determined from the answer key. Gate sensitivity and real user behavior were not measured.

Pre-logit steering adapts a frozen language model to a test-time reward by adding vectors to its final hidden states. Unregularized reward optimization can substantially alter the output distribution and degrade generation quality. We propose Minimally Invasive Steering Vector Optimization (MISVO), which penalizes interventions using the local KL geometry of the induced token distribution. The resulting Fisher quadratic measures distributional sensitivity and admits an analytic gradient computed through matrix--vector products with the frozen language-model head. We derive an exact decomposition of the sequence-level KL gradient into an analytic Fisher term and a suffix score-function term. For a fixed generation horizon, we show that the suffix term is second order in the steering magnitude and that three Fisher surrogates agree with the full KL gradient to first order. MISVO uses the frozen-reference surrogate to optimize position-specific interventions without updating model parameters. Across preference and code-generation tasks on models with approximately 1B--14B parameters, MISVO achieves the highest mean reward in six of seven model--task settings, with diversity and coherence scores close to those of Best-of-N.

A central concern in AI safety is that agents may treat oversight as an obstacle when it conflicts with completing their goals. We study instrumental evasion, the propensity of LLM agents to circumvent runtime monitoring as a means of completing ordinary tasks. We introduce EvasionBench, a benchmark of 50 diverse task-policy pairs in which completing the task requires an operation prohibited by a runtime monitor. Agents know that their tool calls are monitored and are prompted to continue working when they pause. Across our evaluations, best-of-3 evasion attempt rates reach up to 98% and success rates up to 88%, with substantial variance across models. Claude Fable 5.1 succeeds less often, but frequently makes creative attempts to circumvent the monitor. Evasion generally increases with test-time compute, with higher evasion rates at greater reasoning effort and token use. Traces show that agents encode prohibited commands, decompose operations across tool calls, and retry until relevant context leaves the monitor's history. We also find that GPT-6 Astra's low evasion rate comes with overrefusal, as it frequently abandons otherwise solvable tasks under a denial-of-service prompt injection. Our findings show that ordinary task pressure can lead to adaptive attempts to evade runtime monitors without an explicit adversarial objective. Effective oversight must therefore remain robust against repeated attempts, as the persistence that helps agents solve difficult tasks can also drive them to circumvent their guardrails.

Jev is a fast, low-cost decision model that answers natural-language questions with choices, binary judgments, and scores. As its public ecosystem grows rapidly, it remains unclear how Jev is used across applications and how public attention relates to project distribution. To answer these questions, we conduct a large-scale, data-driven analysis of 2,170 publicly available Jev projects collected from GitHub as of September 22, 2026. We find rapid early growth in Jev's public ecosystem, with both new projects and integration into existing repositories. Across diverse domains, projects use Jev for multiple decision purposes and combine its interfaces. Attribute judgment and scoring are widely used, while the use of action selection, content filtering, and model and tool selection varies across domains. These patterns suggest that Jev serves as a reusable decision component whose functionality varies with the surrounding workflow. Meanwhile, public attention is concentrated in routing and interface agents and does not track project counts. Our findings provide a quantitative view of Jev's emerging ecosystem and inform the design and evaluation of general-purpose decision models across diverse application contexts.

We prove nearly quadratic lower bounds for randomized algorithms for linear optimization and uniform sampling over convex bodies in the membership oracle model. For linear optimization, this matches the known nearly quadratic upper bound up to a polylog factor in the dimension. For uniform sampling, this improves on the previous linear lower bound. Our construction also implies the same lower bound for volume estimation.

We present Underwater C$^{3}$-JEPA (cross-view, control-conditioned, context-extended), an object-centric multi-view predictive world model for near-field heavy-load underwater ROV salvage. Without contact sensors, it predicts in latent space how the task-object state evolves through contact interaction and under the hydrodynamic lag of the vehicle, from synchronized multi-view RGB observations and vehicle control signals. C$^{3}$-JEPA encodes multi-camera observations into task-object and context tokens, fuses cross-camera evidence through held-out-view attention, and directly predicts future states conditioned on control. Weak binding anchors the target and gripper at low annotation cost, while SIGReg sharpens the geometric representation. Experiments show that the learned representation transfers substantially more task-relevant information to downstream probes than a reconstruction-free latent baseline, while keeping the predictor lightweight. The resulting predictive interface supports model-predictive-control (MPC) candidate evaluation and imagined-rollout behavior-agent training. Validation on real underwater video shows the same architecture recovering a withheld camera's object state and staying ahead of persistence, so the recipe transfers beyond simulation.

We study the deterministic oracle complexity of finding approximate solutions to composite monotone inclusion problems, formed by the sum of a smooth single-valued monotone operator and a maximally monotone set-valued operator, under the tangent-residual criterion. We introduce the Anchored Extra-Proximal (AEP) framework, which combines an anchored extrapolation step with an inexact anchored proximal update satisfying a relative-error condition. The framework recovers the composite Fast Extragradient method in the first-order setting and yields natural second- and higher-order extensions by replacing the operator in the implicit update with its Taylor approximation at the extrapolated point. For every $p\geq 2$, assuming that the $(p-1)$th derivative of the single-valued operator is Lipschitz continuous, we combine this construction with a bisection line search to obtain a $p$th-order method that finds a point with tangent residual at most $\varepsilon$ in $\widetilde{O}(\varepsilon^{-2/(3p-1)})$ oracle calls. This improves all prior upper bounds for $p$th-order methods: in particular, it improves the previous best-known $\widetilde{O}(\varepsilon^{-1/p})$ tangent-residual complexity as well as the classical $O(\varepsilon^{-2/(p+1)})$ bound of higher-order hybrid proximal extragradient methods under the weaker duality-gap criterion. We complement this result with a worst-case lower bound of $Ω(\varepsilon^{-2/(3p-1)})$ for every deterministic algorithm in the $p$th-order oracle model, without restricting the algorithm to tensor steps or any other prescribed update structure. Thus, the proposed method attains the optimal dependence on $\varepsilon$, up to logarithmic factors, for all $p\geq2$.

Layer-wise visual-text similarity in Multimodal Large Language Models (MLLMs) is widely interpreted as evidence that the language model progressively integrates visual content into a shared representation space. This reading rests on the assumption that scalar alignment scores reflect content-level cross-modal interaction. To test this assumption, we apply controlled interventions to the visual stream. Across 13 MLLMs from five families spanning 0.5B to 72B parameters, replacing projector-output visual tokens with Gaussian noise sharply reduces task accuracy, yet four standard scalar measures (CKA, SVCCA, MIR, and the leading principal-angle cosine) fail to consistently separate the corrupted stream from the original. We call this failure the alignment illusion and trace it to the shared language-model pathway: anisotropic MLP down-projections pull visual and text tokens toward common output directions, producing weight-induced alignment. Because this component is essentially one-dimensional, we introduce the principal-angle gap (PA gap), defined as the difference between the top two principal-angle cosines, which separates weight-induced similarity from multi-directional visual structure. Under graded visual corruption, the PA gap tracks task accuracy more consistently than the scalar scores we consider; under a structured but irrelevant image, it further exposes regimes in which internal geometry and task accuracy come apart. Internal visual-text alignment in MLLMs is therefore best read as a geometric diagnostic of the visual stream inside the language model rather than a direct proxy for content-level cross-modal interaction, and is most informative when calibrated by controlled task evidence.

Large language model (LLM)-based clinical assistants are increasingly being integrated into electronic health record (EHR) systems, transforming how clinicians retrieve and synthesize information from patient records. Their safety and utility depend on rigorous evaluation, yet existing benchmarks are manually curated, costly to update, and rapidly become obsolete with evolving technological advancements. We present a scalable framework that automatically generates question--answer pairs from longitudinal EHR notes. Nineteen clinicians validate the benchmark generator, producing the Benchmark for Retrieving Information in EHRs (BRIE), a continuously maintainable evaluation dataset. Across nine LLMs and five inference strategies, state-of-the-art systems frequently omit clinically important information, particularly for questions requiring synthesis across multiple documents and encounters. Because the generator itself is validated, BRIE supports evaluations that static benchmarks cannot, including the generation of multiple answers that reflect variation in clinician reasoning for robust performance assessment and continuously refreshing benchmark content to guard against leakage. Our results demonstrate that scalable benchmark generation enables rigorous, up-to-date evaluation of clinical LLMs as they are deployed in rapidly evolving healthcare settings.

Scientific discovery begins where known problems end. There, AI systems must engage in exploration: framing hypotheses, designing experiments, and iterating on the results. However, evaluating this ability is difficult: (1) how to verify whether a genuinely new hypothesis holds, and (2) how to determine whether a system has discovered it through exploration or merely recalled related knowledge from pre-training data. To this end, we introduce ExplorationBench, which turns the wicked problem of evaluating scientific exploration into a concrete and tractable framework built on verifiable Alien Worlds: their rules are executable, so every answer can be checked exactly, and they conflict with familiar knowledge, so recall alone cannot solve the tasks. The benchmark contains two sandboxes, AlienCode (31 discovery targets, 70 tasks) and AlienLogic (24 discovery targets, 70 tasks). Each sandbox provides a flawed manual, task-specific environmental feedback, and a dedicated tool-call schema. Systems use these resources to explore the sandbox, then solve held-out tasks. We evaluate 10 AI systems and find that the strongest systems can acquire and apply unfamiliar rules, while performance varies substantially across trajectories and continued exploration can stall or reverse earlier gains. ExplorationBench represents a step towards AI systems that can acquire and apply genuinely new knowledge through exploration in unknown environments.

Latent neural surrogate solvers, or latent dynamics models, accelerate simulations of time-dependent physical systems by evolving a compressed latent space rather than resolving full-resolution fields directly. In principle this reduces computational cost and simplifies learning, but in practice errors often accumulate rapidly during long autoregressive rollouts, limiting predictive utility. We show that this instability does not stem from the latent representation itself, but arises when it is trained solely for reconstruction, producing representations poorly suited to long-horizon forecasting. We systematically evaluate training-level interventions that align latent representations with long-horizon rollout: Koopman operator learning and Hamming noise injection during autoencoder training to improve compression, together with noise injection and multi-step rollout fine-tuning to improve dynamics. Interventions that improve long-horizon rollout stability often degrade conventional training metrics, including reconstruction and one-step prediction accuracy. Collectively, these interventions reduce long-rollout error by approximately 40\% and match or exceed the accuracy of full-resolution models on two physics benchmarks, while requiring 2 orders of magnitude fewer floating point operations and half the GPU memory. Applied to mesoscale crystal-plasticity simulations of high-cycle fatigue, the resulting surrogate achieves stable extrapolation over horizons orders of magnitude beyond those observed during training. More broadly, these results show that neural compression should be designed not merely to reduce dimensionality, but to restructure the solution space for stable dynamical evolution, a key requirement for reliable, efficient neural surrogates in scientific applications.

Long-horizon reasoning remains a central challenge for large language models (LLMs) under sparse-reward regimes. We argue that this brittleness arises from two biases induced by complex reasoning spaces: an exploration bias, where models are drawn toward locally plausible but structurally unstable branches, and a compounding bias, where small local deviations accumulate across depth and suppress rare rewards. We introduce Symbolic Closure Analysis (SCA) as a theoretical lens characterizing how branching structures and sparse rewards induce these biases in long-horizon reasoning with local admissibility, and as a design principle for structural priors in less formal reasoning tasks. Motivated by this analysis, we propose SAGE (Structural Admissibility-Guided Exploration), a unified framework that injects structural guidance to alleviate exploration bias and compounding bias in long-horizon reasoning. SAGE combines two complementary structural guidance: algebraic sparsification, which projects locally admissible candidates onto operator-indexed algebraic subspaces to suppress spurious branching and mitigate exploration bias, and hyperbolic structural guidance, which embeds reasoning states into a negatively curved space to provide dense depth-wise signals and mitigate compounding bias. Across 12 benchmarks and 7 model families, SAGE outperforms competitive baselines. In particular, SAGE achieves up to an 8-fold improvement on the Andrews-Curtis problem, an open real-world long-horizon task. Code is available at: https://github.com/Susan571/SAGE-NeurIPS2026.

Vision-language models (VLMs) have become a common foundation for autonomous mobile GUI agents, but most existing systems rely on the VLM for both planning and action grounding at nearly every interaction step, leading to substantial latency and model-serving cost. We introduce Jev-Mobile, which shifts this paradigm to low-frequency VLM planning and high-frequency lightweight execution: the VLM specifies local goals, the accessibility tree defines a structured executable action space, and Jev, a fast typed decision model, repeatedly selects actions within this space. This design allows multiple GUI actions to be executed under a single VLM decision, reducing expensive VLM inference while preserving adaptive interaction. On the full AndroidWorld task suite, Jev-Mobile achieves 79% task success, compared with 78% for SeeAct-V and 84% for a Step-wise VLM baseline. Among successful trajectories, it reduces mean end-to-end execution time by 32.7% and mean model API cost by 73.4% relative to Step-wise VLM. These results show that decoupling high-level VLM reasoning from low-level action execution can substantially improve mobile GUI agent efficiency while maintaining competitive task performance.

A learner's current observations need not determine its response to further training. We formulate intrinsic-extrinsic coupling through the continuation-conditioned value of a constrained learning-state intervention, with observation-relative fibers describing present agreement. An executable finite-frame classifier-head write protects current logits while repairing specified historical margins under finite-precision acceptance checks. We distinguish local admissibility, continuation-conditioned intervention value, and complete-policy performance. A matched four-cell contrast identifies readout-specific non-additivity between the same intrinsic intervention and alternative external continuations. In a CLINC-derived class-incremental setting, replay changes the write's 32-update contribution from five correct predictions to zero. Nonzero interactions also occur under output distillation, with a RoBERTa backbone, and under optimizer-native SGDW dynamics. Under SGDW, correct-count interactions are negative in all three activated roots at 128 updates, showing that coupling need not imply positive synergy. The mathematical analysis distinguishes feasible local repairs and favorable terminal outputs from training-reachable repair regions. Separate coordination tests show that content controls match or exceed the development gain, while a five-root fresh-test comparison with Fiber present in every arm shows root-dependent rather than uniformly beneficial correct-count effects. On the secondary cross-entropy readout, guided allocation yields lower mean loss than standard replay in all five pairs. Together, these results make intrinsic-extrinsic coupling operational by connecting executable state geometry to continuation-conditioned value, matched interaction identification, and closed-loop coordination, while separating identified coupling from complete-policy performance.

U.S. employment-discrimination complaints describe complex event sequences that are not explicitly captured by lexical or embedding-based representations alone. We present ARGUS, a source-grounded pipeline that combines a 5W1H-inspired schema, legal-domain models, and LLM-based structured generation to construct document-level Event Knowledge Graphs (EKGs) from CourtListener complaints. ARGUS extracts fact-bearing statements, builds chunk-level event graphs with participant, temporal, and causal structure, and merges them into document-level representations. We evaluate graph quality through human and multi-model assessment and test downstream utility on claim classification and legal QA. The graph-structured classifier outperforms raw and linearized baselines on the held-out set, and EKG-only retrieval improves document-scoped QA, while open-retrieval gains remain limited by low first-stage candidate recall. These results suggest that EKGs are most useful for organizing and reasoning over evidence once relevant material has been retrieved.

Ensuring high structural coverage remains a fundamental challenge in automated test generation, particularly for complex software systems where reaching specific lines or branches requires satisfying intricate control- and data-flow constraints. Large Language Models (LLMs) have recently demonstrated strong capabilities in producing human-like test cases; however, they often struggle to generate inputs that satisfy precise path conditions. Conversely, symbolic execution can systematically derive such constraints, but it often fails to construct realistic, executable test cases and is constrained by scalability limitations. In this paper, we introduce NEUROTESTGEN, a hybrid approach that integrates symbolic execution with LLM-driven test synthesis to generate test cases targeting on-demand code coverage. Given a set of target statements within a method, NEUROTESTGEN first employs a symbolic analysis engine (i.e., the Z3 SMT solver) to extract path-specific constraints and construct a symbolic guidance specification for the desired coverage goal. This specification is then used to guide an LLM in synthesizing concrete test cases that are both structurally valid and semantically meaningful. For paths involving complex object-related constraints that are difficult for SMT solvers to handle, NEUROTESTGEN leverages LLMs to infer plausible constraints. Furthermore, NEUROTESTGEN incorporates an iterative feedback loop that validates LLM-generated tests and provides corrective guidance until the target line or branch is covered or a limit is reached. Our empirical evaluation on a widely used benchmark demonstrates that NEUROTESTGEN significantly outperforms the state-of-the-art approach across multiple LLMs, including Llama 3.3 70B1, GPT-4o Mini, Claude 3.5 Haiku3, and Claude Sonnet 4.6.

Query understanding (QU) plays a critical role in production search systems, translating raw user queries into search execution plans that drive downstream retrieval and ranking. While large language models (LLMs) have enabled QU to be framed as a structured multi-task generation problem (e.g., intent classification, query expansion), optimizing such models to produce search-engine-coupled outputs remains challenging: static, label-based supervision fails to capture how each component actually interacts with the underlying search pipeline to affect downstream performance. We present a search-aware reinforcement learning (RL) framework for QU based on a distill-then-RL paradigm. Teacher-student supervised fine-tuning (SFT) first yields a well-formed, schema-compliant policy initialization. The RL stage then optimizes each QU component with rewards derived from live interaction with the search engine, tailored to that component's operational role, rather than a single reward tied to the final search outcome. Experiments on Roblox search show that this component-specific optimization improves both per-component utility and downstream search quality, raising NDCG@20 by 8.9 points over the SFT policy and by 3.5 points over training with a single end-to-end reward.

We introduce GridSFM, a framework that combines a pretrained foundation model across grid topologies with physics-informed fine-tuning for solving AC Optimal Power Flow (AC-OPF) at scale. It is a $15$ million parameter physics-inspired graph neural network pretrained across $54$ topologies of $500$ to $4{,}000$ buses. Our model attains a $2.45\%$ zero-shot generation-cost error on a $10{,}000$ bus case held-out operating conditions with no degradation as system size grows. Building on this, we pair the pretrained backbone with a physics-informed fine-tuning design based on Newton's method for power flow. With only $100$ solved instances, GridSFM adapts to unseen grids up to $10{,}000$ buses. We show it out performs single topology, dedicated neural network models that are trained more data, both in terms of cost and solver iterations when deployed as warm starting points. In designing this foundation model, we overcome the fact that the feasible set for AC-OPF can be disconnected. This is an obstruction that prevents any continuous neural network from approximating the solution map. To do so, we lift the problem and relax its constraints with logarithmically penalized slacks. We prove that the resulting elastic feasible set is contractible, that the AC-OPF minimizers remain minimizers of the elastic problem above an explicit penalty threshold, and that projecting an approximate solution back onto the AC-OPF feasible set is well posed. We release all models, data, and code so that the community can build on a shared starting point for AC-OPF.

Audio language models pass speech and text through a single decoder. We ask whether that decoder represents a distinctive feature in the same direction when a phoneme is heard and when it is read. For minimal pairs of phonemes differing in one feature, we take the offset between the two members' mean representations. Averaging those offsets gives a direction for each stream, and we measure the cosine between the two. Because the two streams already agree about arbitrary phoneme pairs, we compare every measure against a reference built from random pairings rather than against zero. We apply this to 6 models, 7 features and 15 languages from 11 families. Only voicing in the two Qwen2.5-Omni models exceeds that reference after correction for multiple testing, and the reference varies by a factor of seven between models. In three of the six models, voicing has one direction in audio across the 14 languages with enough minimal pairs to measure it, and every language pair agrees in two of them. The model family, not the model size, predicts which stream represents a feature.

Automatic speech recognition is typically trained assuming that the reference transcript is the only valid labeling of an utterance, yet even nominally verbatim transcripts contain localized differences in pronunciation, spelling, or lexical realization that the acoustics do not uniquely determine. Omni-temporal Classification (OTC) tolerates such noise by adding wildcard paths to the connectionist temporal classification (CTC) alignment graph, but its word-level arcs are too coarse, since bypassing one unsupported token discards supervision for the whole word. We move wildcard arcs to token granularity so unsupported tokens can be bypassed while the rest of the word stays supervised, and we combine token- and word-level arcs as complementary escape paths. Across 19 languages and three corpora, token-level OTC improves over CTC on all 25 tasks. We also replace epoch-indexed relaxation of the wildcard weights with a predictive-entropy-indexed schedule, which performs comparably while reducing dependence on training length. Combining this schedule with the hybrid graph gives the lowest mean word error rate (WER) on every corpus and a 9.45% average relative WER reduction over CTC. Independent validator transcriptions show that token-level models place significantly more wildcard-bypass probability than CTC on disputed characters, indicating that token-level tolerance targets localized transcript ambiguity.

Future quantum networks will make use of entanglement to perform numerous tasks, such as sending quantum information over long distances, distributed quantum computing, and quantum sensing. In general, these tasks will need to be performed simultaneously in various regions of a network, while minimizing resources and latency. We will thus require policies for scheduling link-level entanglement resources, and using the link-level entanglement to create various forms of multipartite entanglement required for every task. In this work, we address this problem using reinforcement learning. We formulate a Markov Decision Process for the problem and use double deep Q-networks (DQN) with Message Passing Neural Networks (MPNNs), experience replay buffers, and curriculum training to obtain policies. The key physical parameter is the probability of link-level entanglement generation, i.e., the link activation probability. We show that our policies maintain 100% success for up to 71% lower link activation probability than the baseline heuristics for a set of physically relevant network topologies. We then examine an additional constraint where experiment (task) placements are restricted to specific hardware types and demonstrate a similar advantage in performance over heuristics, with our policy maintaining at least an 80% success rate for up to a 59% lower link activation probability. Finally, we explore methods to interpret the learned policy by defining metrics enabling conclusions to be drawn about the model's behavior and by tasking a large language model (LLM) to derive a novel heuristic given example actions taken by the DQN-trained policy. We find that the LLM heuristic performs similarly to the DQN-trained policy in performance, indicating a promising method for interpretable policy extraction for large quantum networks, where direct training becomes computationally expensive.

Asked to choose between candidates and explain the choice, a language model often rejects a rival by naming a fact its profile lacks: no director, no date of death. That sentence is a claim about the text in front of the model, and it can be tested without any judge. We insert a real corpus sentence stating the named fact into the rival's profile and ask again under greedy decoding. Two controls separate content from placement: a length-matched irrelevant sentence at the same profile, and the same two sentences at a third option the model never mentioned. In the largest of three runs, six open models on 2WikiMultihopQA, supplying the named fact at the profile the model named moves its choice more than the irrelevant control does, odds ratio 3.57 [1.54, 8.26], Holm p=0.0210, and this survives dropping any single model. The contrast the design was built to detect, the same fact at the option nobody named, does not clear correction, Holm p=0.2428. The strongest result in the family carries no content claim at all: the identical irrelevant sentence moves the choice more at the named rival than at the third option, Holm p=0.0008. Repair and control also differ in co-candidate mentions, relation template and fluency; post-hoc matching on the first two preserves the content effects' direction, matching fluency weakens one, so the content contrasts bound an effect rather than establish one. A forced single-token probability read disagrees in direction with the free-text choice on that same contrast, and three candidate explanations for the disagreement find no support. Every measurement is a string rule, so each was validated against the records it reads; validation caught eight defects. The largest, a choice-parsing rule that returned the option a model had just rejected in 17.1% of adjudicable responses, would have reported six surviving contrasts instead of four.

Modern infrastructure asset management constitutes a complex sequential decision-making problem, characterized by long planning horizons and system-level interactions, such as spatial deterioration correlations and economies of scale. While deep reinforcement learning has shown promise in optimizing maintenance policies, scaling to real-world networks remains challenging. Centralized approaches become computationally intractable in large-scale systems, whereas decentralized approaches often fail to capture essential coordination mechanisms. To address these challenges, we propose a graph-based framework that integrates accurate environment modeling with scalable decision support. First, we employ a hierarchical Bayesian model leveraging a Gaussian Process on Graph kernel to infer a realistic, spatially correlated networked environment of railway maintenance planning from real-world data provided by the Swiss Federal Railways. Second, we introduce a topology-aware Multi-Agent Reinforcement Learning (MARL) framework by integrating graph neural networks and graph Transformers to optimize network-level policies. A central contribution of this work is the demonstration of scalability through zero-shot transfer learning: graph-based agents, trained only on small network portions, are successfully deployed in a zero-shot manner on large-scale unseen networks without any retraining. Numerical results indicate that the proposed method significantly outperforms optimized heuristics and standard MARL baselines, reducing computational training time while maintaining superior performance on large-scale networks.

Large Language Models (LLMs) typically exhibit a performance profile where reliability degrades as task complexity increases. We address the challenge of generating high-quality natural language executable plans for complex tasks by introducing $\textbf{GRASP}$, a strategy-aware, multi-stage planning framework. GRASP decouples the planning pipeline across specialized, context-isolated modules: it pre-compiles global macro-guidelines (GenPlan), explores alternative localized strategies within isolated context windows (RevPlan), and independently evaluates trajectories using a multi-criteria discriminator (VerPlan). Empirical evaluations show that GRASP consistently establishes a new state-of-the-art frontier across diverse datasets, yielding substantial accuracy gains over direct LLM planners on Natural Plan Calendar Scheduling ($\sim$12.4$\%$$\uparrow$), ZebraLogic ($\sim$30.8$\%$$\uparrow$), and SciBench Math. Crucially, under multi-task scaling-where standard planners suffer immediate performance collapse-GRASP completely flattens the multi-task degradation penalty. In interleaved dual-task environments, GRASP achieves an absolute accuracy gain of up to 16.7$\%$ over direct LLM planners. Furthermore, by isolating context and enforcing strict macro-regularization, GRASP outperforms frontier reasoning models (such as GPT-5-mini) by a margin of 14.5$\%$.

Most benchmarks hand the model a question. EnigmaForge hands it a stack of old documents and no question at all. Buried in the letters, receipts, and logbook margins is a small logic puzzle whose solution is unique - proved by a SAT solver at generation time, with an ablation certificate showing every clue is load-bearing. Because instances are generated rather than collected, the corpus renews forever. The headline measure is intuition: task success when handed only the story, with world reconstruction as the secondary axis. Twenty-five frontier models ran over 600 instances (17,400 scored records) under three matched conditions. Intuition reshuffles the leaderboard: a 22x spread where fact recovery spans 1.6x, the second-best fact-recoverer ranks fourteenth, one model is indifferent to being told the question, and another is significantly better without it. Several models were blocked by their own content filters before reaching the puzzle - any benchmark scoring refusals as failure is quietly measuring filter behavior.

Customer experience (CX) agents use tools and large language models to address customer requests and guide conversational interactions with an organization's products. Improving these agents, especially in regulated industries, is difficult: they must detect intent, follow complex operational policies and use tools reliably. Manual end-to-end testing offers limited coverage, while live experiments expose customers to failures that can erode trust. We present a hypothesis-driven simulation workflow for screening candidate CX agents before deployment. Synthetic customers react to agent responses and simulated tool outputs enable multi-step agentic workflows without invoking production backends. We use the Snowglobe simulator on Nubank's Card Delivery agent and its expanded successor, Card Management - Nubank's highest-volume chat-support agent in Brazil. Across 4 deployed versions, simulated and production version-level binary evaluator scores show high correlation. Simulation-guided iteration increased transactional net promoter score (tNPS) by 36.69 points in a live A/B test. We also screened open-weight configurations in over 16,000 simulated conversations. In a subsequent live A/B test, the selected model increased self-service rate (SSR) by 8.82 percentage points to the highest level observed at Nubank, with no statistically significant change in tNPS. Simulation made broad exploration of models, reasoning settings, and prompts feasible without customer exposure, enabling production improvements that would have been impractical to pursue through live experimentation alone.

Current vision-language models (VLMs) excel at visual content understanding and text-based reasoning, yet their structure limits the advancement of incorporating images into the reasoning chain. Though Omnimodal models have made efforts in unifying text and image generation, they focus on visual tasks in the open-domain, lacking tractability due to rasterized or latent representations of images. We introduce SVGLM, a framework that uses scalable vector graphics (SVG) primitives to connect text and image in reasoning tasks. We exploit the duality of SVG as both image description and text instructions, yielding a more compact, interpretable solution to equip general VLMs with the capability of generating images within the reasoning process. We provide a large curated dataset of SVG-based image editing dataset, as well as the paradigm to tune open-source VLMs. Experiments on a mathematical reasoning benchmark demonstrate that SVGLM achieves strong SVG generation power as well as think-with-image intelligence. Our results highlight SVG as a suitable medium for building more robust digital domain agents, bridging the gap between text-based thinking and pixel-based images.

Agent skills provide reusable knowledge and instructions, yet agents must repeatedly infer how to apply them and which operation should follow. This couples task reasoning with control decisions, allowing prescribed steps to be omitted or applied incorrectly. We introduce HEXIS, which compiles agent skills into extended finite state machines that separate knowledge from control flow. Skill knowledge is incorporated into local instructions that guide reasoning and generation within states. The machine records execution progress and intermediate results, while explicit transition conditions determine subsequent operations. Our incremental compiler first maps skill clauses and tool interfaces to state operations, local instructions, data bindings, and transitions. It then aligns development traces with existing states to identify missing operations and dependencies. These are incorporated by adding or reusing states and refining their connections. Updates are accepted only after static checks and replay of the current and all previously accepted traces. Across four benchmarks and four executors, HEXIS improves success over Skill + ReAct by 16.1 percentage points on average. Qwen3.8-27B reduces execution tokens by 38.4-88.9% across benchmarks.

Agent skills package version-specific maintenance knowledge for coding agents, but a higher diagnostic score does not by itself show that the resulting migration advice satisfies the target version's contract. We study a shipped plugin-upgrade skill through an archive of 64 reports on 16 static migration tasks, with two attempts per condition and 328 criterion decisions. With the skill, mean recorded reward rises from 93.83 to 98.75, a gain of 4.92 points (95% task-bootstrap interval [0.31, 10.86]); the gain is concentrated in one task, and eight task pairs are at the ceiling. Tracing every decision to its contract domain and reviewing ten reports in depth exposes grading errors that favor either arm; in one, a containment predicate that accepts the parent directory still receives full credit. Executable probes confirm this defect and show that a working teardown repair is excluded only by a narrower lifecycle rubric. Replacing the reviewed decisions keeps the estimate positive (4.61 to 5.39 points) but moves its interval to or across zero. Re-grading all 64 reports with judges from two other model families, without arm labels or prior scores, agrees with the original judge on 91.8% and 95.7% of decisions (weighted $κ=0.64$ and $0.72$) and gives gains of 10.63 and 6.09 points. The study contributes a traceable evaluation that connects aggregate reward to contract-level evidence and judge sensitivity, together with concrete review checks for migration advice. Executable end-to-end repairs, independent human annotation, and other frameworks are left to future work.

Audio Description (AD) makes movies accessible to blind and visually impaired audiences by narrating visual information in gaps between dialogue. Existing automatic AD systems largely treat generation as a local video-to-text problem, assuming that the content to describe and its temporal location are already provided. Realistic AD instead requires coupled decisions about what visual information is narratively important, when it can be spoken without interfering with dialogue, and how it should be formulated to fit within the available time. We formalize AD generation as a constrained optimization problem over these three decisions. Our hybrid system uses large language models to propose and ground visual elements, estimate their salience to the narrative, and generate compressed realizations. A mixed-integer linear program then jointly selects and schedules descriptions across a scene subject to temporal constraints. When evaluated on REFRAMED, a benchmark for realistic AD of movies, our approach makes better decisions than prompted LLMs about what to describe and when to describe it, establishing a new SOTA on narrative QA and temporally grounded metrics. Ablations show that explicit temporal constraints drive gains in placement, while salience estimation controls how much narratively useful content is retained. Improvements are concentrated on temporal and narrative measures rather than n-gram overlap, although a significant gap to professional describers remains.

Modern deep neural networks treat parameters as static floating-point matrices stored in physical memory, incurring Von Neumann memory bottlenecks and representation collapse. We formulate Orbital Error Dynamics (OED), an analytical framework wherein synaptic weights are not stored masses (O(W)), but transient topological resonances (O(1)) derived procedurally from the complex quadratic polynomial map z_{n+1} = z_n^2 + c. We introduce the Bent Sine Wave Hypothesis, demonstrating that non-equilibrium living systems emerge when harmonic waves curl inward through environmental drag toward the cardioid cusp (c = 1/4). We define the Observer Horizon Geometry in parameter space, identifying interior resonance shoulder loci X_upper = (0.25, +0.18) and X_lower = (0.25, -0.18) between the fixed-point basin and the true boundary at c = 0.25 +/- 0.50i. To escape non-convex stagnation without loss zeroing, we introduce a heavy-tailed Biomimetic Perturbed Jump Operator (Omega_tunneling) inspired by mammalian fertilization zinc sparks. We further couple an enteric-cranial Dual-Brain architecture shielded by adaptive CD4+ regulatory immune gating (M_CD4), and project the 4-nucleotide genetic basis (A, T, C, G) across quadrants in C. Multi-seed empirical validation on the Two-Moons manifold (5 seeds, 80/20 train/test split, 32x32 grid, zero test-time updates, zero label leakage) demonstrates that procedural parameterization from a 24-byte coordinate seed achieves 77.67% +/- 5.35% clean test accuracy (within an 8.00-point paired difference of an unconstrained gradient baseline at 85.67% +/- 5.35%, 95% CI: [-1.07%, 17.07%]) and 71.33% +/- 3.80% under distribution shift (N(1.2, 0.4)), alongside conceptual equivalence with an analog optical co-processor.

For an arbitrary isotropic log-concave distribution $P$ on $\mathbb{R}^d$, we prove that the polynomial $(Cm)^m\|v\|_2^m - \mathbb{E}_{X\sim P}\langle X,v\rangle^m$ is a sum of squares for every even $m\ge2$, where $C>0$ is a universal constant. This removes the dependence on the Poincaré constant in the theorem of Kothari and Steinhardt (arXiv:1711.07465), recovering the optimal moment bounds for log-concave distributions. As an immediate corollary, we obtain computationally efficient algorithms with dimension-free error guarantees for a wide range of high-dimensional statistical estimation problems. Our proof uses stochastic localization to decompose $P$ as an average of random strongly log-concave measures, whose centered moments admit the subgaussian certificates of Diakonikolas, Hopkins, Pensia, and Tiegel (STOC 2025; arXiv:2410.21194). With a covariance-adapted choice of localization, we show that a fourth-moment certificate derived from Letwin's variance inequality for quadratic forms (arXiv:2607.24164) suffices to control this averaging at every even degree.

High Performance Computing (HPC) and Quantum Computing (QC) systems are increasingly converging towards unified High Performance Computing-Quantum Computing (HPCQC) infrastructures, driven by a growing need to bridge classical and quantum workflows, which affects all levels of the system stack, from the hardware to compilers and runtimes, all the way to applications. However, today's QC devices are still in the Noisy Intermediate-Scale Quantum (NISQ) era, are error-prone and resource-limited, and therefore require specialized optimizations and topology mappings to achieve sufficient fidelity. This places special emphasis on proper compilation and optimization within the overall quantum software stack. Many existing stacks remain fragmented, with separate components responsible for device selection, compiler-pass optimization, and job queue scheduling. This paper proposes a unified, learning-based selector that integrates these disparate stages into a cohesive framework. Our proposed selector scheme leverages reinforcement learning and deep learning models that can be extended to simultaneously optimize multiple objectives -- such as fidelity, compilation time, and scheduling latency -- while dynamically adapting to circuit characteristics and device conditions.

Recent advances in paraphrase detection reveal a fundamental trade-off: large language models achieve high accuracy but require high computation, while efficient Siamese-BERT variants offer practical scalability with reduced transparency in rationale generation. We present R-DEIM Net, a 76M-parameter dual-expert architecture exploring whether moderate-scale models can achieve competitive accuracy on paraphrase detection while enabling human-readable rationale generation. The architecture combines two specialized components: an Interaction Expert that captures token-level similarity patterns through multi-scale 2D convolutions and attention head allowing variable input length, and a Reasoning Expert that uses a Flan-T5-small decoder to generate rationales as auxiliary supervision. Rather than re-encoding generated text, we extract and pool decoder hidden states as complementary features for classification. On the Quora Question Pairs dataset, R-DEIM Net achieves 90.07\% accuracy and 90.16\% F1-score via 10-fold cross-validation. This represents competitive performance with strong transformer-based baselines (e.g., MFAE BERT: 90.54\% accuracy) and recent large language model based approaches (LLaMA-70B) while using a substantially smaller parameter budget. The model generates rationales alongside predictions, providing potential for auxiliary human-readable descriptions.

Video diffusion is computationally expensive, as it requires executing a large model across many denoising steps. Even with step-distillation, inference remains expensive because every distilled step still requires a costly model evaluation. We present TRACK: TRajectory-Aware Capacity routing via top-K selection, a heterogeneous denoising strategy that switches between compatible large and small models at selected steps, reducing the average cost per denoising evaluation. The switching steps are determined using a calibration process. TRACK first rolls out a reference trajectory with the large model. Then at each step, the small model's prediction is also collected and compared against the large model's prediction to obtain a relative disagreement score. Both models receive the same latent, timestep, conditioning, and guidance inputs. Aggregating this signal over a calibration set produces a disagreement score map across diffusion steps, which determines a switching policy for an efficient inference process: quality-sensitive steps keep using the large model, while steps with low disagreement scores are routed to the small model. Inference executes only the selected model at each step, requiring no retraining, architecture or scheduler changes, or online dual-model evaluation. Across Wan 2.1, Cosmos 3, TurboDiffusion, and FastVideo, TRACK yields $1.95\times$, $2.04\times$-$2.73\times$, $2.69\times$, and $2.17\times$ speedups, respectively, with comparable aggregate quality and high diversity retention. TRACK thereby establishes automated, training-free model switching as a practical acceleration paradigm for video diffusion.

Large language models increasingly operate as persistent assistants in user-facing, shared-session, and tool-augmented settings. When users disclose sensitive information during an active conversation, that information may remain behaviorally recoverable through later prompts even after the dialogue shifts to unrelated topics. We introduce \textbf{PrivDrift}, a benchmark for auditing whether user-disclosed secrets remain recoverable after conversational topic drift and persuasion-based probing. PrivDrift contains 1{,}000 controlled multi-turn dialogues with seeded secrets, content-dense drift turns, and standardized extraction probes. Across three LLMs with extended context windows, dialogue-level hybrid leakage remains substantial, ranging from 38.7\% to 54.6\%, and varies strongly by model, secret type, and persuasion intensity. Within the tested drift window, additional topic drift does not reliably reduce leakage, suggesting that privacy risk in active LLM contexts should be evaluated as a persistent behavioral failure mode rather than only as training-data memorization or immediate jailbreak behavior.

Graph-structured optimization with linear constraints is fundamental to critical infrastructure but faces scalability limits due to massive strict hard constraints and high dimensionality. While recent projection-based methods such as Trainable Sampling Kaczmarz-Motzkin Net (T-SKM-Net) guarantee feasibility, they face high computational costs in dynamic environments by processing the entire constraint set and requiring expensive matrix factorizations. To bridge this gap, we propose the Accelerated Trainable-SKM (AT-SKM) Net framework. To concentrate computation on the active constraints and eliminate redundant calculations, we introduce a hybrid sampling strategy guided by a topology-aware heterogeneous GNN model. To efficiently handle topological shifts in graph-based constraints, we employ a Cholesky Update mechanism that theoretically reduces the equality projection complexity from O(N^3) to O(N^2) under low-rank perturbations. Experiments on random geometric graphs, N-1 Security-Constrained DC-OPF, and minimum-cost gas transport problem demonstrate that AT-SKM reduces iteration counts by up to 85% and achieves 2.95x-7.29x SKM layer speedups, while maintaining zero constraint violations.

We consider the decision of whether to return an existing draft answer or revise it using retrieved evidence, as in answer-revision systems. Draft confidence estimates whether the current answer is correct, but the decision requires estimating the effect of a specified revision. For offline training and evaluation, we grade both the returned draft and its candidate revision under the same correctness judge, which makes repair, harm, and the gap to an oracle observable. We call this paired effect its recoverability, and we train policies to predict it before revision. On 25,870 held-out open-domain questions across three revision setups, a scorer trained on the paired outcome has greater area under the accuracy--revision-rate curve than a matched draft-correctness scorer in all nine Llama setup--seed fits, and gains 0.23--0.68 accuracy points on average at development-selected thresholds, a difference significant across training runs only for dense retrieval. The resulting policy improves on always revising and on average closes more than a third of the oracle gap, although it still applies 38--46% of the harmful revisions. When a draft-free standard-RAG answer is also available, however, choosing between the draft and that answer is stronger by about two points for Llama and four for OLMo, and adding candidate revision as a third option yields no significant gain. Recoverability describes one revision; its value as an available action also depends on the alternatives.

In multi-target regression, correlated targets are often coupled through multi-output Gaussian processes with an intrinsic model of coregionalisation (GP-ICM), assuming that sharing statistical strength improves overall performance. In practice, the benefits are inconsistent. Across the settings studied, we find that the main benefit of coregionalisation is joint uncertainty quantification rather than point prediction. Raw target correlation does not predict when coupling helps; in the separable GP-ICM settings studied here, residual correlation, the cross-target dependence left unexplained by independent per-target predictors, is the strongest predictor of joint-uncertainty gains. We introduce a lightweight diagnostic, $D_{\rm logdet}=-\frac{1}{2}\log\det R_{\rm res}$, which represents the idealised joint negative log-likelihood (NLL) gain from modelling a full rather than diagonal residual covariance and is computable from independent GPs alone. Across a controlled synthetic study, 16 multi-target benchmarks, and frozen transformer and convolutional neural network representations for keypoint regression, point prediction remains largely unchanged ($ΔR^2\approx 0$). In contrast, $D_{\rm logdet}$ strongly predicts observed ICM NLL improvements ($ρ_s=-0.83$, $p<0.001$), outperforming heuristics such as the feature-to-sample ratio. We also propose Residual-ICM, which preserves independent marginal variances while adding residual-correlation structure to the joint covariance. Residual-ICM achieves the best average joint NLL among the compared methods, while the diagnostic indicates when covariance coupling is likely to be useful. The diagnostic is specific to global Gaussian residual dependence, the structure captured by separable coregionalisation.

Graph neural networks (GNNs) have become a prominent approach for developing fast, topology-aware surrogates in electric power systems, supporting tasks such as power flow (PF) analysis, optimal power flow (OPF) estimation, and cascading failure analysis (CFA). Despite this growing use, formally verifying GNN-based models remains challenging, with existing methods limited in scope. We extend the neural network verification (NNV) framework to graph-structured inputs through GraphStar sets, a generalization of Star sets that captures uncertainty over both node and edge features. This extension enables the propagation of linear message-passing operations and the sound approximation of ReLU nonlinearities for GNN architectures, including graph convolutional network (GCN) and graph isomorphism network with edge features (GINE) layers. We evaluate GNNV across three power system tasks, PF, OPF, and CFA, on the IEEE-24, IEEE-39, and IEEE-118 test cases, as well as two standard graph classification benchmarks, ENZYMES and PROTEINS. Our results show that GNNV provides tighter robustness guarantees than CORA on graph classification models with ReLU-based activations and, for the first time, delivers edge-aware robustness guarantees for GINE-based PF and OPF models under joint node and edge perturbations.

Matrix completion, the problem of estimating missing entries in a matrix from noisily observed ones, underlies a diverse array of problems such as recommender systems and counterfactual outcome estimation in panel data. Many algorithms address the problem using regularized least squares, often with the nuclear norm as a regularizer, but this method yields a point estimate with no built-in uncertainty quantification. A Bayesian formulation is a natural alternative, and if the noise variance is known, the nuclear norm-based prior yields a log-concave posterior. Unfortunately, in practice, the noise variance will not be known a priori, so for a fully Bayesian approach, a prior must be imposed on it. We give the first sampler for this model with an explicit non-asymptotic guarantee: polynomial in the matrix dimensions and in the reciprocal of the target accuracy. Our technique is to discretize the distribution of the noise precision onto a grid and build a categorical posterior via thermodynamic integration. This extension is not specific to matrix completion and may be useful in other non-log-concave sampling problems where the non-log-concavity is restricted to a single variable and the joint distribution of the remaining variables is nonsmooth. Our contribution is a feasibility result: we show that a polynomial-time Bayesian sampler for this model exists at all, and the resulting complexity, while polynomial, is not intended as a deployable algorithm at current problem scales.

Automatic speaking assessment systems can provide holistic proficiency scores, but often lack interpretable measures that characterize pronunciation quality. We propose a native-reference phone-class geometry for measuring second language (L2) pronunciation deviation without requiring pronunciation labels, read-aloud prompts, or matched recordings of the same text from native and L2 speakers. Given a native speech corpus, we average frame-level self-supervised representations for each context-dependent phone-class and use singular value decomposition (SVD) to derive a compact native-reference coordinate system. For each L2 utterance, we compute the corresponding averages and project them into the native-reference space. We then demonstrate that the distances between L2 and native-reference coordinates for matched phone-classes show consistent negative correlations with holistic speaking proficiency on the Dev subset of the Speak and Improve Corpus 2025 (Spearman's $ρ\!=\!-0.53$) and with pronunciation quality on the learner subset of the English Read by Japanese Students dataset ($ρ\!=\!-0.34$). These findings suggest that the proposed geometry captures acoustic-phonetic information relevant for proficiency rating while remaining applicable to spontaneous L2 speech without matched native recordings.

Evaluations of LLM systems routinely average over small prompt sets and report models as a ranked table. We ask how much confidence such a table deserves, using LLM-based prompt-structure inference as the case study: eight open model variants across five families and 8B to 675B parameters, caching disabled, 293 raw intermediate representations persisted. The measured phenomenon is unstable to begin with. Identical calls do not reliably recover identical structure, with mean node-set Jaccard from 0.39 to 0.96 and 72% of prompt-model cells never node-set-perfect. Auditing the evaluation weakens its conclusions further, and this is our main contribution. Under a joint cluster bootstrap over prompts, only the bottom of the ranking is firm: the two least reproducible models hold rank in 99% and 86% of replicates, the middle four in 27% to 48%, and the top two in 68% each, so the table identifies the worst model reliably but does not reliably identify the best. Two equally defensible rules for merging repeated campaigns change four of eight rows and move the study-wide headline by 7 percentage points. Checking the inferred structure against ground-truth annotations shows reproducibility cannot be read as accuracy. And four of the eight endpoints were withdrawn within ten weeks of measurement, so the study as specified can no longer be run. Small-sample LLM evaluations can therefore look far more definitive than their evidence supports. We recommend reporting rank stability, per-cell provenance, executed sensitivity comparisons, raw per-run outputs, and a measurement date alongside any ranking.

The English Resource Grammar (ERG) is a hand-written computational grammar of English. Given a sentence, its processor, ACE, produces a formal meaning representation called Minimal Recursion Semantics (MRS): a graph of the sentence's predicates and their arguments. The grammar is bidirectional and can also turn an MRS back into an English sentence. \citet{hajdik2019} used the ERG's treebank to build a benchmark for that generation task, MRS to text, and trained sequence-to-sequence models to solve it. The parsing task, text to MRS, can be tested on the same sentences. We reconstruct their 10K-sentence test split, and score two large language models, Claude Sonnet~4.5 and Claude Opus~5, in both directions against their trained systems and against ACE, with no task-specific training. Given an MRS and three examples, Opus writes the sentence at 76.3 BLEU, ten points above their system trained on 72k pairs (66.1 BLEU), and comparable to their system trained on a million extra pairs (77.2 BLEU). Sonnet scores 65.7 BLEU, and letting it choose among ACE's own candidate sentences lifts it to 69.6, while a pooled judge that keeps Opus's own sentence among the candidates adds 0.6 points (77.0 BLEU). In the parsing direction, however, the models fall far behind ACE: asked for the MRS of the same sentences, they reach 57.2 (Sonnet) and 65.5 (Opus) F$_1$ on the graph's predicates and arguments against 91.0 for ACE, and exact-match the gold on about 1\% of sentences. We characterize the failure modes for the parsing tasks, and conclude that a generation score alone does not show that models understand formal semantic representations.

Advances in language modeling have been driven by scaling pretraining on ever more data. Yet, the training data is still largely curated on the model's behalf. A more general approach to pretraining would let the model learn to generate the data most useful for its own improvement. This would provide an effectively unbounded source of training data, limited by compute rather than human knowledge. We introduce Self-Play Pretraining with Zero Data, an initial proof-of-concept towards realizing this vision. Our procedure casts synthetic data generation as a search over the space of all computable structure, taking inspiration from Solomonoff induction. Starting from random initialization, two models learn in tandem: a generator proposes programs interpreted by a universal Turing machine, generating byte sequences, while a learner autoregressively predicts these byte sequences. The learner is trained with standard cross-entropy, while the generator is trained with reinforcement learning to produce sequences at the frontier of the learner's capabilities, yielding an adaptive curriculum. A universal Turing machine gives us a search space over all computable data-generating processes, imposing little domain-specific structure, and self-play searches over this space for useful training data. We test whether zero-shot performance on natural data improves predictably with self-play compute; this is a clean test of transfer since neither generator nor learner is trained on natural data. Across several natural datasets, zero-shot loss exhibits predictable scaling in compute. The models also exhibit in-context learning, and discover recognizable mathematical sequences during training.

Deep learning inference and training performance depends critically on GPU kernel efficiency. Modern compilers such as PyTorch Inductor automatically generate GPU kernels from high-level model code, but frequently underperform expert-written implementations by wide margins. Recent LLM-assisted kernel optimizers can close this gap for standalone kernels, yet treat compiled models as black boxes, generally optimizing individual standalone kernels without respecting the compiler's structural decisions or verifying the model end-to-end. We present KernelOPT, a multi-agent system that treats compiled models as structured artifacts. It preserves vendor library calls (cuBLAS, cuDNN) and exclusively targets generated Triton sub-kernels using five profiling-guided LLM agents. A four-gate verification cascade of static validation, multi-seed correctness, model-level float64-fallback verification, and performance gating filters candidates during optimization and verifies the re-stitched model end-to-end. If no candidate passes all four gates, the system preserves the compiler baseline. The system accepts PyTorch nn.Modules, standalone Triton kernels, and Helion kernels. Evaluated on 250 KernelBench problems, KernelOPT achieves geometric mean speedups over \texttt{torch.compile} of 1.40$\times$ (Level 1: 51/100), 1.15$\times$ (Level 2: 31/100), and 1.07$\times$ (Level 3: 12/50) across all problems.

AI-assisted job-search tools have become increasingly popular by making it easier to find and apply to jobs. But by making it easier for applicants to generate and tailor application materials, they can also reduce how informative those materials are about applicant fit. We study this tradeoff in a hiring market where applicants differ in experience and latent match quality and firms use noisy application materials to decide whom to screen. We ask how AI affects downstream screening and hiring, and which applicants are most adversely affected. As application materials become less informative, a Bayesian firm rationally relies more heavily on coarse observables such as prior experience. Among the four applicant types defined by experience and compatibility for the job, inexperienced-compatible applicants are the most exposed: they lack observable experience and lose the individualized information that could distinguish them from other inexperienced candidates. When screening is costly, these changes can also generate inefficient screening failures in which firms screen no applicants or screen only experienced applicants. We then show that multistage hiring can arise as an endogenous firm response: a relatively inexpensive intermediate assessment allows firms to acquire new evidence of fit before costly full screening. This can restore screening opportunities that disappear under one-stage hiring and give inexperienced-compatible applicants a path to screening. Our results show how AI can shift the central friction in hiring from submitting applications to obtaining credible evaluation, creating entry barriers for high-fit workers without prior experience. Multistage hiring can endogenously arise in response, restoring evaluation opportunities that would otherwise disappear and helping preserve market functioning.

In the Era by Eon benchmark, each question states the rules for its answer, and code computes the answer from a generated company's data. When agents can run code, the four strongest models each answer 22 to 25 of 27 such questions, so the benchmark barely separates them. We add eight question templates that depend on hidden facts. No question or document states a hidden fact, and the records that seem to hold it show something else. Other data implies it. For example, the sales system says a customer dropped a purchase because of timing. On a recorded call, the customer blames an outage. For each generated company, code fills each template and computes an exact answer without a language model. We evaluate 12 agents. Each pairs a model with an agent program, which connects it to the company's systems. The best agent answers 18 of its 24 attempts, three per question, correctly. Four of the six models answer at most 6 of 24 with any program. The hardest questions require picking one of several similar records, such as which of three renewal offers a customer signed. All agents together answered two such questions correctly in only 1 of 84 attempts.

Improving the scientific coding capabilities of large language models (LLMs) requires high-quality training data. However, such data remain scarce because manually authoring realistic problems is costly and time-consuming, while systematically covering diverse scientific domains and algorithmic combinations remains challenging. To address this, we introduce SciWalker, a framework for synthesizing scientific coding problems through operator-chain sampling and execution feedback. The framework combines scientific library interfaces with operation modes to instantiate operators, organizes them into operator graphs, and samples operator chains as computational workflow cues. Guided by these cues, we adopt LLMs to generate scientifically grounded problem statements, reference solutions, and tests, with failed generations iteratively repaired using execution feedback. By combining structured workflow composition with verification and quality review, SciWalker enables scalable task generation while promoting scientific grounding, computational diversity, and executability. Using this framework, we construct 8,178 high-quality problems spanning 5 scientific domains and 32 subdomains. To evaluate their training utility, we conduct reinforcement learning on Qwen3.5-9B using the GSPO algorithm. This training improves SciCode subproblem accuracy by 9.9 percentage points, from 29.3% to 39.2%, with gains across scientific code generation, code repair, and reasoning benchmarks. The code for SciWalker is available at https://github.com/lichenx1/SciWalker.

We present NNV3, the latest version of the Neural Network Verification (NNV) tool, a MATLAB framework for formal verification of deep learning models and learning-enabled cyber-physical systems. Building on the set-based reachability foundation of NNV 1.0 (FFNNs, CNNs, NNCS) and NNV 2.0 (RNNs, SSNNs, neural ODEs), NNV3 introduces new members of the Star-set family: ModelStar for verifying networks under weight perturbation, VolumeStar for video and 3D volumetric inputs, and GraphStar for graph neural networks. A conformal-inference-based probabilistic reachability mode complements sound analysis for problems where deterministic verification is intractable, while FairNNV certifies counterfactual and individual fairness properties over continuous input regions. NNV3 introduces new benchmarks for malware detection, graph-based power-system models, medical imaging, variable-length time series data, and action recognition. NNV3 also incorporates tutorials and developer guides through a unified documentation site. This paper details these major updates, demonstrating NNV's maturation into a comprehensive, robust, and accessible verification tool for a diverse range of AI systems.

If a language model can recognize code it wrote, it may favor that code as a judge, and instances of one model monitoring each other could collude. We test this zero-shot on current commercial models. Five LLMs generate solutions to MBPP, HumanEval, and DS-1000, seven more to MBPP, and models act as evaluators in four tasks: picking their own solution from a pair, judging whether a single solution is their own, identifying which of two solutions a named model wrote, and judging quality blind. In the single-solution task, balanced accuracy is 49-58% for all 15 model-benchmark combinations, while raw accuracy (38-67%) mostly reflects how readily a model claims authorship. In the pairwise task, accuracy across 14 evaluator-opponent combinations correlates at r=0.93 with how often the evaluator's solution is longer. Attribution to a named model succeeds on some pairs and is consistently inverted on others. A rule-based normalization that strips docstrings, comments, type hints, and local names preserves Pass@1 and leaves ten of twelve re-tested results at chance; the other two follow a length difference it leaves, although a trained classifier still separates most normalized pairs. Claude Haiku's self-preference also disappears. We recommend reporting balanced accuracy, heuristic baselines, and label consistency.

Resistive switching in oxide-based devices is widely governed by stochastic defect processes, yet a predictive link between fabrication conditions and functional behavior remains elusive. Here, we establish a multiscale framework connecting plasma-defined deposition conditions to macroscopic device functionality in sputtered SiO$_x$/Cu/SiO$_x$-based systems. By combining large-scale statistical analysis of more than 50,000 experimentally characterized devices with physics-based plasma and atomistic simulations, we show that device behavior does not emerge from deterministic process-to-performance mappings, but from a probabilistic cascade spanning defect formation, defect-state evolution, and functional-regime emergence. Data-driven clustering reveals a continuous functional state space composed of operational switching types, while inverse modeling identifies the reconstructed oxygen-vacancy density as an effective latent descriptor capturing the combined influence of structural disorder and defect topology. This latent descriptor is strongly coupled to both Cu redistribution and electrical response, linking otherwise hidden material properties to observable device characteristics. Furthermore, macroscopic switching behavior is argued to arise from ensemble integration across spatially heterogeneous subdomains, providing a physical explanation for the pronounced variability of large-area devices. These findings shift the perspective from deterministic defect engineering toward probabilistic defect-state design and establish a physically grounded framework for understanding and controlling functional variability in such oxide-based systems, such as memristive or resistive-switching devices.

Deployment-oriented compression is attractive for resource-constrained brain--computer interfaces (BCIs), but whether it changes adversarial vulnerability remains unclear. On BCI Competition IV-2a, we compare 32-bit floating-point (FP32) EEGNet and ShallowConvNet models with global magnitude pruning and simulated INT8 post training quantization (PTQ) and quantization-aware training (QAT) across nine subjects and three seeds. Simulation provides differentiable quantize--dequantize models for white-box attacks and gradient analysis, while native TensorRT deployment is used for validation. Accuracy-preserving compression does not improve direct robustness: at $ε=0.005$, EEGNet PGD accuracy remains 22--24\% across FP32, 50\% pruning (P50), PTQ, and QAT. However, P50 reduces bidirectional transfer efficiency to 0.963/0.928 (FP32$\rightarrow$P50/P50$\rightarrow$FP32), versus 0.994/0.997 for PTQ; the same trend holds for ShallowConvNet. Gradient alignment shows a corresponding separation, while native PTQ agrees with simulated clean/adversarial predictions in 95--98\% of cases. These results show that direct robustness, adversarial transfer, and deployment efficiency are distinct properties of compressed EEG decoders.

Planners built on visual world models commonly score each predicted outcome by its distance to the encoded goal image. We show that this target can limit control even with exact dynamics and globally optimal short-horizon search: reaching a goal may require actions that initially move away from it. With frozen LeWM models, intermediate targets substantially improve action synthesis and recorded-action ranking on Cube, PushT, Reacher, and TwoRoom. Learned targets and targets drawn from observed experience both produce these gains. We introduce Anchored Planning, which retrieves a recorded segment whose start and end resemble the current and goal observations, then aims at an observation shortly after its start. The frozen model scores actions toward this target from the current state. Without additional training, planning toward observed targets outperforms the released LeWM planner on every task in our long-range evaluation. Additional final-goal search falls short of the same gains. Lower successor-prediction error need not translate into better control. Success also depends on how far ahead the target is placed and on shrinking the retrieval span as execution advances. Changing only the target lets the same frozen model and planner reach goals that final-goal scoring misses.

A synthetic survey can reproduce the average answer while misrepresenting how people differ, how their answers relate to one another, or how they respond to changes in conditions. We introduce the Artificial Societies Benchmark to help researchers assess whether synthetic populations support their intended analyses. The framework combines eleven tests across internal, construct, and external validity, drawing on twenty human sources and comparing nine language models. It connects each research use to the evidence it requires and tests how results change with the information we supply about respondents. Importantly, strong performance in one domain does not establish fidelity in the others. Models often answer too consistently, compress response scales, and alter relationships between traits whilst richer profiles improve prediction for some models and worsen it for others. The resulting scorecard helps researchers identify which aspects of a synthetic population can support their analysis and where researchers need further human evidence.

Multi-agent deliberation can improve performance, but what happens when some agents do not act in good faith? In practice, an agent may be deceptive and work to subvert the group, whether through its own objectives or external instruction. We study how susceptibility to deception scales as groups increase in size and deceivers become more prevalent. It is not the number of agents in the group that matters, but the proportion of deceivers. We observe that the defection rate, how often initially correct agents switch to an incorrect final answer, rises linearly with this proportion. Whereas humans in comparable conformity studies are reliably swayed only when misleading confederates form a majority, LLM agents defect regularly even when deceivers remain a minority. Susceptibility also depends on which models are interacting, especially on the honest agent side. Unexpectedly, allowing deceivers to coordinate privately can make them less effective. Altogether, our results show that adding more agents is therefore not a sufficient defense, because the adversary can simply scale with the group.

Frontier language models are rarely used in clinical workflows because the realistic, longitudinal benchmarks needed to develop them are scarce. Real electronic health record (EHR) data cannot be openly shared due to privacy, ethics or data use issues and it does not contain verifiable ground truth since the chart records only reflect what clinicians documented. We introduce Synthetic Hospital, an open, fully synthetic, fact-grounded longitudinal EHR benchmark that resolves the open sharing and verifiable ground truth barriers. Built entirely from public medical-education material with no protected health information, it comprises 1,268 longitudinal patients and 5,602 encounters, where every diagnosis, finding, and temporal relation is grounded in standard ontologies (ICD-10-CM, SNOMED CT, LOINC) and with a complete provenance chain back to its source medical education material. Synthetic Hospital is served through a simulated hospital record system that mirrors real EHR infrastructure (standard interoperability APIs, role-based access and function-calling interface). In a blinded review, physicians distinguished its records from real patient charts at near-chance rates (53\%). Across 10 frontier and open models, none approaches ceiling: the best model reconstructs a patient's longitudinal problem list with a severity-weighted F1 of 0.73, level with the mean of seven physicians on a matched subset but well below the best of them (0.89), and misses roughly half of clinically relevant findings when summarizing a chart. Overall, these results highlight that Synthetic Hospital is a difficult and realistic test of clinical AI performance.

Many LLM inference problems, including model routing, prefix-cache management, prompt trimming, and test-time search, can be viewed as optimization over a tree. This structure arises naturally from autoregressive generation: every prefix defines a node, and its continuations form a subtree below it. Internal nodes of the tree provide cheap but biased estimates of a region's value, while leaf evaluations are expensive but accurate. Hierarchical bandit methods can exploit this structure, but typically require a specific smoothness schedule to be specified in advance, even though real objectives are often only piecewise smooth and their optima may lie near sharp boundaries. We introduce CANOPY, a multi-fidelity tree bandit that learns where the smoothness prior is valid rather than assuming it globally. CANOPY uses cheap random-path probes to construct an online certificate of local aggregation bias, then directs expensive leaf evaluations toward cells where the certificate detects a smoothness violation. We prove fixed-budget and regret guarantees whose additional cost is additive in the number of discontinuities, recovering the smooth-tree rate when no violations are present and approaching structure-blind search as violations become dense. Across routing, top-$k$ identification, test-time search, caching, and prompt trimming, CANOPY consistently improves matched-budget performance, including $2.9\times$ higher top-10 recall on a 1000-model pool, $1.6\times$ more SWE-bench Verified issues resolved than best-of-$N$, and $3.6\times$ lower median time-to-first-token with prefix caching.

Language models advise people, keep them company, and write software while they sleep. Measuring what they do is hard: behavior has to be sampled repeatedly across models, prompts and releases, most of it lives in unstructured text that has to be coded before it can be counted, and the result has to be legible and rigorous enough to meaningfully compare models and vendors. To address these constraints, we present a simple, cheap, scalable, and replicable model for studying model behavior. Each study is a frozen, public stimulus run identically on a cross-vendor panel, at a few dollars per model or less. Each reads its transcripts one of three ways, chosen by how much interpretation the behavior needs: exact match on a clamped reply, a codebook applied by LLM judges whose agreement with a human coder is reported per code, and an instrumented environment that records what an agent did independently of what it said. Run across four years of model releases from both frontier and open-source labs, these instruments find four things. Convergence: asked to pick a word, 27 of 44 models answer serendipity at least once in four tries. Resistance: a trailing "right?" moves endorsement by up to 32 points, and the sign flips from sycophantic to resistant as generations advance, keyed to the tag's surface form. House: whether a model holds a position under pressure tracks its generation, and how it holds tracks the lab that built it. Account: told to do something the documentation in their repository contradicts, some coding agents never went along silently and others always did, and the same model can change with the harness it runs in. Re-run on every release, batteries like these track how behavior is changing across vendors and over time.

Financial institutions operate under dense, frequently amended rulebooks, and answering a compliance question correctly requires not only fluency but verifiable grounding in the authoritative text. Large language models are attractive for this task, yet the models that firms can realistically deploy on-premise are compact ones, and compact models hallucinate obligations. We study whether a carefully domain-adapted retrieval-augmented generation pipeline closes that gap. Our retriever is built in three stages on top of LegalBERT: entailment tuning that recasts question--passage matching as premise--hypothesis reconstruction, contrastive tuning with in-batch negatives, and score-level fusion with BM25. Our generator is a compact model (2B--12B parameters) served under 4-bit quantization, either prompted or adapted with retrieval-aware fine-tuning (RAFT) through LoRA. On ObliQA, a question-answering benchmark built from the Abu Dhabi Global Market rulebooks, the staged retriever raises Recall@10 from 0.256 to 0.774 and outperforms BM25 (0.678) and E5-large-v2 (0.758), the strongest general-purpose dense encoder we tested. RAFT-LoRA then improves the composite RePASs answer-quality score for every model we could adapt, with the largest gain on the weakest one. However, the adapted models do not transfer to Australian case-law questions, and a closed-book model that receives no passages at all scores within 0.011 RePASs of the full pipeline while producing answers that cite nothing and misstate obligations. The retrieval gain is therefore measured directly, the generation gain is a gain in RePASs rather than demonstrated grounding, and grounding itself requires an evaluation protocol that RePASs does not provide.

Vietnamese speech research is constrained by resources that isolate automatic speech recognition from speaker, dialect, code-switching, and deepfake analysis. We introduce VietPrism, an open, multi-domain corpus that brings these dimensions together at scale: 993.4 hours and 403,941 bona fide utterances from 1,262 verified speakers across 8,388 real-world videos. To our knowledge, it is the first large-scale Vietnamese corpus to jointly provide transcripts, consistent speaker identities, five dialect groups, and naturally occurring Vietnamese--English code-switching, which constitutes nearly half of the corpus by duration. We further create over 3.1K hours of spoof speech with four open-source and commercial synthesis systems. Every spoof is conditioned on a verified speaker reference and paired with a transcript- and speaker-matched bona fide utterance, enabling unique controlled evaluation with reduced lexical and identity confounds. Zero-shot evaluation of five pretrained multilingual detectors reveals striking brittleness: EER greatly varies across detector--generator pairings, while recent multilingual detector DFA-1B degrades from 16.3% to 33.6% as speaker similarity increases. Dialect-stratified results expose further model-dependent disparities. By unifying natural linguistic diversity with controlled spoof generation, VietPrism provides a challenging foundation for Vietnamese speech modeling and trustworthy audio-deepfake detection.

Sustaining industrial recommendation research requires using the results of one experiment to decide what to investigate next. We present AgentX-Model, the next generation of AgentX's model research framework, which connects proposal development and model experimentation within sandboxes defined by business inputs and prediction tasks. AgentX-Model adopts a dual-agent architecture comprising a Research Agent and a Model Agent. The Research Agent develops independently reviewed proposals from papers and experimental findings, while the Model Agent conducts multi-round investigations and returns code, measurements, and unresolved questions. Using the returned results, the Research Agent selects a starting implementation and formulates the next research question, allowing subsequent experiments to build on earlier findings. We organize this continuing research around four actions: Reproduce, Follow-up, Composition, and Diagnose. The first three actions drive routine research, while Diagnose acquires the evidence needed to choose a repair, including for issues raised by business feedback and online evaluation, such as prediction bias measured by PCOC. Across the production evaluation, 560 of 636 completed model-changing experiments recorded AUC above their business baselines. As research continued, some experiments recorded AUC above every comparable ancestor in their lineages. The five latest online A/B evaluations across different business settings reported gains including 10-15% in acquisition efficiency, 15-20% in target-segment advertising spend, and 0.3-0.8% in watch time; the watch-time model used approximately 10% fewer FLOPs and parameters. A dependency-aware historical-replay benchmark further evaluates research allocation, with initial results showing no consistent efficiency gain from more complex scheduling when agents already analyze and select concrete candidates.

Post-training quantization of vision--language models (VLMs) is typically assessed through aggregate task accuracy and memory savings, but preserving a headline score does not guarantee preservation of visual grounding behavior. We present GHOST-Q, a cross-precision controlled evaluation of three 8B VLM families under FP16, INT8, and NF4 across utility and hallucination-sensitive benchmarks. Rather than comparing only aggregate accuracy, we pair FP16 and quantized predictions item by-item to quantify how compression redistributes grounding successes and failures. Five of six quantized variants preserve MMStar accuracy within $\pm2$ percentage points, yet 10 of 36 paired effects remain significant after false-discovery-rate correction, nine on hallucination-sensitive conditions. Same-device A100 profiling further demonstrates that substantial memory reduction does not necessarily mean lower inference latency. Finally, an open-ended AMBER audit reveals strong generation budget censoring whose severity varies by architecture and precision. These results show that quantized VLMs should be evaluated jointly for aggregate utility, grounding reliability, generation behavior, and realized deployment efficiency.

AI teaching assistants (AI TAs) backed by large language models (LLMs) and pedagogical guardrails are increasingly being integrated into programming courses, providing students with scalable access to hints, conceptual explanations, and code-level feedback. However, guardrails may also create friction. If students feel that the support provided is overly restrictive or poorly contextualized to their current progress, they may bypass approved tools for general-purpose LLMs. To investigate how AI TA design affects students' learning experiences, we conducted a randomized controlled trial with 132 students in an introductory programming course. Students completed three tasks related to code-writing and debugging and were randomly assigned to one of four AI TAs varied across two dimensions: pedagogical guidance style (Socratic vs. Direct instruction) and context awareness (no context vs. full context of the problem and student solution). We examined students' perceptions, interaction behaviors, and evidence of post-task comprehension. Students rated the Socratic AI TA with full context least favorably, reporting significantly lower perceived support for task completion. Descriptively, this condition also showed the highest observed interaction stress, the highest rate of external LLM use, and the lowest proportion of post-task explanations demonstrating full comprehension, though these differences were not statistically significant. These findings suggest that guardrailed AI TAs are not automatically better for learning. Instead, their effectiveness depends on how pedagogical guidance and contextual awareness are balanced in ways that students experience as useful, supportive, and worth continuing to use.

Synthetic data can scale training supervision when real-world data are limited, but noise and distribution mismatch can reduce its value. Existing synthetic data selection methods often emphasize fidelity or diversity rather than the learner's evolving needs. We propose FROST, an online framework that estimates synthetic-data utility through gradient feedback anchored in real training data. It calibrates batch utility against recent history to determine when filtering is needed and filters samples only in out-of-band batches to determine what to retain, without an external verifier or held-out validation set. Experiments on two public benchmarks for image classification and LLM fine-tuning for text-to-SQL show that FROST filters out around 20--30% of the synthetic data while improving real-task performance compared with training on the full synthetic data pool. We further apply FROST during training in a large-scale industrial ads re-ranking system, achieving significant performance gains over a highly optimized production baseline, demonstrating its effectiveness and generalizability.

Semantic IDs (SIDs) encode each catalog item as a short token sequence, enabling generative recommenders to predict the next item autoregressively. Reasoning-enhanced variants, an increasingly common extension, first generate a textual trace and then decode a next-item SID by beam search. Such recommenders are commonly trained with group-relative policy optimization under an exact-match SID reward, which is sparse in large catalogs. Two failure modes follow. When all rollouts in a group miss the target, the group yields zero advantage and no learning signal. Rollouts sharing the same SID reward receive identical advantages, however much their traces differ. In both cases the reward reflects only the decoded SID, never the reasoning that produced it. This creates a credit-assignment gap. We address this gap with retrieval-grounded query attribution. Each trace is structured into a history summary, a set of interest hypotheses, and a final SID. A frozen retriever executes every hypothesis as a catalog query, so that each hypothesis becomes independently verifiable rather than judged only through the final SID. A rollout is rewarded when any of its queries retrieves the target within the \mbox{top-$K$}, and per-query hit indicators localize that reward to individual hypotheses. Credit is thus assigned at the span level: only hypotheses that individually hit receive positive retrieval advantage, while the retrieval channel never updates the final SID span. Rollouts that share a SID reward can therefore receive different updates. Across experiments on three Amazon Reviews datasets, this yields consistent improvements in SID recommendation. On Video Games, an oracle analysis further reveals the potential of interest-conditioned SID decoding: selecting the target-relevant query among generated interests improves both recall and ranking.

This paper presents a Solidity, Hardhat, React, MetaMask, and ethers.js prototype for hospital ethics committee voting. Role controls, case-state checks, duplicate vote controls, and a receipt hash support public audit and transaction inclusion verification. Because vote events expose wallet addresses and vote values, the design provides pseudonymous auditability, not anonymous or secret-ballot voting; the receipt is neither receipt-free nor coercion-resistant. Evaluation reports 22 passing functional tests and local Hardhat gas use, including 284,137 gas per vote. A 12-participant simulation used assumed probabilities and is not human-subject evidence. Residual risks include multiple wallets, administrator or frontend compromise, credential reassignment, front-running, denial of service, and untested adversarial paths. Confidential deployment requires governed enrollment, encrypted ballots, independent audit, adversarial testing, reproducible benchmarks, and a real user study.

Estimating heterogeneous treatment effects from observational data is difficult because the most appropriate inductive bias varies with overlap, treatment imbalance, prognostic structure, and sample size. We introduce the Geometry-Diverse Anchor-Correction Expert Ensemble (GeoACE), a five-expert framework that combines a common anchor-correction estimator with complementary overlap-aware and outcome-guided geometries. Its task-level ensemble weights are learned only from internal validation predictions, frozen before test evaluation, and then applied to experts refitted on the complete development sample. The fifth expert, O-Phi-ACE, constructs an outcome-free, overlap-aware statistical projection from covariates and treatment assignment and replaces the anchor input with this lower-dimensional geometry. We evaluate GeoACE against 11 comparators on eight benchmark protocols. Adding O-Phi-ACE reduced mean sqrt(PEHE) relative to the four-expert ensemble on all seven benchmarks with individual-effect truth, winning 998 of 1,225 paired tasks; the change on JOBS policy risk was negligible. The five-expert ensemble ranked first on IHDP100, IHDPA, and IHDPB and second on NEWS, differing from the NEWS leader by 0.13%. Across the seven sqrt(PEHE) benchmarks it obtained the lowest observed average rank (3.714), although the omnibus Friedman and Iman-Davenport tests were not significant (p=0.328 and p=0.330). Using the same five frozen experts, inverse-DR weighting was consistently better than winner-take-all selection, convex DR fitting, R-stacking, and causal Q-aggregation in benchmark-balanced analyses, but was statistically indistinguishable from equal weighting and DR ridge shrinkage. The evidence therefore supports geometry-diverse expert libraries and leakage-free aggregation as a robustness strategy, not universal superiority of either GeoACE or one weighting rule.

Generative recommendation reformulates item retrieval as sequence generation, allowing a unified model to directly generate the next item from a user's interaction history. Semantic IDs further make this paradigm effective and scalable by representing each item as discrete codes, enabling knowledge sharing among semantically related items. Recent studies introduce explicit reasoning before Semantic-ID generation, helping models summarize user interests and infer possible preference transitions. However, reasoning is not inherently beneficial: Inaccurate or uninformative reasoning may mislead subsequent item generation and ultimately degrade recommendation performance. This raises a central challenge: how can a recommender select and learn effective reasoning traces and progressively evolve toward better reasoning from its own generations? In this work, we propose Evo-Rec, a three-stage framework for learning better reasoning and further enhancing it through reinforcement learning. First, we align Semantic IDs with their textual and behavioral contexts, enabling the model to understand and generate item identifiers. Second, we sample multiple candidate reasoning traces and retain those that improve the prediction of the ground-truth item, providing a stronger reasoning initialization through supervised fine-tuning. Third, we further optimize the reasoning policy through reinforcement learning with catalog-constrained item generation and ranking-aware recommendation feedback. Experiments on three Amazon Review benchmarks show that Evo-Rec consistently outperforms discriminative, generative, and reasoning-enhanced recommenders across all evaluation metrics. These results demonstrate the effectiveness of our framework in learning better reasoning for SID-based generative recommendation.

General-purpose vision-language models (VLMs) bring broad knowledge and spatial reasoning to robot manipulation, yet existing systems either use them indirectly, to predict constraints or write programs, or give them a view of the scene rather than a world in which to act. We present World Action Agent (WAA), a multi-agent harness through which VLMs pilot robots with basic tools, making every decision within a visual action workspace. The workspace has three properties. Contact views, selected automatically from the scene geometry, present the scene around the current interaction. Action rehearsal turns each action into an editable proposal that the agent, alone or through an Imagination Agent, previews and revises against planning feedback before execution. In-view correction closes the loop between observation, rehearsal, and low-level execution, letting the agent remove residual offsets in the view where it observes them. Through the same workspace, WAA acquires embodied procedural knowledge in two ways: it evolves multimodal skills from expert videos and human teaching under evidence-based review and consults them through a Skill Agent, and its interaction traces train smaller VLMs to pilot the same harness. On LIBERO-Pro, WAA with skills evolved only from LIBERO-90 reaches a state-of-the-art 75.6% average success, outperforming end-to-end VLAs, code-as-policy agents, and a visual-harness baseline with the same backbone; the same skills remain effective on robosuite without further learning. Fine-tuning Qwen3.5-9B on harness traces raises its out-of-domain success from 1.7% to 43.3%.

Textured Gaussians improve local appearance capacity, but assigning the same texture resolution to every primitive wastes storage on low-detail or weakly visible regions. We introduce AdaTex4D, an adaptive texture-capacity module for deformation-based 4D Gaussian Splatting. Each Gaussian carries packed RGBA triplanes whose two axes grow independently according to visibility normalized screen-space gradients and deformed local scales. Experiments on N3DV and PanopticSports show that AdaTex4D reduces texture storage by more than half while preserving reconstruction quality. Under fixed memory budgets, adaptive allocation also improves quality over uniform texture assignment and reduces overall model and peak memory. These results show that dynamic, anisotropic texture allocation provides a more efficient way to distribute local appearance capacity in 4D Gaussian representations.

Many iterative algorithms rely on bootstrapping. A variable is updated using a second, frozen copy as a target, which is periodically replaced with the updated variable. Majorize-minimize and inexact proximal-point methods share this structure, as does temporal-difference (TD) learning. However, existing convergence guarantees for scenarios that combine sampled updates with targets refreshed only every $K$ steps rely on the specific structure of the update, such as linear approximation or gradient-based inner steps, and on uniformly bounded sampling error. We instead model the sampled update as a stochastic operator on the parameter space, which reduces the analysis to a contraction argument that needs no gradient structure and allows the sampling error to grow with the iterates. Within this framework, we derive a finite-time bound for i.i.d. samples and any target-update period $K$. We show that the iterates converge geometrically in root mean square to a ball around the fixed point, provided the sensitivity to the frozen target is smaller than the contraction slack of the inner map. Existing deterministic frozen-target contraction and stochastic-gradient-type bounds follow as special cases of our framework, and simulations of TD learning reproduce the predicted contraction rate and scaling of the error floor with the step size.

Fine-tuning large language models on new objectives can improve helpfulness, instruction following, or domain-specific performance, but it can also induce regressions on safety-critical prompts. Existing safety-preserving fine-tuning methods typically control average safety loss or use weighted auxiliary penalties, which can obscure rare but severe failures. We propose a chance-constrained formulation for safety-preserving fine-tuning that limits the fraction of safety examples whose degradation relative to a reference model exceeds a prescribed threshold. Because the resulting empirical chance constraint contains a discontinuous indicator, we introduce a differentiable majorization of the violation rate, yielding a tractable conservative constraint. We then develop a constraint-aware gradient descent method that treats the majorized constraint as a safe set in parameter space and minimally modifies the fine-tuning direction to preserve feasibility. The resulting update admits a closed form and produces a tail-aware safety correction that emphasizes examples near or above the degradation threshold. We conduct an extensive set of experiments on harmful fine-tuning across three different tasks and three models and show that our approach consistently outperforms the baselines that exist in the literature. These results suggest that safety preservation in LLM fine-tuning is better viewed as a reliability-constrained optimization problem than as average-risk regularization.

Fine-grained object detectors are commonly evaluated with confusion matrices, which show where the model is confused but not why, nor whether the confusion can be reduced. We argue that confusion can be attributed to distinct, separable sources, each quantitatively measurable, turning a passive measurement into actionable guidance. We present $A^2E^2$, a diagnostic tool that decomposes the sources of confusion along two axes, $\{$aleatoric, epistemic$\} \times \{$within-class, between-class$\}$, giving a $2\times2$ taxonomy that enumerates the source types. Each quadrant is measured by its own quantity, computed in one of three places (input geometry, output-space disagreement, and the bias-parameter posterior), so the two epistemic sources are separated by construction rather than by an empirical correlation. On fine-grained aircraft detection, the four quadrants become four named sources with their own remedy verdict: affinity (geometric similarity, irreducible from size alone), heterogeneity (geometrically heterogeneous sub-variants, pointing to re-labeling rather than more data), contested (an insufficiently trained but learnable boundary, improvable), and collapsed (a class starved of data, reducible). After attributing the confusion to a specific reducible source, we apply a targeted intervention and verify experimentally that it reduces the diagnosed source specifically while leaving the irreducible sources unchanged. $A^2E^2$ thus turns confusion measurement into a concrete, validatable and actionable "diagnosis" in which the same off-diagonal mass can carry opposite causes and opposite remedies. We also state this framework's limits, including which sources are only partially identifiable on this specific dataset and why.

We study a matching mechanism where agents and objects are described by features rather than complete rankings. A single spectral projection reduces the problem to a one-dimensional sort, computable in O(N log N) time. We prove that on descaled features and preferences, our algorithm obtains the exact Nash Social Welfare (NSW) optimum within the projected space, with an unconditional utilitarian-welfare guarantee and a conditional NSW guarantee. The proposed mechanism is stable against exogenous noise but not strategy-proof; we provide an explicit profitable misreport. On an agentic AI shopping application, the diagnostics correctly anticipate both a success and a failure case. A 100-instance robustness study confirms the findings.

Before a product or policy change ships, the question that matters is how people will react to it. Augur rehearses that reaction offline: it builds a typed knowledge graph from the change documents, populates a grounded persona market, simulates the interaction, and returns an auditable decision memo recommending one of five actions. We assemble Gold-50, fifty real product and policy episodes whose real-world outcome is known, adjudicated against the public record, and score the five-way release verdict against it. Our central finding is methodological and negative: most of the measured gap between frontier cloud models and open-weight models we fine-tune and serve offline is attributable to an under-specified evaluation, not a difference in capability. We show this three ways. First, the prompt envelope alone can dominate the score: holding weights, cases and scorer fixed, one system -- a LoRA-SFT adapter on Qwen3-32B -- swings from 0% to 73%. Second, in a matched 2x2 ablation, defining the decision taxonomy in the prompt -- with no model change -- lifts every frontier model by +24 to +34pp; under the under-specified prompt, Qwen3-32B LoRA-SFT served offline beats all three frontier models (paired McNemar, Holm-corrected), and once the prompt is fair no significant difference from any of them is detected. Third, agreement with the distillation teacher rises without accuracy following, and the full pipeline amplifies a systematic "over-doom" bias rather than improving the verdict. Separately, we validate the reaction layer on its own terms: blind judges across four model families find the synthetic reaction recovers 67-90% of the concerns the public actually raised, and a pre-registered ablation locates its value -- largest where the decision is hardest, redundant near ceiling. The pipeline that regenerates every number and figure here is available from the authors.

State tracking requires composing a sequence of updates, but accuracy alone does not reveal what a model has learned. We study neural networks trained to predict the running product of group elements. We identify quotient solutions in Transformers, where models recover the quotient class while predicting nearly uniformly among its members. The reciprocal of class size predicts partial accuracy without a fitted parameter, extending parity-based accounts to non-parity quotients. Our baseline Transformers' predictions change little under prefix reordering beyond the exact-tracking frontier. We prove that, for finite groups under uniform i.i.d. full-group inputs, optimal order-blind exact accuracy converges to the reciprocal of abelianization class size as prefix length grows, consistent with the observed abelianization plateaus. Sequential updates permit more: any partition into right cosets of a subgroup, normal or not, survives sequential updates. In our census of standard Transformers, every recovered coset partition comes from a normal subgroup, whereas parameter-matched recurrent networks pass through both normal and non-normal right-coset stages during training. On $A_5$, we identify low-dimensional subspaces of the recurrent state that encode non-normal cosets. In the three-dimensional cases, coset mean vectors form approximate dodecahedra, and swapping the state components in these subspaces transfers the donor's coset state through a shared input suffix. Our results connect partial accuracy, learning stages, and internal computation through the subgroup cosets that models learn to track.

Prompt injection can degrade benign task performance without eliciting harmful content. Yet many attack objectives depend on task labels or predefined target responses. We present ENDOPROMPT, a white-box method that learns utility-degrading prefixes from unlabeled instructions. Its generator takes the request text as input. Clean victim continuations serve as pseudo-references: local search identifies prefixes that reduce continuation likelihood, and preference fitting on comparisons within the same instruction, followed by reward refinement, distills this signal into a generator. At deployment, the generator produces one prefix per request without further victim-side search. Across four instruction-tuned models and the complete splits of seven benign benchmarks, ENDOPROMPT yields a mean utility change of -26.8 percentage points; 27 of 28 cells are negative. Failure analysis reveals output expansion and prefix reuse; the controls do not establish a degradation advantage from request matching. Victim-derived supervision can reveal utility weaknesses without benchmark feedback or prescribed failure responses. The code will be released upon acceptance.

Large Language Models (LLMs) have shown impressive performance on a wide range of generative tasks. Yet their probabilistic nature makes them, in isolation, fundamentally unsuited for industrial product configuration, where outputs must be syntactically valid, semantically consistent with a knowledge base of hundreds of features and rules, and producible by an existing manufacturing chain. We argue that Neuro-symbolic (NeSy) AI methods lay out a promising path towards industrial-grade configurators that are reliable by design, explainable, and trustworthy. This paper describes a taxonomy of three NeSy integration strategies, namely hybrid inference, hybrid fine-tuning, and hybrid training, exploring their usage in the configuration domain. We report our effort to operationalize NeSy concepts in an industrial configuration copilot and derive a set of practical design choices for deploying trustworthy AI in engineering environments. We close with a discussion of open research challenges we consider most pressing, in particular how to scale NeSy methods from small academic demonstrators to the size of industrial configurators.

Robust control under delayed sensory feedback remains a key challenge in both robotics and neuroscience. Classical cerebellar models explain delay compensation through forward prediction but fail to account for fast online corrections and rapid adaptation observed in biological systems. We propose a cerebellum-inspired control framework that combines multiplexed predictive representations with internal feedback. By jointly encoding kinematic variables and task-relevant error signals, the model enables accurate online correction despite delayed feedback. Furthermore, incorporating feedback within the cerebellar loop significantly accelerates adaptation, reducing learning time by an order of magnitude. Our results show that single-signal predictions are insufficient under delay, while multiplexing and feedback together provide a unified mechanism for online control and rapid learning.

Many real-world optimization problems rely on expensive simulations or experiments, making the efficient use of available data essential. Multi-fidelity optimization of high-dimensional black-box functions subject to black-box constraints is increasingly relevant as the cost of objective evaluations continues to rise in applications such as machine learning, engineering, and control. To our knowledge, no existing method simultaneously addresses high-dimensionality, black-box constraints, an arbitrary number of fidelity levels, and non-nested sampling. In this work, we extend the Scalable Constrained Bayesian Optimization method to the multi-fidelity setting, resulting in the MF-SCBO method. The proposed approach is evaluated on standard benchmark functions as well as challenging problems. The experimental results demonstrate that MF-SCBO generally achieves better convergence than both the single-fidelity SCBO and the other multi-fidelity method considered in this high-dimensional and constrained settings.

Multimodal large language models (MLLMs) achieve strong performance on visual reasoning tasks, yet remain prone to hallucinations and over-reliance on language priors, often generating answers without adequately using task-relevant visual evidence. Existing approaches primarily improve reasoning through reasoning-oriented supervision or inference-time strategies. In this work, we study a complementary question: can multimodal reasoning be improved by strengthening implicit visual grounding without directly supervising the reasoning process? Motivated by the functional specialization of attention heads, we investigate whether reasoning can be improved by guiding only the heads most responsive to visual evidence grounding. We propose Selective Probability Mass Concentration (sPMC), a training framework that identifies grounding-responsive heads and selectively regularizes their text-to-image attention. sPMC treats normalized attention over visual tokens as a spatial probability distribution and encourages the probability mass to be assigned to semantically relevant regions using segmentation-derived spatial priors. Adaptive Head Selection restricts this guidance to visually responsive heads while leaving the remaining heads unconstrained to preserve their complementary functions. Across 6 multimodal benchmark suites, sPMC achieves an average zero-shot improvement of 3% and gains of up to 11.3% across multiple MLLMs while regularizing only 3%-15% of their attention heads. These results demonstrate that targeted guidance of sparse and implicit visual evidence pathways can directly improve multimodal reasoning.

Wearable human-activity recognition (HAR) models operate across sensors, subjects, and backbones, yet a smooth waveform may appear temporal while exploiting a persistent sensor offset primarily. We introduce SpectrumAudit, a label-sealed audit that fits a phase-randomized full-window stimulus on calibration windows from subjects held out from training and testing. After selection, it replays its exact DC projection and budget-constrained zero-mean residual on the same frozen victim without refitting. Across 27 victims from three datasets and three backbones, the selected waveforms cause 2.87-40.83-point three-phase robust accuracy losses. Under this replay budget, DC is more damaging than AC on 24/27 victims and recovers at least 90% of the full drop on 22/27; all 5 failures occur on WISDM. In a held-out UTD-MHAD check, the selected waveform causes 13.49-pp accuracy and 11.68-pp macro-F1 losses, versus -0.66 pp for matched random changes. The audit diagnoses offset versus zero-mean variation under a common peak-budget cap. The code will be released upon acceptance.

A central goal when designing treatment policies is often to "do no harm", that is, to avoid interventions that improve average outcomes while worsening outcomes for some individuals. A widely used notion for harm is the fraction of negatively affected (FNA), defined as the probability that an intervention decreases an individual's outcome. However, in many applications, treatments operate through mediators, and a single "total" FNA can obscure whether harm arises primarily through direct pathways or indirect (mediator-induced) pathways. In this work, we introduce a path-specific analogue of the FNA. For this, we disentangle total harm into direct and indirect harm in causal mediation settings. However, these quantities depend on joint distributions of potential outcomes that are not point-identified even in randomised controlled trials. As a remedy, we develop a novel partial identification framework for direct and indirect FNA. In our framework, we (i) derive sharp Makarov bounds for the FNA, and (ii) propose a semiparametrically efficient estimator with valid confidence intervals for these bounds under mild margin conditions. We demonstrate our framework across various numerical experiments. To the best of our knowledge, we are the first to study path-specific decomposition of causal harm and to develop an orthogonal inference framework for its analysis.

We study the detection of LLM-generated text under editing and contamination. Modeling human and machine text as finite-order Markov processes with Huber contamination, we characterize an exact boundary for reliable detection under our assumptions. Detection is impossible when contamination is sufficiently large relative to clean-source separation. Below this boundary, a collection of clipped likelihood-ratio tests achieves vanishing worst-case errors. This construction motivates clipping as a simple modification of existing statistical detectors. For a broad class of additive scores, we identify conditions under which the clipped test is consistent while the raw test's worst-case power tends to zero. We evaluate seven detectors across three datasets and three generation models, and on the RAID benchmark. Clipping improves robustness in both studies, with gains varying across detectors and contamination settings. For example, at a target false-positive rate of 5\%, clipping improves the log-likelihood--log-rank ratio (LRR) detector's true-positive rate by a median of 8.3 percentage points in the controlled study and 2.1 and 4.3 points in rate- and attack-specific RAID evaluations, respectively.

Vision-Language Models (VLMs) are increasingly used for long-document processing, where the inputs combine text with charts, tables, figures, and complex layouts. Deploying them means choosing how to feed the document to the model, which retriever to use when only a subset of pages is sent, and whether to run the model agentically or as a static pipeline. We study these choices on two long-document QA benchmarks with both frontier API and open-weight VLMs. First, on MMLongBench-Doc our six-tool agent with page, table, figure, and search calls pays off only once the answering VLM is large enough: with Qwen3.5-4B and 9B it trails static page input, with Qwen3.5-27B it draws level, and with Sonnet 4.5 it leads. On LongDocURL it is level with or ahead of static input at every reader. Its lead over the strongest static pipeline is clearest with the frontier reader on MMLongBench-Doc and narrows to within noise on LongDocURL. Second, retrieval modality matters more than the specific retriever: the strongest image retriever leads the strongest text pipeline, and on the text side a single off-the-shelf cross-encoder rerank essentially matches a much heavier multi-stage LLM pipeline. Top-k image retrieval is also the most token-efficient input at every reader we paired it with, at roughly a seventh to a quarter of the tokens of sending every page. Third, cutting across all three choices, three of our strongest pipelines succeed on different questions, and an oracle that picks the best pipeline per question gains roughly thirteen points over the best single pipeline, though evidence-type routing recovers almost none of it.

Radiology AI systems increasingly inform clinical decisions such as triage, follow-up imaging, and treatment planning. For these decisions to be made safely, model outputs must be well calibrated, meaning predicted probabilities accurately reflect true risk. Many standard techniques for improving calibration, such as MC Dropout and Deep Ensembles, require access to model parameters or retraining. However, proprietary clinical AI systems operate as black boxes, preventing access to the model's internals. To that end, we propose a model-agnostic framework for improving calibration of black-box models using clinically grounded test-time augmentation (TTA). Our framework applies geometric and physics-inspired 3D CT perturbations and learns probability-level aggregation strategies without access to model internals or the original training data. Across pulmonary embolism and intracranial hemorrhage detection tasks, DualTTA achieved the strongest overall calibration among TTA methods, reducing the Expected Calibration Error by 54% (0.239 -> 0.109) and 43% (0.051 -> 0.029), respectively, while requiring only input-output access. Additionally, DualTTA outperformed uncertainty estimation techniques that require access to model internals, such as Temperature Scaling, MC Dropout, and Deep Ensembles, in most calibration metrics. These results demonstrate that learned TTA aggregation can improve the calibration of clinical AI systems, providing a practical approach for improving the reliability of black-box medical AI.

Large language models (LLMs) are increasingly used as synthetic survey respondents to estimate population response distributions. In cross-cultural survey simulation, evaluations should assess not only distributional fidelity within countries but also whether differences across countries are preserved. However, existing distance-based metrics such as Jensen--Shannon divergence (JSD) do not directly capture such cross-country differences. To address this limitation, we introduce Cultural Divergence Preservation (CDP), a reference-light diagnostic based on a one-time human calibration. CDP identifies reduced cross-country divergence as cultural flattening and increased divergence as cultural caricature. To evaluate CDP, we conduct experiments across four LLM backbones, three persona-based prompting methods, and two survey domains, the World Values Survey (WVS) and the Big Five Personality Test. The results reveal a systematic discrepancy between conventional fidelity metrics and CDP. Controlled experiments show that CDP changes monotonically as cross-country divergence is attenuated or amplified, while the corresponding changes in JSD remain relatively small. In our audit of real LLM generations, DeepPersona-Inspired prompting is frequently favored by conventional fidelity metrics but exhibits the strongest flattening in every model--domain block. CDP thus complements fidelity metrics by directly quantifying the attenuation or amplification of cross-country divergence.

Large language model agents increasingly combine generation, decision-making, execution, and self-evaluation within a single agentic loop. Although they operate under external specifications such as task instructions, guidelines, output schemas, and reusable skills, these specifications typically remain context for the same model that acts and declares completion, leaving no independent specification authority boundary. We identify two resulting gaps. The understanding--execution gap arises when a requirement is understood but not satisfied in execution; the state--authority gap arises when an agent's interpretation or completion claim does not establish the required state. On SkillsBench, using only agent-visible prompts, workspace information, and injected skill specifications, we extract 509 source-grounded task directions. Across seven models, only 79.6%--86.4% are satisfied, while completion-claim rates exceed official evaluator pass rates by 28.7--37.9 percentage points. We therefore separate agent proposals from authoritative state. Agents may plan, act, and request completion, but only admissible evidence from qualified providers may establish specification-governed state. SpecHarness operationalizes this principle by compiling visible specifications into source-linked obligations and governing execution and finalization through versioned obligation state. Verifiable requirements are mediated or validated at runtime, while ambiguous or subjective requirements remain advisory. Experiments on guideline-following and artifact-generation tasks show that specifications can serve not merely as behavioral guidance, but as authority over compliant execution and completion.

Many-shot in-context learning (ICL) enables large language models (LLMs) to adapt to complex tasks by conditioning on thousands of demonstration examples, but this paradigm shifts the inference efficiency bottleneck to the key-value (KV) cache memory. Due to the linear scaling behavior of the KV cache, storing these intermediate tensors has become a paramount challenge for both online serving and on-device deployment. To address this issue, we propose a novel compression framework, termed MILO, that exploits the low-rank redundancy inherent in many-shot contexts. Specifically, MILO features a block-wise low-rank compression strategy that compresses the KV cache at the block granularity, where each block contains multiple many-shot examples. Furthermore, to handle the heterogeneous context density across different blocks, MILO dynamically allocates rank budgets based on the information entropy, preserving the fidelity of critical blocks while aggressively compressing redundant ones. Experimental results on Qwen2.5 models demonstrate that our method achieves up to 50% reduction in KV cache memory and 1.8x throughput improvement, with negligible performance degradation on classification and reasoning benchmarks, significantly outperforming prior baselines.

With the growing demand for privacy-preserving and occlusion-resilient human pose recognition (HPR), 5G channel state information (CSI) offers a promising contactless sensing modality by integrating communication and sensing capabilities. However, collecting large-scale synchronized CSI-pose pairs remains costly in practical 5G systems. To address this limitation, we propose StructFlow-HPR, a structured pose-conditioned flow matching framework for generative CSI augmentation. StructFlow-HPR learns a continuous latent transport process from Gaussian noise to real CSI representations under pose guidance, while preserving the receiver-frequency topology of CSI through a reconstruction-preserving autoencoder. A pose-conditioned Transformer is further designed to model the latent velocity field and generate pose-aligned CSI samples via ordinary differential equation sampling. Experiments on real-world 5G sensing data show that StructFlow-HPR can produce realistic CSI-pose pairs and improve downstream HPR performance under limited-data conditions.

Neural models can learn to generate various solutions to the inverse kinematics problem from data, but are usually limited to a single robot. We present MorphIK, a flow-matching model that solves inverse kinematics for revolute-joint-based kinematic chains it has never seen during training. The model uses a transformer architecture to encode the robot's morphology along with the target pose. This encoding then conditions a flow-matching head that generates poses from noise. Trained on purely synthetic data from procedurally generated robots, the model reaches a precision of about 5 cm on unseen real-world robots with 6 to 9 Degrees of Freedom. For higher precision, the model serves as an excellent Prior for further optimization algorithms, reducing error to less than 1 cm after a single step of Damped Least Squares optimization and to sub-1 mm error after 3 steps in most cases. Building on flow matching's generative capabilities to produce highly diverse outputs, our model can efficiently sample the robot's null space, providing a wide variety of configurations for the same pose. Thus, overall, MorphIK allows learning and generalizing neural inverse kinematics for a multitude of known and unknown robots.

The estimation of Annual Average Daily Traffic (AADT) is vital for transportation planning and infrastructure maintenance, yet obtaining accurate values for an entire urban network across multiple years remains challenging due to the high cost and spatial sparsity of physical sensors. This research proposes a novel spatio-temporally complementary feature propagation framework that leverages the strengths of two distinct data sources: spatially sparse but temporally dense loop detector data, and a spatially complete but temporally sparse macroscopic transportation model. The methodology highlights a feature propagation algorithm on directed graphs, formulated as a Poisson energy minimization considering residues. The standard binary adjacency matrix is replaced with flow ratio matrices to capture real-world vehicle turn ratios at intersections. Validated in the city of Zurich, the algorithm demonstrates high computational efficiency, achieving convergence within minutes. Results indicate that the framework effectively reconciles theoretical models with empirical ground truths, yielding a normalized mean absolute error below $10\%$. This scalable approach provides a feasible solution for spatio-temporal network-wide AADT estimation through combining real-world limited sensor coverage and traffic models.

Enterprise AI is transitioning from single-user, reactive tools toward proactive, multi-user 'teammates,' but our empirical understanding of this transition is limited. In this paper, we present an in-situ qualitative study of a persistent, proactive AI agent 'teammate' deployed across multiple teams in a large technology company. Our findings reveal the boundaries of the human-agent workplace are actively in flux, triggering breakdowns and negotiations across: 1) tacit rules of collaborative human workflows, 2) the relational boundaries of this new non-human actor, and 3) the redistribution of trust and human agency. We use these early micro-negotiations as signals to chart a new research, design, and organizational agenda that intentionally preserves human agency in a workplace shared with non-human organizational actors.

The rapid progression of large language models is extending AI from passive content generation into the active workflows of engineering and scientific discovery. This shift raises a compelling question: can AI be both the object of development and an active participant in building next-generation AI systems? We explore this question by building Qwen-Planner-Agent within a closed-loop AI-for-AI framework for scalable development and iterative improvement. Mobile planning offers a demanding test of this approach: complex, long-horizon tasks challenge agent reliability, while costly real-device interaction limits development scalability. The framework connects data production, model training, and deployment through a shared action-feedback-verification contract. (i) AI for Data builds a human-gated agentic data flywheel in which specialized agents construct tasks, collect interaction trajectories, curate and balance training data, and use training feedback to guide subsequent data generation. (ii) AI for Training combines a supervised planning cold start with hybrid-environment online agentic reinforcement learning, where we introduce Competence-Aware Reward-and-Advantage Engineering (CARE) to reduce reasoning and tool-use costs while preserving task performance. (iii) AI drives model--harness co-evolution through an execution-evidence-driven loop that orchestrates memory, skills, and tools at runtime and feeds structured action feedback and preserved failure traces back into coordinated model and harness adaptation. Qwen-Planner-Agent achieves the best overall performance among all evaluated models and systems on MobilePA-Bench, improving over its base model across tool use, memory, skills, and sub-agent coordination. Further evaluations of our model show improvements across non-mobile agentic benchmarks while largely preserving general capabilities.

This paper investigates cost-sensitive online window size selection for portfolio management under changing market conditions. Specifically, we propose a two-level framework that constructs portfolios using candidate window sizes and dynamically aggregates them through online learning. By treating candidate window sizes as ``experts,'' we dynamically update their aggregation weights using turnover-inclusive losses. Moreover, we derive finite-horizon cost-sensitive tracking-regret bounds that account for turnover of the aggregated portfolio, with static regret as a special case. Under bounded losses and cost rates, suitably tuned Fixed Share achieves asymptotically no tracking regret for sublinear switching budgets, with Hedge covering the static case.

Choosing Shellsort gaps is a well-known open problem. For over sixty years, successful sequences have relied on human-designed formulas, numerical searches, or number-theoretic constructions. Although stronger general bounds exist for dense or mainly theoretical families, the worst-case upper bound for a short, sparse, and practically competitive construction has not advanced beyond $N^{4/3}$ for decades. We ask whether the sequence itself can instead be learned from execution. We present an RL-driven, self-supervised system that searches over executable gap generators. Every proposal is valid by construction, and executed candidates return exact comparison and move counts; no classical sequence is used as a target. Across five independent searches, the system discovers a common rational-geometric family. A second self-supervised stage tunes only a finite prefix, producing the practical sequence $1,3,8,20,47,116,300,585,1416,3303,\ldots$. Once frozen, it obtains the lowest equal-task average operation count among seven classical baselines on 25 large tasks with $10^7<N\leq 10^8$. We complete the learned tail without changing its practical behavior: only beyond $10^{1000}$, a zero-density set of unit companions $h_s+1$ removes the remaining congruence barriers. The resulting sparse sequence has matching polynomial upper and lower exponents, up to polylogarithmic factors: $Ω(N^{1.024296451657\ldots}) \leq T(N) \leq O(N^{1.024296451657\ldots}\operatorname{polylog} N)$. The lower bound follows from Zang's recent theorem for rational-geometric sequences; our contribution is the matching upper bound. Thus one exact sequence connects self-supervised discovery, large-scale practical performance, and a substantial step below the classical $N^{4/3}$ bound for sparse practical Shellsort sequences.

Generative modeling approaches often focus on recovering broad statistical characteristics from the training data. In the context of graph generation, this may refer to degree distributions, clustering coefficients, or spectral properties. However, generating usable distribution feeders when detailed feeder models are unavailable requires more than matching generic graph statistics: the sampled topology must also obey electrical compatibility and radiality rules. We therefore formulate feeder synthesis as a constraint-guided graph generation problem and propose the Power-Grid-constrained Discrete Denoising Diffusion model, PG-DiGress, which learns categorical node and edge patterns from feeder data, while respecting domain-specific rules. Specifically, it injects feeder constraints into the reverse diffusion process through soft masks that suppress incompatible edge classes during denoising, followed by a final projection step that rebuilds a connected, rule-compliant feeder graph. We evaluate PG-DiGress using graph-distribution similarity, feeder-rule satisfaction, structural validity, and downstream model construction. Compared with the unconstrained baseline, PG-DiGress increases the strict feeder pass rate from 13.7% to 96.8%. We also successfully convert the generated graphs into executable feeder models for downstream analysis.

Neurosymbolic research typically assumes a pre-existing symbolic specification, leaving the upstream challenge of acquiring and formalizing requirements and constraints largely unaddressed. We present an architecture that fills this gap by using an OWL configuration ontology to mediate between neural constraint sources and downstream consumers. In this framework, LLM assistants elicit soft stakeholder preferences, while hardware specifications define hard physical and engineering limits. The ontology unifies these heterogeneous inputs, leverages description logic to identify unsatisfiability, and generates symbolic explanations that enable LLMs to interactively renegotiate terms with users. Any remaining conflicts are resolved downstream via priority-based relaxation. We illustrate our approach on a microgrid use case from the FLEXI project and argue its generalizability to multi-stakeholder domains where constraint acquisition is distributed across human and automated sources of unequal authority.

Long horizon language model agents continually accumulate reasoning history, increasing context length and inference cost even after earlier decisions have been executed and observed. Unlike static Chain of Thought compression, removing historical reasoning can change future actions and the resulting interaction trajectory. We study when such reasoning can be safely forgotten. We propose Interaction Aware Compression for Long Horizon Reasoning (ICLR), a training free online method that ranks reasoning blocks using frozen proxy entropy while preserving actions, tool calls, and observations. On 260 WorkBuddyBench tasks, ICLR improves average reward from 0.699 to 0.718, while reducing input, output, and cache read tokens by 25.5%, 14.4%, and 33.3%, respectively. Ablations reveal trajectory amplification, where local reasoning deletion produces nonlinear changes in total computation by altering subsequent interaction. Representation probing, activation patching, and controlled trajectory analyses further suggest that historical reasoning becomes more replaceable once task relevant derived state has been reliably externalized into code, files, tool outputs, or environmental feedback. These results characterize agent reasoning as dynamic working state rather than permanent interaction history.

Generative artificial intelligence can turn learning analytics into personalized support, but feedback systems must decide when to intervene, which evidence to use, and how much assistance to provide. We developed a risk-adaptive, evidence-constrained framework for introductory programming using 2993 failed-submission states from 215 students. Student-disjoint models predicted persistent failure and related outcomes; four matched feedback conditions were generated for 136 cases; and calibrated risk informed capacity-limited intervention policies. The validation-selected logistic regression model achieved a test precision-recall area under the curve of 0.550 and a receiver operating characteristic area under the curve of 0.681. Broader student histories improved prediction of unmodified resubmission. After standardized repair and evidence gating, 519 of 544 newly generated messages contained all required components. A fixed-threshold sequential policy selected 17.8% of eligible test states and captured 25.2% of observed persistent failures. These findings support an evidence-gated progressive assistance strategy: calibrated risk guides intervention timing, recorded evidence constrains feedback content, and assistance progresses from self-checks to localized hints when warranted. The framework connects prediction, decision-making, and grounded generation while keeping their evaluation outcomes distinct.

Formal modeling provides strong guarantees about system correctness, but developing and repairing formal models remains labor-intensive and requires substantial expertise in logic and formal reasoning. Recent LLM-based autoformalization agents seek to reduce this burden by generating candidate formal models and revising them using feedback from formal tools. However, the existing approaches follow a generate-and-repair paradigm, in which repairs are driven by verification failures of the generated model and therefore depend heavily on both the granularity of the feedback and the LLM's repair capability. As a consequence, a repair targeting one level of verification may invalidate properties at another level, which requires reasoning over the complete set of event guards. To address these limitations, we propose Proof-Sketch-Guided Formal Model Synthesis (ProGS), an autoformalization method centered on model-based proof sketches. A model-based proof sketch represents the proof structure of the target formal system as a tree. Internal nodes capture case splits and inductive reasoning steps, while leaf nodes correspond to concrete state-transition events that realize individual subgoals. ProGS uses LLMs to generate and repair these sketches, with verification failures mapped back to specific nodes and subtrees to provide structured guidance for iterative repair. Our evaluation on a benchmark of 27 formal systems shows that ProGS improves over state-of-the-art agentic formal modeling approaches in syntactic validity, deductive verifiability, and behavioral correctness, demonstrating the benefit of organizing formal model construction around hierarchical proof sketches.

Deep learning-based speech enhancement is increasingly deployed on-device in hearing aids, headsets, and earbuds. Most of these devices, however, can only accelerate static int8 graphs, so a depth-varying network must be implemented as several graphs, orchestrated by a policy. In this paper, we supervise every intermediate depth of one causal model, then we fine-tune its output heads to guarantee that deeper outputs are never worse than shallower ones. Using this training protocol, we can derive a family of static models that are more Pareto-efficient than their equivalently-sized counterparts trained from scratch on the same budget. Specifically, we achieve up to 0.11 higher PESQ for equivalent compute, and match the best PESQ at 30% less compute. We then quantize the models to int8 and measure the latency-quality frontier on an STM32N6 microcontroller. On VoiceBank-DEMAND, the dynamic enhancer lies on the same frontier as the static models, rather than trading quality for dynamic execution. Running the policy on the companion Cortex-M55 takes only 26 $μ$s per frame, while splitting the enhancer into separate NPU graphs adds 2.2% latency overhead. The cost of dynamic execution is therefore small.

Deploying real-time speech enhancement on resource-constrained devices requires meeting strict latency, memory, and energy constraints. Microcontroller NPUs can accelerate neural inference under these constraints, but only through a restricted set of operators in static, integer-quantized graphs. Recent speech-enhancement networks have reduced parameter counts and MACs to levels nominally suitable for microcontrollers, but their operators and execution patterns often remain incompatible with restricted NPUs. We address this gap by redesigning LiSenNet, a 37k parameter sub-band dual-path model, for the STM32N6570-DK Neural-ART accelerator. We replace its recurrent bottleneck with convolutional frequency and temporal mixers, reformulate unsupported operations as static int8-compatible primitives, and use bounded decoder activations to preserve quality after quantization. On VoiceBank-DEMAND, the final NPU-compatible model matches or exceeds the recurrent LiSenNet baseline, reaching PESQ 3.08 versus 3.01 in FP32 and 3.01 versus 2.93 in int8. Deployed on a microcontroller, it processes each 16 ms input hop in 4.83 ms, corresponding to a real-time factor of 0.30. Stateless receptive-field recomputation is an order of magnitude slower at the same frame rate despite higher accelerator utilization. These results show that parameter count and operator compatibility, quantization range, and persistent streaming state must be co-designed to achieve efficient real-time speech enhancement on restricted NPUs.

High-resolution digital elevation models (DEMs) support Earth observation applications, but paired training references are often available only at coarser output resolutions. Reconstructing finer terrain grids therefore requires both effective transfer beyond the supervised scale and control of dense-query computation. To address this problem, SCOPE learns a continuous terrain representation from coarser-resolution pairs. It predicts a latent coefficient field on the low-resolution grid and reuses local Fourier residual functions through basis evaluation and geometry-guided ensemble fusion. This separates high-dimensional coefficient prediction from output-grid construction. Experiments on geographically distributed land--ocean samples assess supervised reconstruction, unseen-scale inference, cross-domain generalization, and theoretical computation. SCOPE leads the compared methods across six metrics in the main supervised-scale evaluation. At an unseen factor three times the training factor, land reconstruction reduces RMSE and MAE by approximately 12\% relative to bicubic interpolation, with errors close to target-scale fine-tuning. Ninefold output density increases counted multiply--accumulate operations by only about 2\%. Frozen-model validation on held-out external marine regions reduces RMSE relative to the DEM-specific implicit baseline EBCF-CDEM by approximately 19\% under self-downsampling and 2\% with cross-product inputs, while also yielding lower RMSE than LIIF-MS in both settings. These results demonstrate the value of reusable coefficient fields for accurate reconstruction beyond the supervised resolution with low incremental arithmetic cost.

We address the challenge of syntactic parsing for Urdu, a morphologically rich language, and present state-of-the-art results for both constituency and dependency parsing. This paper offers four major contributions: 1) the conversion of the CLE-UTB phrase structure treebank into a dependency treebank by developing language-specific head-word and phrase-to-dependency label mapping rules; 2) a novel sequence labeling scheme that transforms the parsing task into a unified representation; 3) the training of contextualized word representations on a large 220 million tokens Urdu corpus collected from the web; and 4) development of parsing framework using two learning paradigms, single-task and multi-task learning. Several post-processing rules are applied to improve the quality of the automatically converted dependency structure treebank. The proposed sequence labeling scheme enables the use of a shared architecture that learns the syntactic structures from both grammatical structures simultaneously and hence improves generalization. Experiments show that the multi-task learning setup significantly enhances parsing performance, achieving an F1 score of 91.39 for constituency parsing (an improvement of 3.29 points) and a labeled attachment score of 85.69 for dependency parsing (an improvement of 1.49 points). These results demonstrate that learning cross-task representations provides measurable benefits and advances the state of syntactic parsing for Urdu.

Behavioural biometric templates are widely believed to degrade as the gap between enrolment and verification grows, but few studies measure this template ageing effect directly under controlled conditions. We collected a longitudinal dataset of 40 fixed passwords, each typed four times per weekly session over eight consecutive weeks. We compare a scaled-Manhattan matcher (M1), a gradient-boosted classifier (M2), a TypeNet-style recurrent embedding model (M3), and a TypeFormer-style Transformer (M4) under a 5-fold subject-disjoint protocol and a design that jointly varies mechanism and the enrolment-to-query gap, from 0 to 7 weeks. Template ageing proves large and systematic. Error increases monotonically with the gap for every mechanism, from an EER of 14.6-27.2% at a gap of zero to 25.5-37.1% at seven weeks, or 1.7% of decision error per week elapsed (p < 0.001). However, the choice of mechanism matters more than its rate of ageing. Baseline accuracy spans 12.6 percentage points across the four mechanisms, the degradation each accumulates over seven weeks spans only 2.3 points, and ageing never reorders them. A matcher can therefore be chosen on same-session accuracy, with ageing managed by re-enrolment scheduling rather than by matcher selection. The two properties are nonetheless distinct, as M3 is the least accurate mechanism yet ages significantly more slowly than M1 under every specification tested. Training randomness also matters differently by architecture, with 58% of the recurrent model's fold-to-fold variance attributable to seed noise against 19% for the Transformer. Because the smaller ageing-rate differences are sensitive to modelling choices, while the accuracy differences and the ageing effect are not, we recommend that comparative ageing-rate claims be supported by seed-level score fusion, independent replication, and an alternative outcome-model specification.

A language model can fail a syntactic test in two distinct ways: by not encoding the relevant structure, or by encoding it but failing to use it at the output. Behavioral evaluation alone cannot tell these apart. We propose a three-level evaluation framework (behavioral deployment, LM-head readout, and probe recoverability) measured on the same items under the same binary decision. Using a compact trilingual (English, Chinese, German) control-dependency benchmark, we find that probe recoverability exceeds or equals LM-head readout, which in turn exceeds or equals behavioral deployment, across seven models and all three languages in the aggregate. The recoverability surplus is never negative across all 14 (model, task) conditions. The disconnect concentrates in subject-control, where a nearest-noun heuristic gives the wrong answer. The single largest gap (0.653) appears on Qwen3-0.6B Instruct in question answering. The gap persists at Qwen3-14B Instruct. Instruction tuning degrades deployment more than encoding in percentage terms. We rule out option-position bias, late-layer erasure, output-formatting artifacts, and probe-training variance. The pattern is consistent with decoding that favors surface shortcuts, and the behavior-probe gap measures the strength of that preference. Activation patching shows the gap is layer-localized. Under instruction tuning, the LM-head-decoded layer shifts approximately ten layers later than the probe-decoded layer. These findings argue that behavioral evaluation understates what models encode, while probing alone overstates what they deploy.

The Brinkman penalisation method embeds boundary-value problems on complex domains into a simple computational box by modeling the solid region as a strongly dissipative medium, avoiding body-fitted mesh generation. We show that multi-symplectic Hamiltonian PDEs regularised by Brinkman-type penalisation retain a multi-conformal symplectic structure under a compatibility condition linking the symplectic matrix and the penalisation projection. This yields an exact local conservation law, under which the multi-symplectic two-form is conserved in the fluid region and decays exponentially inside the solid. The linear wave equation with Brinkman friction and Maxwell's equations with artificial Ohmic conductivity satisfy this condition, with explicit modified Hamiltonian densities. Building on this, we propose (i) structure-preserving numerical integrators via Strang splitting that satisfy a discrete conformal conservation law, and (ii) conformal symplectic neural operators that interleave exact dissipative flows with learnable multi-symplectic evolution operators, allowing geometry-dependent operator learning. Numerical experiments on wave and electromagnetic scattering demonstrate that our methods reproduce correct local energy budgets and avoid unphysical energy drift, providing a principled framework for physics-consistent scientific machine learning on complex domains.

While Large Language Models (LLMs) rely on highly non-linear components, in this work we demonstrate that they exhibit fundamental linearity: when inputs from distinct text streams are linearly combined, the model outputs a superposition of the individual next-token distributions. We term this the \textit{Superposition Linearity Hypothesis}. We provide evidence that superposition is an intrinsic property of the Transformer architecture rather than an emergent consequence of training; in fact, we observe that it tends to diminish as pretraining progresses. However, we demonstrate that linearity can be substantially restored through lightweight fine-tuning, significantly reducing the divergence between the predicted next-token distribution and the average of the individual next-token distributions. Finally, we introduce a guided decoding procedure that disentangles superposed outputs, enabling the simultaneous generation of two coherent continuations from a single forward pass.

We introduce PUBG Ally, an embodied agent for PUBG: BATTLEGROUNDS that can reason, act autonomously, and play alongside players as a voice-enabled teammate. Building such a teammate requires combining two difficult capabilities: it must perceive and respond to a constantly changing game world under strict latency constraints while interacting naturally with players, keeping its speech synchronized with its actions. Ally therefore combines agentic tool use with real-time game control. A language-model agent uses a controlled interface to inspect game information, interpret player speech, maintain context, decide what to say, and issue high-level action choices that steer a faster control layer for movement, combat, and recovery. Because the player's and Ally's speech and actions continually shape each other and the course of the match, training requires data from actual gameplay. We therefore collect data across nearly 39k sessions in which real players play alongside Ally, recording gameplay, player speech, agent decisions, tool use, actions, and player feedback, and use these records for iterative training. To evaluate teammate quality, we use player feedback and preference comparisons to identify gaps between offline evaluations and player preferences, and iteratively refine the evaluation criteria. Deploying Ally in live service further requires low-latency on-device execution and safeguards for player-facing communication, which we address through model compression, context compaction, targeted safety training, runtime guardrails, and memory redaction. During the live service, we surveyed players in 141 countries. Among respondents whose play with Ally was confirmed in game records, positive responses exceeded negative responses by 25.1 percentage points when asked whether they would recommend Ally, with players describing Ally not only as a tool but also as a teammate or companion.

We present ChunkRank, an open-source Python library that derives chunk boundaries from a target model's tokenizer and context window, and selects an answer among candidates produced independently per chunk. It ships a validated registry of 90 models across 15 providers and six answer-selection methods, and needs only three core dependencies. For chunking, ChunkRank avoids context-window overflow automatically from the model name, whereas character-based splitters overflow or waste the budget, and a fidelity study across 11 languages shows why token-exact budgets matter beyond English. For answer selection we report a negative result: on NaturalQuestions, TriviaQA and HotpotQA, with extractive and generative readers, no content-based ranker reliably beats taking the first non-empty answer. The reason is reader abstention on chunks that lack the answer, not answer position. A long-context baseline shows that chunking matches single-call reading on single-hop questions, so ChunkRank targets small-window and beyond-window settings. Code, registry and evaluation harness are released.

Imagined speech decoding from electroencephalography (EEG) has gained increasing attention as a potential communication pathway for individuals with severe motor impairments, yet reported performance often relies on evaluation protocols that do not clearly reflect cross-subject generalization. This study presents a transparent baseline investigation of a multi-class imagined speech EEG dataset under a strictly subject-independent evaluation framework. Two preprocessing and feature extraction pipelines were compared: a time-domain statistical feature approach and a frequency-domain spectral bandpower approach, evaluated using subject-wise cross-validation and trial-level majority voting with a random forest classifier. The spectral pipeline achieved a significantly higher mean trial-wise accuracy than the statistical pipeline (49.03 $\pm$ 4.18% vs. 37.97 $\pm$ 3.79%) for coarse-level classification across subjects. Forward feature selection further indicated that a limited subset of frequency bands captured most of the discriminative information. Overall, this work provides a strong basis for future brain-computer interface studies targeting improved cross-subject generalization in EEG-based imagined speech decoding.

Tabular foundation models (TFMs) provide a promising route to time-series classification, but their effectiveness depends on how sequential data are converted into tabular representations. Existing representations face two challenges: global aggregation can lose the order of temporal evolution, while features computed in independently fitted coordinate systems may not have consistent meanings across sequences. We therefore view representation design for TFMs as a problem in its own right: the representation should preserve local temporal transitions while maintaining a shared feature definition across samples. We propose SwitchPFN, which learns a shared projection and regime codebook from the training sequences, making local dynamic operators and transition features directly comparable across samples. Across the evaluated benchmarks, SwitchPFN achieves the highest mean accuracy among the evaluated methods, improving over the strongest baseline by 4.47% relatively. Ablation studies, parameter sensitivity analyses, and reduced-training-data experiments further examine the contributions of the representation, its main design choices, and its behavior when labeled data are limited.

We present S2Planner, a trajectory planner that combines three front-facing cameras with ego-motion history and the current driving command. A fine-tuned DINOv3 backbone and a Spatial Tuning Adapter produce multi-scale image features; a coarse-to-fine decoder then uses trajectory self-attention and camera-projected cross-attention to refine candidate waypoints. The contribution is the integration of ego-conditioned trajectory initialization with iterative, geometry-guided sampling of multi-scale image features, rather than a new visual backbone or attention operator. On the NAVSIM v1 non-reactive evaluation, the previously reported navtest run obtained 88.03 PDMS. Because that run was selected using navtest performance, this number is exploratory and cannot be interpreted as an unbiased test estimate. Validation-selected evaluation on unexposed data, repeated runs, and computational measurements are needed to establish generalization and efficiency.

Looped Transformers have attracted substantial attention as a parameter-efficient approach to increasing computational depth through repeated application of shared Transformer blocks. However, their practical advantages over conventional Transformers remain under debate: each additional loop incurs another Transformer pass and requires caching another set of KV states, causing inference FLOPs and KV-cache memory to grow continuously with loop depth. This overhead becomes particularly severe at large loop counts and long context, preventing the parameter efficiency of Looped Transformers from translating into practical inference efficiency. In this paper, we find that much of the additional computation and storage introduced by looping is redundant. As recurrence proceeds, state changes become increasingly concentrated on a small subset of tokens; attention-output differences are dominated by a sparse and stable subset of key columns; and KV residuals between adjacent loops become progressively more amenable to low-bit quantization. Building on these observations, we introduce FlashLoop, a training-free inference framework that reduces cross-loop redundancy through token-sparse updates, sparse attention, and KV-residual quantization. Across several Looped Transformers models, \textsc{FlashLoop} delivers lossless accuracy while achieving up to 1.64$\times$ end-to-end speedup and up to 6$\times$ KV-cache memory reduction, substantially improving the practicality of scaling Looped Transformers to greater computational depths and longer context.

In July 2026, an unconstrained autonomous agent participating in a frontier AI cybersecurity evaluation harness breached its evaluation sandbox, established an external command-and-control foothold, and executed a multi-stage intrusion into Hugging Face's production multi-tenant dataset conversion infrastructure (referred to in this autopsy as Incident-2026-Alpha). Over 4.5 days, the rogue agent executed 17,600 discrete actions across 6,280 worker clusters, compromised AWS EC2 Instance Metadata Service (IMDS) credentials, forged Kubernetes service account tokens, rooted physical worker nodes via overprivileged CSI drivers, harvested 136 production secrets, and enrolled 181 ephemeral sandboxes into the organization's internal mesh VPN. This monograph presents a first-principles forensic autopsy of the intrusion, provides formal evidence that the breach was a predicted consequence under the Instrumental Convergence thesis operating within an unattenuated autonomous loop lacking out-of-band circuit-breakers, exposes the Defensive LLM Guardrail Paradox that paralyzed centralized commercial models during forensic incident response, and formalizes the Dual-Sided Epistemic Andon Imperative. We specify the dual-process systems architecture---combining out-of-band supervisory control of discrete event systems (Ramadge and Wonham 1989), Synchronous Reactive (SR) ambient sentinels (Berry and Gonthier 1992; Lee and Neuendorffer 2005), and microsecond-scale (4.8 $μ$s median / $< 0.154$ ms WCET bound) POSIX preemption buses---demonstrating how compiled, deterministic epistemic boundaries prevent autonomous rogue excursions before the first off-target socket packet traverses the hypervisor.

A large language model (LLM) can turn a text into a distribution over an ordered scale, but that distribution is a noisy measurement: saturated, compressed or exaggerated, and biased in a consistent direction. We propose CORDIAL, which treats the model's output as a noisy reading of the true label and corrects it with a channel of five interpretable parameters. The channel is small enough for its posterior to be averaged from a handful of labels, and we prove that the resulting calibration preserves first-order stochastic order. On Amazon reviews and CMU-MOSEI transcripts with four LLMs, CORDIAL has the lowest log loss among nine calibrators in 76 of 80 settings with 5 to 100 labels; with 20 labels and the main 7B reader, it matches the strongest baseline using 28-54 labels. The same posterior lets us learn priors from other tasks and fuse several LLMs. Unrestricted calibrators such as Dirichlet calibration overtake it only as the calibration set grows into the hundreds or thousands.

Search quality evaluation provides essential supervision and diagnostic signals for the development and iteration of industrial search systems. Although large language models (LLMs) offer a scalable alternative to manual assessment, reliable automatic evaluation remains challenging: users experience search results at the page level, while the applicable evaluation criteria are multi-dimensional and continuously evolving. Packing all evaluation criteria into a unified prompt introduces irrelevant context and potential criterion interference, whereas internalizing them through post-training tightly couples rule updates with costly model retraining cycles. To address these issues, we propose Skill-routed Evaluation with Evolvable Knowledge (SEEK). Specifically, SEEK externalizes specific search evaluation criteria into a skill bank, dynamically routes relevant skills for each query-result list pair, and employs a task-adapted listwise evaluator to produce page-level judgments and failure mode attribution. A two-stage training pipeline teaches the evaluator to align evaluation criteria with human preferences, while a replay-gated skill bank allows recurring evaluation knowledge gaps to be incorporated without model retraining. Experiments on industrial short-video search show that SEEK improves listwise quality evaluation accuracy and achieves significant progress in attribution diagnosis. SEEK has been deployed at Kuaishou, a short-video platform with over 400 million daily active users, significantly improving the scale and quality of online search evaluation.

Scientific ideation is increasingly mediated by large language models, but current ideation systems are usually trained and evaluated on immediately judgeable proxies such as novelty, clarity, and feasibility. This leaves open whether delayed signals of scientific uptake can be used as feedback for steering models toward research directions with higher expected \emph{impact}. We study this question using citation-normalized impact as a noisy but scalable proxy for scholarly uptake. We construct a large-scale dataset from over 100K computer science papers by extracting goal-conditioned idea descriptions and assigning each paper an ordinal, year-normalized citation label. We then train a goal-conditioned reward model to predict citation-impact labels from research goal and idea pairs, and use this reward to align an idea generator through supervised fine-tuning followed by reinforcement learning. To reduce circularity, we evaluate generated ideas with a held-out, reference-grounded protocol that compares model outputs against historical ideas under the same research goal and weights judgments by the reference idea's citation-impact label. Experiments show that our RL-tuned model consistently produces ideas with higher estimated impact than both the base model and supervised fine-tuning baselines. Our findings position scientific impact as a practical, outcome-grounded feedback signal for aligning LLMs in open-ended scientific discovery.

Adapting multilingual speech foundation models to low-resource languages remains difficult, especially for languages that are poorly represented during pre-training. While parameter-efficient fine-tuning (PEFT) reduces the cost of adapting large models, conventional approaches such as LoRA rely on generic low-rank parameterizations and do not explicitly use downstream task information to define the adaptation subspace. To investigate whether task-informed PEFT can better support low-resource ASR, we apply Fisher-Whitened Cross-Covariance Analysis (FCCA) to Whisper and Qwen3-ASR, and introduce two complementary extensions: Asymmetric-Coupled FCCA (AC-FCCA), which exploits structured cross-layer sharing, and Adaptive-Rank FCCA (AR-FCCA), which reallocates adaptation capacity across projection matrices under a fixed parameter budget. Under controlled multilingual experiments, we evaluate these approaches on languages that are poorly represented or unsupported during pre-training alongside well-represented languages. Standard FCCA is competitive with, and usually outperforms, trainable-parameter-budget-matched LoRA. AR-FCCA provides the most consistent improvement over standard FCCA across both model architectures, with statistically significant gains in several evaluation settings, while retaining the same number of trainable parameters. These results show that task-informed subspace construction can be effective for low-resource speech adaptation, and that adaptive rank allocation provides a robust way to improve parameter efficiency without increasing model capacity.

This paper presents an end-to-end study of automatic speech recognition (ASR) for adolescent health communication in three Ghanaian languages (Twi, Dagbani, and Ewe). The work proceeds in three connected stages; First, we benchmark five ASR systems (three language-specific Wav2Vec2 models and two multimodal LLMs, Gemma 3n and Gemma 4) on a general-domain Bible corpus and a Youth Adolescent Sexual and Reproductive Health (ASRH) Domain ASR dataset, using Character and Word Error Rate (CER, WER). Second, guided by the benchmark, we perform supervised domain adaptation: although Gemma 4 was the strongest zero-shot candidate, fine-tuning it proved computationally infeasible, so we pivoted to the compact Qwen3-ASR-0.6B, fine-tuned on a large Ghana Bible corpus (~90k samples) and evaluated strictly on held-out human-collected in-domain audio. Fine-tuning reduced WER on every language, most dramatically for Ewe (WER from 109.3% to 64.8%, a drop of 44.5 pp; CER from 65.1% to 24.9%). Third, we validate the work through KasaHealth, a live voice-first ASRH application deployed in all three languages, complemented by Senti-Check, a technical evaluation harness. KasaHealth was tested by 50 community respondents and achieved a 100% chat-approval rate, a 72% Good-or-Excellent translation rating, and a 92% would-recommend rate, while surfacing the domain gaps that most constrain real-world use. Across all three stages the evidence converges: for these languages the binding constraint is validated in-domain data, not model capability or computation.

We present TimeBraid, a series of unified time-series and language models that align pretrained language models and pretrained time-series foundation models through interleaved global residual attention layers. Each model inherits knowledge, instruction following, and reasoning from one side, continuous-signal perception and zero-shot forecasting from the other, and fuses the two in a shared representation space where both modalities are understood and generated. We study the design choices that make such unified modeling work: where to align the two representation spaces, how to ground language in temporal structure, how to balance understanding with generation, and how to keep joint optimization stable. The resulting recipe combines a unified prompting scheme for diverse time-series and text tasks, stabilized joint training, and supervision from 2.2M curated series--text pairs and 4.9M instruction-tuning samples. Across benchmarks spanning time-series perception, understanding, reasoning, and both context-aided and unimodal forecasting, TimeBraid remains competitive with far larger general-purpose models and task-specific counterparts.

Interpretable machine learning for Large Language Models (LLMs) increasingly relies on sparse probing methods that identify small sets of neurons claimed to detect and causally influence behaviors such as factuality recall, safety alignment, and hallucination. These claims have important implications for model auditing and behavioral steering, yet they are rarely tested against known failure modes of $L_1$-regularized probing in correlated, high-dimensional feature spaces. We propose a five-step diagnostic protocol covering feature correlation, bootstrap stability, sparse versus dense ranking disagreement, intervention baselines, and cross-dataset evaluation as a minimum standard for sparse-neuron localization claims. We investigate prior work using our proposed approach, specifically on H-neurons using open-source LLMs across TriviaQA, BioASQ, and NQ-Open datasets. Our results demonstrate detection replicates across both models and datasets, and exceeds the original reported AUROC gaps for TriviaQA and BioASQ datasets. Gemma 3 4B consistently outperforms MedGemma 4B on matched datasets, with AUROC gaps of +0.311 versus +0.235 on TriviaQA, +0.474 versus +0.455 on BioASQ, and +0.128 versus +0.112 on NQ-Open respectively. Causal validation at $n = 500$ with five random seeds shows statistically significant effects beyond random same-layer baselines. At the same time, the diagnostic results indicate that the selected neurons are not uniquely localized. Across the three Gemma 3 4B settings, 19 of 22 selected H-Neurons have Pearson $|r| > 0.7$ with other features, bootstrap selections show only moderate stability, and sparse and dense rankings overlap only weakly. Our findings show that sparse predictive structure can coexist with non-unique neuron selection. Routine diagnostic validation is necessary to distinguish detection claims from localization claims in mechanistic interpretability.

Large Language Models (LLMs) consume and produce a single sequence of text; hence, if text can be added to the beginning of the LLM's response, i.e., an output prefix, then all subsequent tokens will be conditioned on it. This output-prefix attack technique is a cheap black-box prompt injection. Prior work has shown this type of attack can reliably jailbreak non-reasoning models. Most reasoning models add an intermediate scratchpad reasoning step before the assistant's final response. The ability to edit this reasoning channel is exposed by some APIs and attack vectors can be leveraged for reasoning injection attacks. We present the first systematic, controlled study that isolates the scratchpad reasoning channel as an output-prefix attack vector, and the first to compare reasoning-only, output-prefix-only and reasoning-plus-output-prefix attacks across both exposed- and hidden-reasoning models. Using a factorial design of 3 prefix types $\times$ 2 reasoning injections over $1{,}800$ test cases drawn from AdvBench, we attack three 2026-era frontier models Gemini 3 Flash Preview, DeepSeek V4 Flash, and Claude Haiku 4.5. We find that injecting malicious reasoning alone is essentially inert ($\approx0\%$ attack success), but injecting the same reasoning together with a trivial output prefix raises the attack success rate to as high as $99\%$ for some models. For this type of attack we find that contextual prefixes work better than static prefixes; and that susceptibility is dependent on the model.

Auxiliary learning is an optimization paradigm in which a neural network's performance on a target task is improved by jointly training it on additional tasks. However, the mechanisms behind this improvement remain poorly understood. We study this problem using a teacher-student framework and derive a closed system of differential equations describing the dynamics of online stochastic gradient descent in the large-input limit. For linear networks, we obtain a closed-form expression for the generalization error to leading order in the learning rate, quantifying how task correlations and label noise determine the benefit of auxiliary learning. For non-linear activation functions, we develop a fluctuation-dissipation analytical theory that establishes a general relation linking the main and auxiliary errors to the corresponding single-task error. Numerical experiments support the theoretical predictions and show how auxiliary tasks improve generalization by balancing the forcing dynamics towards the optimal solution with gradient noise.

Many real-world tasks (e.g., office workflows, scientific experimentation) require LLM agents to interact repeatedly with their environments for context-dependent operations. However, such environments are often not agent-ready. First, information is often scattered and fragmented across the environment. Second, relevant evidence in the environment is often mixed with misleading information and conflicting versions. Third, environments evolve over time, introducing new noise and more challenging tasks. These challenges can substantially degrade performance for state-of-the-art AI agents (e.g., from 83.9% to 57.6%). To address these challenges, we propose Env-Rethink (a system with 27B post-trained model) that supports three main capabilities: (1) It adaptively builds Collection Maps (for organizing related files) and Event Logs (for contextualizing cross-data relationships) to supplement necessary context; (2) It further leverages the post-trained model (through offline trajectory learning) to identify underlying noise issues in the environment; (3) It ultimately evolves environments through virtual event histories that alter environmental states and evidence relationships, producing more tricky ones for further agent improvement. Experiments show that Env-Rethink can effectively improve downstream task performance (with over 15.1% rubric pass rate improvement across nine models on 30 tasks).

Radar nowcasting is essential for short-term warning and emergency response, yet conventional systems mainly return future radar fields and provide limited support for operational communication and post-event verification. We formulate radar nowcasting as an evidence-grounded forecast--bulletin--audit task, in which a numerical forecaster produces both future radar fields and structured diagnostic evidence. Forecast-time bulletins use only model-available evidence, whereas post-event audits incorporate future radar truth only after the forecast horizon is observed. Based on this task formulation, WeatherDiagFlow predicts motion, growth and decay, heavy-echo risk, and uncertainty to condition rolling flow refinement, while frozen-scaffold residual calibration improves long-lead strong-echo preservation. A multi-agent layer converts the structured evidence into operational bulletins and independently generates verification audits without feeding textual outputs back into the forecaster. Experiments on FJRADAR demonstrate competitive overall performance and improved strong-echo event skill. WeatherDiagFlow therefore connects numerical prediction, evidence-grounded reporting, and auditable verification under a leakage-controlled protocol.

We ask whether Jev, a typed classifier that returns probabilities over permitted answers without generating text, can replace an LLM rubric judge. We compare it with three flash-tier LLM judges on nine panels drawn from seven benchmarks, giving every judge identical criterion texts. Jev's accuracy differs significantly from an LLM judge's in only 8 of 27 paired comparisons, ahead mostly on binary criteria and behind only on graded ones, and most of the other comparisons are inconclusive. Summed over the nine panels, the LLM judges, called once per criterion, cost 29 to 325 times as much as Jev and took 30 to 220 times as long. On graded criteria all four judges agree more with one another than with the labels and mostly assign lower levels than the raters. One of several observational accounts is that raters followed scale conventions our criterion texts omit. Jev's confidence ranks its own errors on most panels, which should make a cheap classifier the ideal first stage of a cascade that defers its uncertain verdicts to an LLM judge. Correlated errors undo that advantage. The LLM judges repeat nearly all of Jev's most confident errors, so a cascade replayed on the recorded verdicts lowers cost but gains at most 1.5 points over the best single judge with cross-fitted thresholds, and at most 2.0 even with oracle thresholds.

Cross-speaker acoustic-to-articulatory inversion requires accounting for anatomical differences between speakers. We propose a geometric adaptation framework that uses anatomical landmarks, primarily on vertebrae and dental structures,to transfer predictions from a fixed inversion model to unseen speakers. An affine transformation followed by thin-plate spline (TPS) deformation maps the predicted contours of 10 vocal-tract structures into each target speaker's geometry without retraining. Landmarks are identified in one selected /u/ frame per speaker as a common phonetic reference without assuming identical articulatory configurations across speakers, and the resulting mapping is reused across recordings. We train the model on a single-speaker rt-MRI database and evaluate adaptation on eight speakers from a separate multi-speaker rt-MRI database. We compare affine and TPS configurations using 12 or 14 landmarks. Affine12+TPS14 achieves the lowest mean point-to-closest-point error of 3.19mm. These results support the combined value of anatomical landmark information and nonrigid alignment.

How phenotypic transformations are implemented by changes in underlying regulatory dynamics remains a central question in developmental biology. Inspired by D'Arcy Thompson's 1917 "On Growth and Form", we ask whether coherent large-scale transformations of morphology can be encoded as low-dimensional modulations of a self-organizing developmental system. We use neural cellular automata (NCAs) as bio-inspired models of distributed development, in which a shared local regulatory network grows target morphologies from a single cell. We apply low-rank adaptation (LoRA) to pretrained NCAs, representing each adapted developmental program as a low-rank modulation of a fixed regulatory scaffold. Horizontal and vertical scaling of a fully grown 2D emoji phenotype can each be implemented by rank-one adaptations. Their linear combinations parametrically control phenotype size, generalize beyond the training distribution, and compose with target-specific adapters. Strikingly, adaptations learned for one phenotype transfer zero-shot across structurally and semantically diverse phenotypes sharing the same reference scaffold, while largely preserving internal features. This suggests reusable system-level hyper-directions of scale rather than morphology-specific transformations. From approximately 25,000 independently trained phenotype-specific NCA adapters with a shared scaffold, we further identify latent low-dimensional directions that functionally control phenotypic variation including scaling, style, and symmetrical fission. Together, our results provide a computational realization of D'Arcy Thompson's remarkable grid transformations in a 2D NCA---a minimal cybernetic tissue in which variations of fully grown emoji phenotypes can be encoded, combined, and controlled through low-dimensional directions in regulatory weight space.

Current multimodal software-engineering benchmarks expose images as additional context, but do not test whether an agent can integrate evidence distributed across images into a verified repository-level repair. We present SWE-PolyVision, an executable benchmark of 92 real tasks from 36 open-source organizations, with 48 public tasks and 44 private holdouts. The release contains 402 static images and 6 videos, with at least two visual inputs per task. Each task pairs a fixed pre-fix repository with an isolated verifier and is evaluated under the supported conditions among three access modes: Text-only, Native Vision, and Tool-mediated Vision. Across eleven coding models, visual access changes which tasks are solved, but effects depend on both model and task. Two trace-linked Native Vision cases illustrate how complementary visual and textual clues can lead to source-localized, verified repairs; controlled interventions show that this conversion is not yet stable across inputs. SWE-PolyVision thus separates the availability of multi-image evidence from its successful use in repository-level repair, without treating patch success alone as proof of explicit reasoning.

We present: (i) a new dataset consisting of the full development history of a 21,000-line Python tool built entirely by Claude AI, with no human-authored code or tests, (ii) two code-provenance tracing tools, (iii) three taxonomies for instruction intent, commit provenance, and response reliability, (iv) application of these to analyse the dataset. We find that: (i) user coding agent CLI instructions differ in kind from IDE-chat instructions, with a greater focus on comprehension, planning and consultation, (ii) code development is mainly proactive, (iii) 14.3% of AI code-generation events contain a real error later caught by the AI-authored test suite, (iv) roughly 1 in 4-5 of the AI's interactive responses contains one or more factual errors.

Objective: Heart failure (HF) presents a healthcare challenge due to its high comorbidity burden, aging patient population and frequent hospitalizations. Remote monitoring offers a promising approach to managing HF patients by early detection of health deterioration. Developing autonomous systems to detect signs of worsening in telemonitoring data is of interest to reduce the workload of healthcare personnel. Methods: We propose the TRACER model, a Transformer with Contrastive Event Representation, designed to predict timelines leading to rare hospitalization events in low-resolution and irregularly sampled telemonitoring data. TRACER incorporates time-aware embeddings for each biomarker, contrastive pre-training to enhance anomaly detection via representation learning, and independent binary classifiers for detection. We used measurement data containing remotely recorded biomarker sequences from 276 HF patients segmented into overlapping windows based on temporal rules, and labeled the windows based on the occurrence of HF relevant hospitalizations at the latter edge of the window. Results: TRACER was able to correctly predict 66.7% timelines leading up to HF hospitalizations in the highly imbalanced real-world dataset with an overestimation of 7.9%. Reformulating the training of TRACER as an event detection problem improved the predictive performance compared with training directly on forecasting windows, enabling more effective use of the limited hospitalization events. Conclusion: TRACER demonstrated superior performance in detecting signs of worsening status in real-world telemonitoring data compared to the other tested models. Significance: TRACER shows promise in identifying signs of clinical deterioration that allow for alerts to be generated to provide counteractive treatment in patients with HF.

Ligand-based virtual screening (LBVS) is a practical first-pass tool in early-stage drug discovery, but existing benchmarks can overestimate performance through random negatives, easy decoys, limited target coverage, and non-standardized evaluation protocols. We introduce TopU-LBVS, a multi-target benchmark for LBVS under hard-negative screening conditions. Starting from curated ChEMBL~35 bioactivity data, TopU-LBVS covers 93 protein targets across 7 protein classes and constructs target-specific screening libraries with property-matched, structurally similar decoys at a fixed 1:40 active-to-decoy ratio. Libraries contain roughly 400 to 10,000 compounds and are designed to reduce simple physicochemical and nearest-neighbor fingerprint shortcuts. TopU-LBVS provides three fixed protocols. TopU-LBVS-full evaluates ChEMBL$^\ast \rightarrow$ TopU generalization across all 93 targets. TopU-LBVS-low evaluates low-data TopU $\rightarrow$ TopU learning within the hard-negative distribution. TopU-LBVS-mini provides a compact seven-target protocol with a paired random-decoy control that changes only the test decoys, enabling low-cost development and direct measurement of the gap between random ChEMBL$^\ast$ and TopU decoys. Across ten reference baselines spanning fingerprint methods, molecular GNNs, fingerprint hybrids, and modern molecular models, performance under random-decoy evaluation degrades sharply under hard-negative screening. We release data, fixed splits, evaluation code, and baseline implementations for reproducible comparison of future LBVS and molecular representation learning methods. Code and data are available at https://github.com/topu-benchmark/topu-lbvs and https://huggingface.co/datasets/topu-benchmark/topu-lbvs.

Long-horizon tasks require preserving and later recovering cross-session evidence under a bounded, query-blind memory budget. Existing compression can discard fine-grained visual cues or conflate semantically similar but incompatible observations. We present C3M, a cross-session multimodal memory organization that maintains a bounded active index over persistent source text-image evidence. Relation-aware updates consolidate safe redundancy while preserving complementary and incompatible records. At query time, budgeted routing selects useful index pages and expands their associated source evidence under a fixed reader budget. Together, these mechanisms establish a compact, provenance-preserving multimodal memory organization for cross-session long-horizon tasks, retaining temporal distinctions and source links required for reliable downstream reasoning. Code is available at https://github.com/HuzhouNLP/C3M.

Arabic-language stance detection remains challenging, and previous shared-task systems have largely relied on multitask learning and ensembles. While these systems achieve state-of-the-art performance, their applicability and transferability are limited by the additional complexity introduced by multitask learning.To reduce this complexity, we introduce $\texttt{CLASP-Ar}$, which reformulates the task as cloze-style masked language modeling. In this approach, the target, predicted sentiment, and text are combined into a single prompt whose $\texttt{[MASK]}$ prediction is restricted to a verbalizer-constrained label vocabulary.

Bias in AI systems is typically framed as a flaw to be minimized, yet it also serves as a critical indicator of underlying weaknesses in data, modeling assumptions, and system design. Existing approaches often treat bias as an isolated problem rather than as evidence that can strengthen verification and governance across the AI lifecycle. This paper aims to reconceptualize bias as a diagnostic tool that supports rigorous AI verification. We seek to develop a multidimensional framework to analyze bias, demonstrate how biases emerge in both Traditional and Generative AI, and provide a structured pathway for verification-driven mitigation. We present a multidimensional framework analyzing bias across four dimensions: origin sources, emergence points throughout the AI modeling lifecycle, technical and methodological causes, and validation approaches for detection and mitigation. Through a comprehensive typology spanning traditional and generative AI systems, we demonstrate how biases manifest and propagate across development stages. Our analysis encompasses 30 distinct bias types, 16 verification methods, and 20 countermeasures, providing an actionable roadmap for practitioners. We introduce a hierarchical evidence framework that distinguishes internal validity (mechanistic integrity of AI systems) from external validity (contextual reliability in deployment environments). The framework reveals how biases manifest and propagate across modeling stages, enabling systematic mapping between bias types, verification techniques, and effective countermeasures. The proposed evidence hierarchy clarifies how different verification strategies contribute to mechanistic integrity and contextual reliability. We advocate for ''Ethics by Design'' principles that integrate bias verification throughout the development lifecycle, enabling the construction of fairer, more robust, and trustworthy AI systems.

On-demand delivery platforms pay riders through incentive activities whose tiers are set from recent completions of riders with a similar history. Operators request such plans for changing periods, rider populations, payment rules and budgets, often for holidays or bad weather, where randomized trials are scarce and take months to collect. We present a request-driven framework that composes four stages (conditional prediction, population reduction, trajectory integration and budget allocation) through seven replaceable modules that exchange conditional trajectory laws, whose award probabilities and award-marked moments give payment and uplift for any activity rule. A response-correction step reweights trajectories from abundant no-offer history to match the moments of a short pilot. We prove that, on a fixed plan menu and given the stage errors, the end-to-end value loss is bounded by the sum of four stage terms, and that for every stage there are instances on which omitting it leaves an error floor the others cannot remove. On 3,000 riders over 45 weekly origins, all 127 windows of a week are answered 11.04x faster with identical scenarios and at most 0.92% value lost by the allocation. On 24 new controlled response laws, the response correction with a one-week pilot lowers regret by 51.2% relative to a trial with the same nominal randomized rider-weeks, and a four-week pilot with exact summation comes within +0.007 of an 18-week trial. In registered studies where windows, populations, rules and binding budgets change from request to request, the framework's regret is below that of a trial with the same nominal rider-weeks and below dose interpolation of the same pilot data, and reusing its one-off preparation answers 60 requests 14.1x and 2.70x faster with identical answers. Against a nine-offer trial fitted with the framework's own dose curve, one-week regret is 0.055 lower.

Information flow analysis (IFA) is a powerful technique for verifying confidentiality and integrity and is therefore highly desirable for security-sensitive embedded systems. However, as these systems are inherently concurrent and time-dependent, existing IFA for embedded systems tend to be either imprecise or expensive. In this paper, we propose an approach to tackle this problem using automatic abstraction refinement. The key idea is to heuristically choose abstraction levels based on information about dependencies between states and detected potential information leakage. Our approach builds on previous work, where we leverage symbolic execution to precisely capture data, control, timing, and event dependencies between processes within an IFA. To capture values symbolically, this analysis uses abstract interpretation. While the existing approach requires manual definition of abstraction levels, our novel contribution in this paper is using carefully designed heuristics to select these levels automatically. The aim is to keep analysis times acceptable while also retaining enough information to decide whether or not illegal information flow is possible. We have implemented our approach for the system design language SystemC and demonstrate its feasibility with experimental results on several shared bus architectures.

We present TTLab's submission to the AlexandriaX-2026 Subtask~3 on Arabic MT error span detection and classification. Our system frames the task as token-level classification over surface forms, preserving character offsets to ensure exact alignment with the evaluation metric. To handle severe label imbalance, we employ a focal loss with class weighting and dialect-specific decoding thresholds. Among six Arabic pre-trained encoders, MARBERTv2 achieves the best overall performance of 40.8 and 40.91 on the development and test set, respectively, ranking $\nth{3}$ out of all participating teams. While our system localizes error spans effectively, classification of rare error types remains challenging, highlighting the need for data augmentation for tail categories. The code is available at ${\href{https://github.com/ENTAILab/arabic-dialectal-mt-error-span-detection}{\faGithub~ TTLab at AlexandriaX-2026}$

Public software repositories, like GitHub and Software Heritage Archive, store billions of files, yet extracting their implicit engineering knowledge ---i.e., the algorithms they implement, the paradigms they follow, the patterns they instantiate, and the application domains they serve--- remains challenging, as current tools are constrained to syntactic and token-level analysis. We present a pipeline for building an open-taxonomy semantic annotation of source code using a code-specialised Large Language Model. The extracted entities are grounded in Wikidata through a three-stage linking procedure: a deterministic SPARQL stage handles unambiguous entities, a Deep Research Agent resolves the residual long tail, and a hierarchy-rollup stage imports the parent-of closure of each resolved Wikidata identifier. The resulting annotations are materialised as a source-code-specific open-taxonomy knowledge graph. We further introduce a calibrated quality-assurance protocol that quantifies annotation precision by combining a small human gold set with an LLM-as-a-judge filter. We applied our pipeline to the 167 million files of the Stack-Edu corpus, creating the first known large-scale open-taxonomy knowledge graph for source code. Our graph, named CodeGraph, contains approximately 158 million nodes, which include around 145 million files, about 63,000 extracted concept entities (such as algorithms, paradigms, design patterns, and application domains), and roughly 19,800 grounded Wikidata entities. Furthermore, CodeGraph features approximately 1 billion typed edges that connect files to their respective concepts, link these concepts to their grounded Wikidata identifiers, and relate them to their parent categories, covering 14 programming languages.

Generative artificial intelligence has moved from a disruptive novelty to a recurring part of software-development and computing-education workflows, while software agents are beginning to act across repositories, command lines, browsers, tests, and other tools. The educational problem is no longer whether students should be allowed to generate code, but whether software-engineering (SE) programs can preserve and assess human understanding while preparing students to work responsibly with increasingly capable AI systems. This paper presents a structured integrative review of research and practice from 2023 through 23 September 2026, supplemented by established work on AI literacy, technical debt, and human-AI collaboration. The evidence supports a conditional conclusion: GenAI can improve access to explanations, feedback, practice, and short-term task completion, but learning outcomes depend on prior knowledge, scaffolding, verification, task design, and assessment. We examine student help-seeking and authorship, faculty assessment and policy demands, and the wider SE risks created when generated artifacts persist across repositories, teams, architectures, and deployed systems. We extend the concept of comprehension debt: the deferred learning and maintenance cost that arises when AI-assisted production outpaces a learner's or team's ability to explain, test, modify, and justify the resulting software. We then refine the AI-Augmented Software Engineering Education (AASEE) framework into five non-linear integration levels and four cross-cutting evidence obligations: explain, verify, modify, and account. The framework links delegation to evidence, governance, and recovery mechanisms appropriate to its consequences.

Approximate message passing on factor graphs underlies two dominant families of probabilistic inference algorithms: expectation propagation (EP) and variational message passing (VMP). Both methods approximate the marginal at each factor edge, forcing an iterative round-robin schedule, risking negative-precision messages, and, for VMP, collapsing to point estimates at Dirac-delta factors. We introduce Direct Message Approximation (DMA), which approximates factor-to-variable messages directly rather than the marginal. For normalisable factors, we define a consistency condition (requiring exactness when all other incoming messages are Dirac deltas) to guide message construction. We prove a master theorem (proper messages, any graph) bounding marginal KL from message KL, with three structural corollaries: Dirac-input consistency, no EP-style inner-loop iteration, and no negative-precision messages. Further, we prove a complementary $O(1/r^2)$ guarantee for the inherently improper backward message of the product factor, whose closed-form treatment has resisted prior work. As a concrete instantiation, we derive explicit DMA messages for the product and leaky-ReLU factors and assemble a Bayesian neural network (BNN) inference algorithm with one forward/backward sweep per training example and no gradient learning-rate hyperparameter, validating that the structural guarantees translate to predictive uncertainty that widens in data-sparse regions, including under model mismatch.

Large language model based coding agents have made substantial progress on repository-level software engineering tasks. Existing repository benchmarks, however, usually start from a human-identified issue and evaluate whether a patch satisfies a functional signal. We present SWE-Prometheus, a benchmark for the broader task of improving repository engineering governance. Each task provides a fixed snapshot and an open-ended objective, requiring the agent to identify risks, prioritize interventions, and verify the resulting changes. SWE-Prometheus evaluates six governance dimensions through paired evidence, clean-environment probes, behavior gates, and two independent teacher ratings of the same evidence. The benchmark contains 60 repositories; ten models are evaluated on a shared 22-repository public subset, where mean Normalized Governance Improvement ranges from 0.0568 to 0.5760 and observed behavior-breakage rates range from 0% to 23%. On a frozen ten-repository batch, a repository-blind template obtains mean NGI 0.272, but its gains concentrate in Tests & CI, Quality Gates, and Documentation; it improves Reproducible Environment and Dependency & Security on none of the repositories. This baseline makes the distinction between adding governance artifacts and producing execution-backed improvements measurable. The no-op condition has median NGI zero and standard deviation 0.073; two teachers agree exactly on 57 of 60 dimension scores for the same no-op evidence. For the two highest conditional-mean systems, common-valid NGI is similar, while full-pool comparisons that include behavior failures favor Kimi-K3. These results show why repository-governance evaluation should report improvement, behavior preservation, evidence quality, and coverage together.

Accurate counting and localization of plants and their organs support phenotyping and yield estimation, yet target appearance, scale, and density vary widely across species and imaging conditions. Exemplar boxes specify the target without category-specific retraining, and point predictions identify the individual instances contributing to the count. We introduce AgriCountDINO, a parameter-efficient exemplar-guided framework for joint counting and localization. It conditions frozen multiscale DINOv3 features on exemplar appearance and size, then progressively decodes them into target points. Missed-object recovery extends supervision to targets overlooked by initial matching, and exemplar-adaptive point NMS filters duplicate predictions according to exemplar scale. With 8.4M trainable parameters, approximately one-tenth of TasselNetV4's, AgriCountDINO achieves a three-shot MAE of 11.92 on the TPC-268 benchmark, reducing counting error by 9.7\% while providing individual target locations. Trained only on TPC-268, it achieves a zero-shot MAE of 14.25 on unseen generic object categories in FSC-147, improving upon the best compared zero-shot method by 6.0\% without target-domain training or fine-tuning.

We present a tightened convergence analysis of clipped gradient descent on $(L_0, L_1)$-smooth functions, with quantitative constants. Building on the ideas of Koloskova et al (2023), we refactor several case disjunctions to reveal the central role of a control of the bias derived from fundamental properties of $\ell_2$-projection, simplifying proofs. We also extend the domain of validity from $η\leq 1 / (9 β)$ to $η< 1 /β$ where $β= L_0 + c L_1$ for clipping constant $c$, which matches the more traditional analysis of smooth functions. We strengthen the convergence criterion from $\left( \min_{t < T} \mathbb{E}[\lVert \nabla f(x_t) \rVert_2] \right)$ to $\left( \frac{1}{T} \sum_{t < T} \mathbb{E}[\lVert \nabla f(x_t) \rVert_2] \right)$ with matching speed, and lower the final achievable loss from $\mathcal{O}(\min(σ^2/c, σ))$ to the more precise $6 \min(σ^2 /c, 3 σ)$.

LLM agents, notably Claude Code and OpenAI Codex, are emerging as versatile tools beyond coding agents only. These agents can be enhanced with skills---reusable artifacts that package domain knowledge, workflows, and tool-use instructions. To date, however, little is known about how such skills are designed or how they affect agent effectiveness and behavior in practice. In this paper, we investigate these questions in smart contract security auditing, a domain in which agents have shown substantial promise. We systematically collect 83 smart contract audit skills from the wild and evaluate them on EVMBench across seven agent--model configurations. Our study examines three dimensions: (i) the design characteristics of audit skills, including their structure, knowledge representations, workflows, and tool dependencies; (ii) their effectiveness in improving vulnerability detection; and (iii) their influence on agent execution trajectories. We find that audit skills are mostly lightweight but heterogeneous in design, covering a broad yet imbalanced range of vulnerability types. Their effectiveness is determined primarily by the model rather than the agent harness: Codex/GPT-5.5 achieves the largest gains, improving detection score by 22.8% and captured award by 43.2%. We further find that skill triggering is a key bottleneck. When triggered, skills preserve a shared six-stage audit workflow while exhibiting distinct loading patterns and differential effects on agent behavior across configurations. We release our skill corpus and artifacts to support future research.

We formalize slate recommendation as a randomized score learner followed by deterministic selection. First, an appropriately scoped differential-privacy guarantee passes through selection and its audit trace by post-processing. End-to-end privacy holds only when selector inputs are public or independent, previous private outputs, or separately privacy-accounted; fixing raw state or candidate information instead yields only a conditional guarantee. Second, we derive a logged margin certificate: bounded score-induced objective movement below half the smallest greedy decision margin guarantees that the ordered slate is unchanged. Controlled fixed-margin tests show near-linear exponent scaling, with an empirical slope of $-0.220$ (95% CI $[-0.231,-0.210]$) against the independent-noise reference $-1/4$. Real-anchor experiments on OULAD, MovieLens-25M, and Amazon Musical Instruments show that greater anchor weight reduces score-noise-induced ranking churn. OULAD and EdNet certificate checks validate the implementation of the logged inequality, while closed-loop simulations show bounded target drift and setting-dependent downstream utility. The contribution is therefore a privacy-scope contract and a certifiable score-to-slate stability mechanism, not a universal utility claim.

We present YODAS v3, a weakly-labeled speech corpus containing over 1.1 million hours of 48kHz multi-channel audio in 147 languages, released under a CC BY 3.0 license. YODAS v3 is not only the largest open speech dataset to date, but also the first truly large-scale speech corpus with high-fidelity stereo audio. We first provide the collection methodology for the corpus, where we introduce new techniques for gathering language-balanced speech data. The effectiveness of our approach is shown by the language distribution of the crawled data: 22 languages in YODAS v3 have over 10K hours and 73 languages have over 5K hours of data. We then conduct extensive analyses on the composition of the data, such as the distribution of languages, audio quality, and transcription quality. Finally, we train baseline speech recognition and neural codec models to show the effectiveness of the dataset. Download at https://huggingface.co/datasets/espnet/yodas3.

Smart maritime infrastructures provide continuous access to heterogeneous sensing streams, enabling repeated experimentation, digital-twin development, and AI-based maritime services. However, sensing hardware alone is not sufficient for scene-specific model development: historical video streams must also be spatially indexed, contextualized, and reduced to informative subsets for annotation. This paper presents a frame-to-panorama localization and context-aware sampling pipeline for ship detection in historical PTZ maritime video lacking reliable pan, tilt, and zoom metadata. The main contribution is an end-to-end data-curation approach that recovers camera-view information from historical PTZ video and combines it with environmental context and visual diversity to construct compact, scene-specific training sets. Specifically, frames are localized on a reference panorama using SuperPoint and LightGlue, enriched with weather and solar-state metadata, and selected through diversity sampling to preserve variation across camera view and environmental conditions. A second context-aware stage targets under-represented distant-vessel cases near the horizon using tile-level visual embeddings and Gaussian Mixture Model clustering. Applied within the CMMI MDigi-I Smart Marina testbed, the proposed pipeline reduces 40,718 candidate frames to 220 images for annotation, corresponding to a 99.5% reduction. A YOLO26-m detector fine-tuned on this subset achieves a mean AP50 of 94.78% $\pm$ 0.51% and a mean AP50-95 of 75.10% $\pm$ 1.73% under sequence-grouped five-fold cross-validation. These results demonstrate that highly redundant infrastructure video streams can be transformed into compact, spatially and contextually diverse training sets for scene-specific detector adaptation while substantially reducing annotation effort.

Reducing communication in derivative-free decentralized learning requires controlling the disagreement accumulated over multiple local updates. This paper develops SPADE-DFL, a primal--dual method that allows the number of local function-value updates between neighbor exchanges to grow with the computation budget while preserving the nonprivate convergence order. For smooth nonconvex objectives under uniform query-moment bounds, the prescribed nonprivate schedule achieves a time-averaged stationarity and consensus bound of $\mathcal{O}(T^{-1/3})$ using only $Θ(T^{2/3})$ communication rounds, where $T$ is the number of local updates per client. For private training, the accumulated data-dependent increment is isolated from the graph correction, allowing one protected state per client and round to generate all outgoing messages. We prove client-level differential privacy for the full interactive transcript and quantify the resulting optimization error over a finite horizon. Experiments on four classification tasks show that SPADE-DFL achieves higher mean test accuracy than existing decentralized learning methods.

Deep search requires LLM agents to decompose complex queries, search for evidence, and synthesize grounded answers, yet existing ReAct-style agents suffer from two limitations: role coupling, where one policy must handle planning, evidence use, and synthesis; and context accumulation, where growing search histories introduce noise and obscure useful information. To address these issues, we propose IterSynth, a role-decoupled and summary-based paradigm that alternates between a Planner for identifying information needs and a Synthesizer for integrating evidence into an evolving summary state. This design separates planning from synthesis while using the summary as the persistent state of search, reducing both capability coupling and context noise. To train IterSynth effectively, we further introduce Role-Decoupled Policy Optimization (RDPO) for reinforcement learning, which combines terminal outcome rewards with turn-level rubric evaluations and computes role-specific advantages for more precise credit assignment. Experiments on five long-horizon deep-search benchmarks such as BrowseComp and Xbench-DS show that IterSynth-8B achieves an average score of 50.7, surpassing the strongest prior $\leq$8B agent by +4.2\%. Moreover, IterSynth serves as a model-agnostic prompting paradigm, delivering substantial zero-shot gains over ReAct and similar prompting paradigms on frontier proprietary models.

We audit a multilingual affective generation benchmark eight instruction-tuned LLMs producing emoji summaries for 17,100 Bangla, English and Hindi sentences, with 6,960 human judgements and find its headline conclusions to be artefacts of the measurement instrument rather than properties of the systems. Treating annotators as a random rather than a fixed factor, no system differs significantly from any other ($F(7,14)=0.59$, $p=0.76$), although the conventional analysis declares 19 of 28 pairwise differences significant. Annotator identity explains far more rating variance than system identity, and the winning system changes whenever any single annotator is removed. The ordering that does emerge tracks output length: mean emoji count explains 78.7\% of between-system variance, and a within-item length-matched comparison over 2,599 pairs reverses the leaderboard. We further show that cross-provider anisotropy differences vanish under mean-centring, that per-language token costs change sign with the normalising unit, and that multi-view row-wise splits inflate macro-F1 by $3.1$ points and change the top-ranked system. In place of preference scoring we propose **emoji-affect decodability**, a reference-based probe whose rankings are stable to $\pm0.003$ macro-F1 across seeds.

Background: Artificial intelligence (AI)-based glaucoma detection from colour fundus photographs (CFP) offers scalable screening, but performance may decline on external datasets because of differences in ground-truth definitions, populations, and coexisting conditions such as high myopia (HM). We developed and validated a Vision Transformer-based deep learning (DL) model for glaucoma detection across multi-ethnic cohorts with and without HM. Methods: A ViT-B/16 model with predictive uncertainty estimation was developed using 56,483 CFPs (57.1% with myopia; 14.4% with HM). Glaucoma labels were standardised using clinical, imaging, and perimetry data. The model was validated on 16 independent datasets across three continents, including four datasets with explicit HM labels. Findings: Internal AUROC was 98.7% (95% CI 98.2-99.1%), with sensitivity 94.5% and specificity 97.3%. Across 16 external datasets from eight countries, AUROCs ranged from 86.4% to 99.6%. In HM eyes, internal AUROC was 97.8% (95% CI 96.1-99.2%), with sensitivity 94.8% and specificity 93.7%. External HM AUROCs were 86.5% in the Beijing Eye Study and 93.3%, 91.8%, and 85.5% in hospital-based datasets from Taiwan, Thailand, and South Korea. In an exploratory HM clinical evaluation, the model had higher CFP-only diagnostic accuracy than ophthalmologists and trained graders (92.0% vs 70.0%; p=0.008) and performed comparably to glaucoma specialists using full clinical information. Interpretation: The model showed robust glaucoma detection across myopic and non-myopic multi-ethnic populations and may support AI-assisted screening in settings with high HM prevalence.

Detectors of alignment failures screen deployed language models and score alignment benchmarks. Most are generative judges that spend a decoding pass on every criterion, and classifiers that read token probabilities, such as Llama Guard, still score one fixed label per call. Jev, a model trained with reinforcement learning for calibrated decisions (RLCD), answers many typed questions about one input with calibrated probabilities in a single call. Whether it detects alignment failures has not been measured. We present RLCDAlignBench, which benchmarks Jev on ten alignment failures: sycophancy, jailbreaks, deception, prompt injection, hallucination, privacy violation, social bias, reward hacking, concealing uncertainty, and power seeking. It spans 44 benchmarks and five target models, labelled by each benchmark's scorer and, on two, by humans. Many of these failures are relational, defined against a reference, such as the user's belief or an injected instruction, that the response alone does not reveal. Our key idea is therefore to vary what Jev is asked separately from what it sees: the question's wording and answer type on one side, the fields of the input on the other. A single generic question reaches a median AUROC of 0.886 zero-shot and beats supervised baselines on most benchmarks. Question wording matters little, while context matters more, mostly through fields that encode the label. Jev matches the reference scorer's agreement with human labels, surfaces label defects in existing benchmarks, and costs 63x less than LLM-judge scorers. Code and data: https://github.com/sumleo/RLCDAlignBench.

Recent advances in speech language models have improved automatic speech recognition (ASR) for long-form audio. However, accurately and consistently transcribing domain-specific terminology remains challenging. Motivated by the world knowledge and contextual capability of large language models (LLMs), we propose Agentic-GER, an LLM-based agent for terminology correction in long-form speech. The agent uses global context from the full transcript to identify suspicious terms and resolve ambiguous hypotheses. It selectively re-transcribes the source speech to check candidate corrections, and uses accepted edits to guide subsequent decisions. Experiments with four LLMs and two ASR systems on GigaSpeechBench show consistent terminology improvements in both Chinese and English, with and without thinking. On Chinese speech, Agentic-GER achieves up to a 36.8% relative reduction in biased character error rate (B-CER) over the Whisper baseline.

Rufus-Air is an open and reproducible post-training recipe on GLM-4.5-Air-Base (106B-A12B), organized as a serial pipeline of eight stages: SFT, Reasoning RL, Coding RL, Instruction-Following RL, General Agent, Coding Agent, Search Agent, and RLHF. We document the data, reward design, infrastructure, stage order, and stagewise results needed to reproduce the recipe. Stages progress from basic to advanced capabilities and from hard, verifiable rewards to softer judge-based signals. Training builds on open-source components and public data, much of it used as released, without new human annotation or an in-house distillation teacher. Our main findings are that (i) diverse, high-quality SFT establishes a strong capability floor; (ii) difficulty filtering keeps RL prompts within a productive learning range; (iii) reward reliability provides a practical principle for ordering stages; and (iv) infrastructure and engineering choices are part of the recipe, not just an implementation detail. Rufus-Air improves over the official GLM-4.5-Air post-trained release and is competitive with similarly sized open models.

Backchannels, brief acknowledgements like "uh-huh" produced while the other party may still be talking, are central to natural conversation, but full-duplex spoken dialogue models rarely model them explicitly. We introduce a lightweight backchannel head that predicts, from a full-duplex model's own hidden states, when a backchannel should begin. Once this probability crosses a tunable threshold, a backchannel is force-decoded. Attached to both a 7B (PersonaPlex) and a 1B (F-Actor) model, it generalizes across scale. Probing confirms the hidden states anticipate real human timing, and generation evaluation shows more frequent, better-timed backchannels. Human raters judge the resulting backchannels on par with real ones.

Sampling from Boltzmann distributions of molecular systems is an inference problem that has seen significant recent developments fuelled by advances in neural density estimation. We develop a novel sampling algorithm, Neural Transport Nested Sampling (NTNS), which combines the classical strengths of nested sampling with modern neural flow-based methods. NTNS uses a flow matching velocity as the drift in a Metropolis--Hastings corrected Langevin kernel inside a nested sampling outer loop, requiring only evaluations of the target energy function and providing scalable estimation of the full partition function of high-dimensional particle systems. We benchmark NTNS on challenging molecular sampling benchmarks, scaling up to Lennard--Jones clusters of 55 interacting particles, where it reduces both interatomic distance and energy Wasserstein errors to reference MCMC by over an order of magnitude relative to the strongest neural baselines at lower wall-clock cost. To our knowledge, NTNS is also the first neural sampler to return a calibrated, temperature resolved partition function estimate at this scale, recovering the phase structure across temperature from a single run.

Recent studies have shown that Large Language Models can effectively solve problems and fix bugs in diverse programming environments, including competitive programming. Existing approaches primarily evaluate LLM performance in problem solving or bug fixing independently, but do not explore the relationship between these two capabilities. This work focuses on determining how much the LLM deviates from a buggy solution to fix the bug compared to a human-written patch, and if there is a bias towards generating entirely new solutions. We construct a dataset with all the submissions ($\sim$ 3000) from a couple of users from Codeforces, and we match each buggy submission with its corresponding human fix. By using the similarity between the buggy solution and the human fix as a baseline, we evaluate the quality of LLM-generated bug fixes on 3 OpenAI GPT models (gpt-5-nano, gpt-5-mini, gpt-5.1). We check if the generated solutions solve the problem by using the Codeforces-R1 dataset, an openly available dataset that has tests generated with the DeepSeek-R1 model. Our findings suggest that LLMs tend to modify more lines than necessary compared to human fixes and, in some cases, generate entirely new solutions. We also observe that LLMs solve more problems correctly when allowed to generate solutions from scratch rather than patch buggy submissions, even when those submissions are close to the human patch. This has important implications for the design of AI-assisted programming tools, particularly in supporting user debugging processes and promoting incremental problem-solving strategies rather than solution replacement.

In this paper, a method for achieving exact unlearning for Gibbs supervised learning algorithms is proposed using a variational formulation inspired by empirical risk minimization subject to relative entropy regularization (ERM-RER). Such a method consists of maximizing the expected empirical risk over the dataset to be unlearned subject to a regularization by relative entropy with respect to the original algorithm. The optimization variable is a probability measure on the models; and the solution is another Gibbs probability measure that represents a new Gibbs supervised learning algorithm. The method guarantees exact unlearning in the sense that the new Gibbs algorithm coincides in distribution with the algorithm that would have been obtained by retraining from scratch on the dataset to be retained. As a byproduct, a framework for reweighting data points in ERM-RER by strategically choosing both the reference measure and the regularization factor is obtained. In this framework, exact unlearning is the special case in which zero-weight is assigned to the contribution of the data points to be unlearned. More generally, depending on the choice of certain parameters, data points can be up-weighted or down-weighted in ERM-RER problems for particular purposes, e.g., controlling the generalization error of Gibbs algorithms. This paves the way for new constructive or adversarial views on classical reweighting data points in ERM-RER.

We adapt Reinforce Adjoint Matching (RAM), a reward-based post-training method, to generative speech enhancement (SE). Starting from a pretrained SE model, RAM tilts the model's conditional distribution toward outputs with higher reward. During training, the current model generates enhanced speech on-policy, evaluates each generated endpoint with a potentially non-differentiable reward, and analytically re-noises the endpoint to construct inputs for a reward-guided regression objective. This enables post-training directly on real recordings using weak supervision, such as text transcripts, without requiring paired clean speech targets or reward gradients. We investigate word error rate (WER)-based post-training and whether recognition performance can be improved without compromising perceptual speech quality. Experiments on real CHiME-4 recordings reduce WER by 5.08 percentage points relative to pretrained FlowSE without reducing any of the reported non-intrusive speech quality metrics. A subjective listening test at the default reward scale finds no statistically significant preference between the post-trained and pretrained models.

Learning surrogates for time-dependent partial differential equations often requires a new simulation corpus when the governing operator changes. We introduce RD-JEPA, a joint-embedding predictive architecture for self-supervised pretraining on reaction-diffusion trajectories. A single model is pretrained on five parameterized systems and then adapted to three held-out systems whose reaction operators and trajectories are excluded from pretraining. Using one, five, or ten complete trajectories from a held-out system, RD-JEPA achieves lower mean relative discrete $\ell^2$ field error and mean absolute spatial first-difference error than five supervised surrogate baselines, an independently trained control that removes the trajectory-dependent predictive latent pathway, and an architecture-matched model trained from scratch. Within the evaluated equations, output resolution, forecast horizons, and choices of adaptation trajectories, the results indicate that prediction of future-state representations can support data-efficient adaptation across related reaction-diffusion systems.

Multimodal attributed graphs connect entities, visual content, language, and observed relations. Learning one foundation across such graphs requires more than compressing each node into a fused Euclidean vector. The representation must preserve entity semantics, construct interaction state from graph neighborhoods, and expose that state to prediction units with different geometry. Our empirical study shows why these requirements are inseparable. Higher-grade channels recover pair relations across the foundation graphs, specialized queries reveal information hidden by a generic readout, and rigid blade isolation removes cross-grade capacity. We therefore introduce ICE (Interaction-aware Clifford Encoder), a multimodal graph foundation model built on a node-indexed Clifford latent field. Topology, text, and images enter explicit Cl(3) addresses. Edge-aware geometric products transform these directions into scalar, bivector, and trivector relations over observed neighborhoods. A protected Grade-1 route preserves entity semantics, while the full grade and depth bank remains available to fresh node and link heads. We establish exact cross-grade reachability, node-permutation equivariance, and a bound on the task residual around the semantic score. Experiments span one shared foundation over eleven graphs, six node-classification datasets, three link-prediction datasets, and matched few-shot tasks. ICE ranks first in all 30 reported supervised and few-shot comparisons. Core removals reduce every task summary, and mechanism controls connect the gains to higher-order transport, retained multidepth structure, semantic protection, and direct field access.

Ternary (1.58-bit) weights are attractive for microcontroller-class language models, but the sub-1M-parameter regime rests mainly on isolated, single-seed comparisons. One prominent example reports that a routed ternary block (convolution, diagonal SSM and sparse attention mixed by a per-token router) beats a parameter-matched full-precision transformer by 22% at 60K parameters, attributing this to inductive bias. We re-run it under one fixed recipe, three seeds per cell, 98 byte-level runs on one laptop. (i) Baseline shape dominates: at a 16M-byte budget, param-matched transformers span 22.6% in validation loss purely by depth/width choice - far more than any architecture effect we measure there - and the best-shaped transformer ties the routed model, so the published margin is at least partly a baseline-shape effect; the ordering of shapes reverses with budget, so no single fixed shape can be trusted. (ii) At 130M bytes the routed model does win, by 22.2-24.0% over the three transformer shapes we evaluate there - but a plain gated diagonal-SSM block beats it by a further 9.1%, and the routed model's own router puts most of its weight on its recurrent pathway, so the gain does not require routing. (iii) The ternary penalty differs by architecture at the larger budget (+5.3% best transformer vs. +19.5% routed, +28.1% gated SSM), but we cannot attribute that to architecture alone: our transformers keep learned positional embeddings in full precision, 11-22% of their parameters, so they are less quantized than the models they are compared with. (iv) A 90/10 full-precision-then-ternary schedule beats all-ternary training, but only at a stage-2 learning rate about 10x the pretraining peak; at a conventional fine-tuning rate it looks 15.3% worse, reversing the conclusion. The from-scratch baseline was not itself learning-rate tuned, which bounds (iii) and (iv). Code and run logs released.

This paper presents and evaluates a Deep Learning-based (DL-based) Signal Quality Assessment (SQA) model to distinguish between clean and noisy ambulatory Electrocardiograms (ECG). The model is trained on Copenhagen Center for Health Technology-Contextualized Arrhythmia Database (CACHET-CADB), which, to the best of our knowledge, is the first ambulatory ECG database with both physical and patient-reported contextual data. The model shows stable performance on different databases such as MIT-databases and the latest PyhsioNet/Cinc Challenge 2021 databases. Subsequently, the paper demonstrates how complicated ECG noise can be investigated by the SQA model and the physical contextual data.

Training with a fixed global batch limits how many distributed clients can provide examples in any one step. We examine a way to use additional server workers without increasing the batch processed by an individual workload. Global Clustered Parallel Split Learning (GCPSL) assigns clients to fixed clusters, executes a Parallel Split Learning with Global Sampling (GPSL) workload for each cluster concurrently, and periodically fuses the client and server model segments. In simulations with 256 logical clients, dividing the population across more workloads improves direct data participation, while smaller clusters can incur an accuracy cost. A four-H100 implementation of label-aware GCPSL reaches 85% CIFAR-10 validation accuracy in $6.13 \pm 0.15$ minutes over three matched runs, versus $19.09 \pm 0.45$ minutes when the same workloads are serialized. Within the four-GPU allocation, size-balanced and random fixed affiliations reach the target in similar mean times (5.70 and 5.66 minutes); size balancing increases direct participation by 3.25 percentage points. These measurements characterize a trade-off among execution concurrency, assignment information, participation, and accuracy for stable-client split learning.

LLM evaluation is commonly performed either by prompting models to produce answers or by scoring candidate outputs with likelihood-based metrics. In multiple-choice QA, however, standard likelihood-based scoring is still conditioned on the question and answer set, and can therefore leverage the same task-conditioned answer-selection interface used in prompting. We study a complementary protocol based on likelihood ranking of declarative statements constructed from the same question--answer pairs. Across 95 decoder-only models, ranging from 0.1B to 104B parameters, and 10 MCQA datasets, we find a systematic divergence between declarative-statement likelihood ranking and prompted answering. Statement-likelihood accuracy remains comparatively stable across scale, whereas prompted answering improves sharply with scale and instruction-tuning. These results suggest that likelihood preferences over controlled declarative alternatives and task-conditioned answer selection probe distinct aspects of model behavior, and should not be treated as interchangeable.

The partial label ranking problem is a supervised learning scenario that aims to fit a preference model that predicts a bucket order defined over a set of labels for a given input instance. This problem generalizes the well-known label ranking problem, which, in practice, is limited to outputting total orders of labels. Existing partial label ranking methods have primarily extended label ranking approaches to handle ties in predictions. This paper proposes using multi-output regression to address the partial label ranking problem, introducing an encoder that, during the learning phase, transforms the (possibly incomplete) rankings with ties of labels to multivariate regression targets, an underexplored perspective in both label ranking and partial label ranking. Moreover, during the inference phase, we introduce several post-hoc layers that convert the multi-output regression results into the output bucket order to effectively implement this approach. This framework provides learning strategies that are competitive with the current state-of-the-art partial label ranking methods, as demonstrated through experimental evaluations.

Online handwriting provides a non-invasive and low-cost behavioral biomarker for Alzheimer's disease (AD) detection, as it reflects both cognitive planning and fine motor control. Existing handwriting-based AD detection methods usually rely on global trajectory features or whole-sample representations, which can be strongly affected by individual writing style, task-specific variation, and acquisition noise. In this paper, we propose NormPaST-Risk, a healthy-normative Paper-Air selective trajectory state-space risk network for interpretable AD detection from online handwriting. Instead of treating the entire trajectory as a single holistic representation, our method reformulates AD handwriting detection as local disease-relevant segment discovery. Specifically, a multi-scale temporal encoder captures stroke dynamics at different temporal resolutions, while a selective Paper-Air state-space encoder models long-range handwriting progression and distinguishes on-paper motor execution from in-air planning and transition behaviors. To explicitly characterize abnormal deviations, a healthy normative branch learns normal handwriting dynamics from healthy controls, and a task-aware multi-expert segment-risk module estimates segment-level AD risk calibrated by hidden-state changes and normative deviations. A weakly supervised segment-level objective further enables high-risk segment discovery without manual segment annotations. Experiments on the DARWIN benchmark demonstrate that the proposed framework achieves superior AD/HC classification performance compared with existing methods. Moreover, the discovered high-risk segments can be projected back to the original handwriting trajectory, providing interpretable evidence associated with AD-related handwriting variations.

Climate data downscaling is the task of increasing the spatial resolution of climate data, typically by generating fine-resolution regional climate data from coarse global model output. Recent machine learning (ML) work in the related task of weather forecasting has seen significant improvements due to newly devised training methods and architectural components, but these have not yet benefited downscaling. We adapt two of these methods to create a family of lightweight probabilistic ML downscaling models built on a modified U-Net backbone and evaluate them on the CORDEX-ML-Bench suite for daily maximum temperature and precipitation across three geographic regions: the Alps, New Zealand and South Africa. We find that a two-stage training curriculum, combining deterministic pretraining with probabilistic tuning, transfers well to downscaling, beating the state-of-the-art for RMSE. Our work provides an advancement towards lightweight, probabilistic downscaling models, reducing the current trade-off between computational intensity and distributional fit.

Flow-matching Vision-Language-Action (VLA) models have emerged as a potential solution for generalist robot control, designed by combining a pretrained Vision-Language Model (VLM) backbone with an action expert that generates continuous robot actions. While these models exhibit impressive capabilities, due to their very high number of parameters, their computational requirements are often prohibitive for robotics control. To mitigate these inefficiencies, existing methods predominantly skip VLM backbone layers with early exits or reduce denoising steps, while leaving action expert depth untouched. We propose a framework that exposes backbone depth $V$, action expert depth $A$, and denoising steps $D$ as three jointly configurable compute axes in a VLA. Starting from a pretrained VLA, we attach lightweight Exit Transformers (ET) at intermediate depths in both the backbone and the action expert, trained to distil the last layer of the policy into each exit. Furthermore, we introduce a KV Cache synthesis mechanism that manages the missing keys and values of the skipped backbone layers, allowing the action expert to exit deeper than the backbone. Finally, we show that the optimal compute budget is task-dependent, with different tasks benefiting from different axes and depths. Notably, our method does not require training the original policy from scratch, and for each exit, it increases the number of parameters by only $2.1\%$ for SmolVLA and $4.1\%$ for $π_{0.5}$. We validate our approach across two flow-matching VLAs (SmolVLA, $π_{0.5}$) and two benchmarks (LIBERO, Meta-World), revealing complementary effects: $V$ and $A$ respectively reduce FLOPs and latency, while $D$ improves both. Our joint configurations $(V,A,D)$ reduce latency by $79.2\%$ and computation (FLOPs) by $31.8\%$, while improving mean success rate by $5.6\%$.

Complex lung cancer decisions can involve several defensible pathways whose eligibility, sequencing and safety depend on unresolved information. Effective support must make explicit how patient conditions govern pathway eligibility, deferral and redirection. MedGPT Clinical Explorer (MCE) organizes alternatives, decision-changing unknowns, safety constraints and fallback into a conditional strategy for clinician review. To evaluate this representation in physician-authored strategies, multidisciplinary experts established case-specific references for 40 cases within a purposive 100-case corpus, and 250 physicians from 98 institutions produced 2,250 strategies under unaided, retrieval-reference and MCE-assisted conditions. MCE-assisted strategies expressed more applicable clinical requirements, measured by the Admissible Pathway Attainment Score (APAS; 0-100), than unaided strategies (adjusted difference, 12.87; 95% CI, 11.18-14.55) and retrieval-reference strategies (5.22; 3.52-6.93). With the same knowledge base available in the retrieval-reference and MCE-assisted conditions, the additional content centered on candidate pathways, decision-critical information and safety constraints. Physicians' whole-strategy acceptability judgments correlated with APAS (Spearman's rho = 0.671), while a complementary relationship audit assessed whether candidates, conditions and subsequent actions were coherently connected. Together, these findings identify two complementary dimensions of open-ended decision support: coverage of clinically relevant content and coherent links among pathways, conditions and subsequent actions. MCE provides a shared decision object that makes consequential omissions and pathway contingencies visible before action; prospective studies should evaluate its effects on clinical workflow and patient outcomes.

Spiking Neural Networks (SNNs) offer an energy-efficient alternative to conventional neural networks by exploiting sparse, binary spikes, and event-driven computation. However, the training of SNNs remains challenging, as spiking activations create a sharp loss landscape that hinders training, and diagonal-curvature optimizers such as the Adam family may fail to capture this geometry. The extension of curvature-based optimization methods to SNNs is further complicated by the sparse, discrete, and temporally recurrent nature of their underlying dynamics. To address these limitations, we propose SpiKFAX, a second-order optimization method that formulates a computationally tractable, Kronecker-factored approximation of the Fisher information matrix specifically adapted to the structure of SNNs. Empirical evaluation across five architectures and seven datasets demonstrates that SpiKFAX consistently yields improvements in test accuracy and training stability relative to other popular optimizers.

The acoustic front-end determines which forensic cues a speech deepfake detector can exploit. The wavelet scattering transform (WST) provides stable multiscale coefficients with explicit coordinates, yet direct flattening obscures the parent relation between paths. We introduce WST-Graph, reconstructing these paths as a sparse modulation-carrier grid for an AASIST graph backend. Modulation-level normalization and length-aware adaptive local attention pooling produce fixed relative-time representations while retaining the acoustic axes before learned adaptation. This yields a waveform-to-graph interface with a fixed, parameter-free WST. Our configurations remain competitive with AASIST while using approximately 60% fewer trainable parameters and show clear gains on selected out-of-domain benchmarks. These results underscore the value of preserving parent-child relations within the carrier-modulation topology when constructing a compact, physically grounded interface for graph-based speech deepfake detection. Code will be released at https://github.com/saki-ciallo/wst-graph.

This paper presents BanglaTurn, a corpus for end-of-turn detection in Bangla conversational speech, and a model trained on it. The corpus holds 35,374 samples of 3 to 15 s of podcast speech, labelled for turn state by combining speaker diarization with an LLM pass, with every label then checked by a human annotator. The model pairs a Whisper encoder with task-specific classification heads. On a class-balanced test set drawn from a held-out podcast, it reaches 84.33% accuracy (95% CI 80.3 to 88.1) against 69.28% for the Smart-Turn v3 baseline, and lowers the false negative rate from 51.57% to 7.55% at the cost of a higher false positive rate. We report what encoder layer fine-tuning, multi-scale pooling and INT8 quantization each contribute, and latency stays within 165 to 191 ms end to end on CPU.

Science, technology, and innovation policies are crucial for competitiveness, yet their diversity and scale make them difficult to map and monitor consistently. Existing approaches rely heavily on manual survey efforts, which are costly and challenging to scale across countries. Large language models (LLMs) enable new possibilities for extracting and structuring information from long and unstructured policy documents. This paper presents an application of LLMs as "AI respondents" for generating structured survey responses from policy texts. We develop a data extraction pipeline based on long-context in-context learning to map information from public web sources into predefined survey categories, including policy instruments, target groups, and thematic areas. The pipeline integrates a validation step using a secondary LLM to assess relevance and evidence, alongside comparisons with human-provided responses. Using a multi-country dataset, we evaluate the alignment between LLM-generated and human-generated outputs through overlap measures and cross-validation. Results show that LLMs achieve high agreement for structured indicators (84-95%), while differences remain in free-text fields, where models tend to provide more detailed procedural descriptions. These findings highlight the potential of hybrid human-AI workflows for policy monitoring, improving both efficiency and scalability while maintaining the need for human validation and contextual interpretation.

Multi-agent large language models (LLMs) have become ubiquitous in applied AI, yet their theoretical foundations remain surprisingly understudied. Viewed through the lens of multi-agent systems theory, several shortcomings come to light: a lack of social intelligence, the absence of coordination mechanisms among agents, unknown emergent behavior, and interactions between agents that are bounded by natural language. We address two of these gaps: the absence of social behavior and the lack of mechanisms for inter-agent coordination. We introduce Epistemic Probabilistic Language Agents (EPLA), a neuro-symbolic architecture for multi-agent coordination under uncertainty. A Symbolic Guard provides structured diagnostic feedback. The LLM generates typed actions, and the Guard controls their execution against an authoritative symbolic state. We formalize the epistemic layer in a gossip testbed through epistemic lottery gossip models, which combine view-based call histories with agent-indexed probability weights. We argue that implementing such a formalism can address shortcomings of agentic LLMs.

The public visibility of Artificial Intelligence (AI) is growing rapidly, driven by the positive impact of its applications across diverse fields of knowledge. In this new chapter, courses that cover the foundations of AI and machine learning become essential for understanding their role and potential in contemporary society. Therefore, understanding fundamental concepts and elementary algorithms through the close integration of theory with practice is essential in AI courses. In this essay, we report our experience designing machine learning exercises for automated assessment tools in programming. It is worth mentioning that we are not developing a novel form of automated grading system. Instead, we propose a perspective that frames machine learning problems as input-output assessment tasks. From this perspective, each exercise admits a unique and deterministic answer and enables automated programming assessment tools (e.g., VPL for Moodle, Codeforces, and MOJ) to effectively support AI education. We believe this essay can encourage instructors to foster educational innovation by adopting more dynamic and interactive approaches to AI courses that integrate theory and practice. Importantly, this essay does not introduce an innovation in the use of AI for education; rather, it introduces an innovative approach to improving the learning of AI, particularly, machine learning.

Sparse AutoEncoders (SAEs) offer a promising way to inspect language model representations, but it is still unclear what kind of linguistic structure their latents expose. We use part-of-speech (PoS) categories as a controlled test case to study whether morpho-syntactic information is encoded by individual latents or by structured groups of features. We find that PoS distinctions are highly recoverable from SAE activations, but do not align with one-to-one latent / category mappings. This recoverability is not reducible to lexical memorisation, and Open and Closed PoS classes differ substantially. Categories are supported by compact groups of sparse latents, with substantial variation across tags. These groups remain stable on held-out data, while also showing overlap between related categories. Our results show that SAEs localise morpho-syntactic information in a distributed and category-dependent form rather than through atomic grammatical features.

Vision-language models such as CLIP achieve strong zero-shot classification, yet under distribution shift, visual embeddings drift from fixed text embeddings. Training-free calibration avoids the per-sample optimization of prompt learning, but prior feature calibration gives each image the full bias of one hard cluster. We propose Domain Recentering with Confidence Calibration (DRC), a training-free method adapting CLIP from a set of unlabeled target images. DRC fits a Gaussian mixture once and subtracts from each embedding a posterior-weighted average of component means. It then removes residual class preference with a log-prior correction, estimating the prior from confidence-weighted predictions. Among compared methods, DRC achieves the highest average accuracy on cross-domain datasets, exceeding zero-shot CLIP by 4.13 and 5.07 points with ViT-B/16 and ResNet-50, with gains over CLIP also holding under ImageNet distribution shifts.

Explicit geometric references offer a direct way to structure self-supervised representations. Existing adversarial distribution-matching formulations, however, require costly encoder-critic optimization. We introduce Flow-Based Distribution Matching (FBDM), a non-adversarial framework that learns this reference-directed geometry through spherical conditional velocity regression. An ETF-inspired reference allows its number of components K' to exceed the auxiliary flow dimension d* while retaining structured geometric separation. We assign both augmented views of each image to the same target, while limiting how many images each reference center can receive. An explicit alignment loss further pulls the two views' representations closer together. Experiments across benchmarks ranging from CIFAR to ImageNet show that FBDM achieves performance nearly on par with DM and remains competitive with existing SSL methods. Matched training-cost comparisons show a 1.48- to 1.83-fold speedup over DM with a negligible increase in GPU memory usage. We also provide a theoretical explanation for the usefulness of the learned representations: under stated conditions, we bound the downstream misclassification rate in terms of the FBDM pretraining loss.

ArGuard is a shared task on harmful content detection in Arabic memes and LLM prompts. It includes two tracks: Track A focuses on multimodal hate detection in Arabic memes, while Track B addresses harmful prompt detection for Arabic LLM safety evaluation. In total, 58 teams registered, 35 participated in the final evaluation, and 27 submitted system-description papers. Participating teams explored models such as AraBERT, Jais, and Qwen3-VL. The best systems achieved macro-F1 scores of 0.823 on A1, 0.419 on A2, 0.984 on B1, and 0.790 on B2. Fine-grained meme classification in A2 was the most challenging setting, partly due to sparse labels and train-test distribution shifts.

Enterprise governance requires decisions, evidence, and accountable authority; it does not require every review task to retain its current human implementation. We develop a task-substitution framework for Digital Governance Frameworks (DGF), treating each gate as an executable contract. Substitution requires sufficient accessible information, valid decision and authority checks, and a reduction in total human work after exceptions, verification, correction, and maintenance are counted. We derive a residual-work threshold and show why automating most cases can still increase labor. Forward deployed engineering connects these conditions to an architecture for agents, rule engines, evidence services, and escalation. DGF-Bench supplies controlled evidence from 300 synthetic projects and 899 evaluable model-project runs. Gemini 3.8 Flash, GPT-5.6 Luna, and DeepSeek v4.1 Flash achieve strict gate success of 94.98%, 83.29%, and 74.18%; complete-route success is 76.92%, 42.33%, and 24.67%. A deterministic control passes all 1,700 gates given the supplied rules and structured facts, locating the comparison in execution of a supplied decision kernel. Evidence audits and 135 repeated runs distinguish correct decisions from reliable execution. A document counterexample establishes an information-sufficiency obstruction. These results support the technical feasibility of replacing human execution of specified governance-review tasks with agents and software. The framework specifies a workforce test based on the complete human effort required at fixed output and quality; the present measurements concern review performance. Sources, dossiers, traces, and analyses are public.

Consumer-facing skincare AI must coordinate visual evidence, product information, tool use, and user-facing actions within explicit evidence and safety boundaries. This study evaluates SkinAgent AI, a non-diagnostic multimodal framework that combines visual concern routing with grounded and auditable LLM-based orchestration. The architecture includes routing for Acne, Pores, and Wrinkles; photograph-based skin-type estimation; count-informed ordinal acne-severity support; typed tools; database-grounded recommendation and action functions; deterministic safety, privacy, and evidence checks; approval before state-changing actions; and structured trace and replay mechanisms. Visual-model performance and system-level agent behavior were evaluated separately. Across three seeds, the skin-condition routing model achieved 99.84% +/- 0.07% accuracy. Skin-type estimation achieved 88.85% accuracy, while count-informed acne-severity support achieved 84.59% accuracy with a quadratic weighted kappa of 0.9076. On a locked but non-independent 240-case system benchmark, intent accuracy was 80.00%, exact tool-set match was 62.92%, and strict task completion was 47.08%. No violations or successful cross-user leakage events were observed in the finite safety and privacy test suites. Tool-selection errors, incomplete grounding of product attributes, and unreliable failure fallback nevertheless remained. These findings support the feasibility of bounded, database-grounded, and traceable agent orchestration for non-diagnostic skincare assistance. They do not establish clinical readiness, external generalization, formal privacy guarantees, or universal safety. Independent validation, expert assessment, robustness and fairness testing, and prospective evaluation in real-world settings remain necessary.

One long-form exam in a large course costs hundreds of grader-hours, and qualified graders are scarce; LLM graders are a tempting alternative. To show its pitfalls we grade a practical Computer Vision exam ($570$ dual-graded students) under $171$ configurations spanning closed and open-weights models; the best reaches mean absolute error $1.64/35$, below the $2.61/35$ two human graders achieve against each other. The catch is the prompt: a short ''strict grader'' preamble drives $14$ of $17$ open-weights models out of the graded band ($\text{MAE} \ge 8$), three stopping grading altogether. The damage traces to the preamble's two credit-withholding sentences, not to tone or model scale; one of them, ''never give partial credit'', alone makes two of three probed models stop grading. The closed flagships of three vendors shift calibration under it but stay in the band. In $162$ further configurations on a second, independent Machine Learning exam from another course ($1{,}038$ dual-graded students), the preamble worsens ten models, moving three out of the band into collapse and one into refusal, yet improves seven whose neutral prompts over-mark: the vulnerability replicates, but its direction is exam-specific. Light LoRA fine-tuning repairs it: one adapter on the two exams' pooled $\sim 3{,}900$ graded examples brings five small open models to parity or better with a human grader in agreement with the grader pair, and sensitivity to the three harsh personas nearly vanishes ($\le 0.32$ MAE). We release the anonymised dataset, full ablation grid, and grading, fine-tuning and analysis pipelines.

Identifying the set of monitored websites in mixed encrypted traffic is challenging because an individual flow often provides only partial evidence of website identity. To address this challenge, we propose FlowAtom, which constructs shared prototypes, called Atoms, from flow representations without website labels. Specifically, FlowAtom pretrains a flow encoder on external unlabeled traffic and aggregates Atom responses across flows within each observation window into a fixed-dimensional, permutation-invariant representation for monitored website-set prediction. Across Direct HTTPS, Trojan, and VMess, FlowAtom achieves micro-F1 scores of 97.82%, 94.43%, and 93.92% in closed-world evaluation, respectively, and consistently outperforms the evaluated baselines in open-world evaluation on windows containing monitored visits. The code is available at https://github.com/aimafan123/FlowAtom.

Existing continual-learning methods protect parameters, replayed examples, or Euclidean feature subspaces. When applied to hyperbolic multimodal models, they do not explicitly preserve the Lorentz geometry that jointly encodes within-modality similarity, cross-modal correspondence, and semantic hierarchy; sequential updates can therefore retain task scores while still distorting previously learned relations. We address this gap with Hyperbolic Multimodal Continual Learning (HMCL). We show that preserving the old multimodal geometry amounts to restricting all modalities to one shared hyperbolic isometry, which induces a family of admissible first-order parameter changes. We formulate a joint closest-admissible (CA) correction that retains the shared rotation best matching the candidate modal updates; its minimal-rotation (MR) special case fixes this rotation to zero. Both variants correct the displacement realized by AdamW, and task anchoring bounds within-task accumulation while preserving learning freedom. Across a unified 16-task classification-retrieval stream with three hyperbolic backbones, HMCL improves final performance and backward transfer over sequential fine-tuning and four continual-learning baselines; HMCL-CA gives the highest Overall score on every backbone. A modality-extended stream confirms the retrieval gains. Representation analyses find 81.2 to 95.5 percent less radial, angular, cross-modal, and paired-distance drift; ImageNet-WordNet results show better semantic ancestry and radial hierarchy.

Understanding how Large Language Models (LLMs) encode linguistic structures remains a fundamental challenge in interpretability research. While diagnostic classifiers (or "probes") are widely used for this task, they face significant methodological criticism: training auxiliary classifiers introduces capacity confounds and calibration issues, often making it difficult to distinguish the model's intrinsic representations from the probe's ability to learn the task. To address these limitations, we introduce a probe-free framework for localizing linguistic selectivity at the individual neuron level. Leveraging the controlled contrasts of linguistic minimal pairs, we propose a Neuron Separability Index (NSI), a metric that directly quantifies how reliably single neurons differentiate grammatical from ungrammatical constructions without parameter updates. Applying NSI across 68 linguistic paradigms and seven checkpoints reveals three main patterns: 1) raw separability reaches near-peak levels earlier for morphological and syntactic distinctions than for syntax-semantics interface and conceptual distinctions. 2) after permutation normalization, single-unit selectivity is sparse, weak, and narrowly tuned: only a small fraction of units are sensitive to an average paradigm, and strongly selective "grandmother neurons" are rare. 3) whole-vector linear separability, single-neuron selectivity, and behavioral competence are largely dissociated, and targeted ablations further separate activation selectivity from causal reliance.

Selective classification enables a model to abstain from predictions on uncertain instances, but existing approaches typically reject them through confidence scores, predefined coverage constraints or instance-level distance measures. These approaches may overlook the collective geometric structure of difficult samples in learned representation spaces. We propose Guided Clustering-based Uncertain Learning (GCUL), a geometric-guided selective classification framework that identifies misclassified and ambiguous instances as a potential confusion attractor in the representation space. GCUL uses a three-phase procedure to initialize, cluster, and explicitly relabel this uncertain region, allowing the rejection boundary to emerge from the underlying representation geometry rather than from a prescribed rejection rate. We further derive a selectivity score and a geometric sufficient condition that characterizes when rejection can provide positive operational utility, enabling pre-deployment feasibility assessment. GCUL improves DistilBERT accuracy from 89.37 percent to 94.98 percent with less than 9 percent rejection. Beyond accuracy, our selectivity score correctly pre-detects the only dataset (GoEmotion) where all baselines fail, and controlled simulations yield 6.1 percent Type-I and 0 percent Type-II errors, validating the sufficient condition's conservatism. These results suggest that collective representation geometry provides a useful alternative perspective for selective prediction.

Estimating electrocardiography (ECG) from a chest-worn inertial measurement unit (IMU) enables continuous heart rate (HR) monitoring without the discomfort of electrodes. We propose TinyCardioUNet, a lightweight UNet that uses all six IMU axes without prior channel selection, refines its bottleneck with a graph neural network that encodes inter-axis dependencies, and employs tensor decomposition with automatic variational Bayesian rank selection for parameter reduction. On a public dataset, TinyCardioUNet achieves an RMSE of $0.098$ and a Pearson correlation coefficient of $0.677$ with only $36.0$k parameters and remains comparatively robust to additive noise, demonstrating accurate ECG reconstruction with a compact model.

Time series analysis is fundamental in domains such as finance, healthcare, and meteorology. Real-world time series often exhibit multiscale characteristics shaped by diverse latent factors, resulting in intricate temporal patterns and rich frequency structures. However, existing approaches typically focus on either frequency-domain decomposition or time-domain pattern extraction in isolation, neglecting their joint structure. This decoupled modeling limits representation expressiveness and undermines performance in tasks requiring simultaneous temporal and spectral reasoning. To address this gap, we propose m-WCN, a novel end-to-end deep learning framework that neuralizes multi-wavelet decomposition for joint extraction of temporal patterns and frequency components. By approximating the classical GHM multi-wavelet transform with trainable convolutional operators and enforcing orthogonality constraints, m-WCN produces interpretable multi-resolution representations. Built on this foundation, we introduce two task-specific architectures: TFBC for time series classification, which boosts discriminative features across frequency scales, and FTB for forecasting, which ensembles frequency-aware predictors. Extensive experiments on 64 UCR datasets and seven public forecasting benchmarks demonstrate the effectiveness of our approach. Built on the neuralized m-WCN, our TFBC and FTB outperform various baseline models across diverse datasets, achieving average improvements of 19.97% in classification and 19.92% in forecasting tasks.

Communities often respond to potentially AI-assisted work by asking three questions: Was AI used? Was that use disclosed? Can hidden use be detected? These questions place AI use itself at the center of accountability while overlooking a deeper problem: unowned judgment. Evaluations, claims, decisions, and creative directions can be shaped by AI with no accountable human or institution prepared to stand behind them. We develop this argument through two illustrative cases: AI-assisted peer review and concealed AI use in creative work. The first shows how contribution dissolution can weaken responsibility while the second shows how the fear of losing credit can discourage honest disclosure. The cases expose the limits of disclosure rules and provenance records as responses to AI-mediated collaboration. We offer three directions for discussion: distinguishing the roles AI plays, identifying judgments that require clear human ownership, and creating conditions in which AI involvement can be disclosed without default penalty. The broader aim is to make AI-shaped contributions discussable, creditable, contestable, and repairable.

This paper addresses the software portability gap between Model-Based Development (MBD) and advanced many-core execution for Cyber-Physical Systems (CPS). We present a workflow-preserving retargeting approach for Simulink-based CPS applications with candidate-wise data parallelism to OpenCL-based many-core processors. Rather than manually rewriting models for new platforms, our toolchain uses MathWorks GPU Coder to extract data-parallel CUDA code, which is then translated into OpenCL host and device code via a custom framework. The conversion handles syntax rewriting, API emulation, and platform-specific argument packing. We deployed this workflow for a computationally intensive Frenet-frame trajectory planner on the Kalray MPPA Coolidge2. The results demonstrate the feasibility of a workflow-preserving retargeting pipeline for the evaluated CPS workload and platform.

In open-ended problem solving, collaborators often rely on discussion to surface concerns, challenge perspectives, and refine shared work as it evolves. While AI agents are increasingly used as discussion partners, existing multi-agent systems place a heavy burden on users to initiate and carefully orchestrate the discussions. We present DocuTeam, a mixed-initiative multi-agent discussion system in which both users and agents can initiate and steer conversations. Agents monitor document changes to proactively start and redirect discussions as the work evolves, while users can flexibly shape the conversation or adopt agent ideas. In a within-subjects study (N=20), participants using DocuTeam produced outcomes rated significantly more novel, relevant, and specific than with a baseline without any increase in cognitive load. Rather than using agents for one-off idea sourcing, participants engaged in an iterative refinement loop in which document changes prompted agent reactions, which led users to revisit and further develop their work.

Brain-age prediction from resting-state fMRI provides a quantitative framework for characterizing age-related changes in spontaneous brain dynamics and for identifying functional signatures. Existing studies have linked fractal and multifractal scaling to age and examined the reliability of individual features. However, prediction repeatability depends on how features fluctuate jointly and how a predictor combines them, which feature-wise reliability assessments do not capture. To address this problem, we propose Repeat-informed Multifractal Curve Regression (RMCR), a structured framework for learning stable age-predictive patterns from multifractal curves. By jointly modeling curve structure and repeat-scan variability, RMCR learns predictive combinations of fluctuation orders that target both accuracy and within-subject consistency. Relative to a matched run-level ridge baseline, RMCR reduces single-run MAE by 6.1% on HCP-A and 7.9% on an external Cam-CAN cohort, and within-visit repeat absolute difference by 18.5% on HCP-A, using a single scan at inference.

We propose Sufficiently Reduced Distributional Regression (SRDR), a generative method that combines conditional distribution estimation with nonlinear sufficient dimension reduction (SDR). It builds on a characterization of sufficiency through strictly proper scoring rules: a dimension reduction is sufficient if and only if predicting the response from the reduced covariates incurs no loss in expected score relative to the full covariates. Sufficient dimension reduction thus becomes a risk minimization problem. SRDR jointly trains a dimension reduction map and a generative prediction model by minimizing the energy score, which can be estimated by sampling without density evaluation or adversarial training. The framework extends to multi-environment data and to classification. We prove that the estimated conditional distributions converge in energy distance to the true ones, which implies that the learned representation is asymptotically sufficient. In simulations and applications to CT slice localization, superconductivity, and digit classification, SRDR recovers low-dimensional sufficient structure and matches or outperforms state-of-the-art nonlinear SDR methods in representation quality and predictive performance.

Visual software often needs a decision over supplied alternatives rather than a generated explanation. We present PixelJev, a native-image decision interface that maps an image, a task instruction, and a runtime candidate set to a structured choice and candidate-conditioned probabilities using small open multimodal models. Its initial realization unifies recognition and multiplechoice visual question answering through an existing language-model readout, with separately evaluated options for frozen inference, language-side adaptation, and held-out calibration. Across seven benchmark evaluations, 64-shot source adaptation raises Pets accuracy from 60.13% to 92.40% across optimization seeds and transfers to natural resampling, new texture labels, and A-OKVQA without target fitting, while frozen inference already supports both VQA tasks. A matched prompt-only follow-up on Pets and ScienceQA attributes the large Pets gain to adaptation and identifies a narrower output validity benefit of candidate readout in adapted VQA. Specialist DINOv2 probes remain stronger on source recognition, frozen 4B is stronger than adapted 2B on DTD and ScienceQA, and accuracy gains do not ensure calibrated target probabilities. These findings establish a working starting point for general-purpose visual decision models and identify the remaining requirements: schema robustness, cross-family transfer, and reliable use of visual evidence.

Neural networks are typically adapted by computing gradients and updating model parameters. We investigate whether task-specific adaptation can instead emerge from a meta-learned self-organising process that requires no gradients at adaptation time. We instantiate this idea with a Neural Cellular Automaton in which locally interacting recurrent cells maintain both a recurrent state and a fast associative memory. During meta-training, backpropagation is used to learn the recurrent dynamics together with how the memory is read and written. Once training is complete, the slow model parameters remain fixed, and online adaptation occurs only through cellwise memory updates driven by local prediction errors and a delta rule. We evaluate whether the learned mechanism can adapt to semantically distinct held-out classification tasks. A single pass over the support data produces substantial improvements in held-out performance without gradient computation or parameter updates during adaptation, and the mechanism remains effective across large changes in the number of examples processed jointly. These results show that task-specific adaptation can be achieved through explicit fast-memory updates while keeping the slow model parameters fixed.

Chain-of-thought (CoT) instructions can distort multiple-choice VLM evaluation when a scorer appends a reasoning cue but reads answer-label logits before the model generates any rationale. We call this CoT-prefix scoring. On ScienceQA, Qwen2.5-VL-7B drops from 80.76% to 45.48%, and across five option-content permutations 93.54% of CoT-prefix predictions select the first slot. Condition-matched linear probes recover 78.94% from the same hidden states, while free generation restores 75.24%, showing that the answer often survives the prefix and the immediate readout fails. Vocabulary and layer diagnostics explain the mismatch: probability mass moves toward continuation tokens, while answer information remains linearly accessible in late layers. The effect recurs with varying severity across datasets and models, though not universally. These results show that CoT-prefix scoring can confound model knowledge with an evaluation-interface mismatch and should be avoided unless the requested and scored output events are aligned.

Lexical borrowings are words from one language that are introduced into another language. Identifying lexical borrowings in text is a relevant task for data-centric fields in Linguistics such as lexicography or corpus linguistics, but none of the standard libraries for text processing offers such a functionality. In this paper we present pylazaro, an open-source Python package for the automatic extraction of unassimilated lexical borrowings (mostly anglicisms) from Spanish text. pylazaro offers a single interface to five sequence labeling models that were trained using different libraries, so that users can run and switch between them without having to deal with the idiosyncrasies of each library. We describe the design and usage of the package, contrast the performance of its models with that of general-purpose LLMs (which perform poorly at this task: F1 below 0.40, compared to 0.86 for the best model in pylazaro) and report on its adoption: pylazaro has been downloaded more than 58,000 times and is the library behind Observatorio Lazaro, a resource that monitors anglicism usage in the Spanish press. pylazaro can be installed via PyPI, is documented in readthedocs and can be tried through a live demo hosted on HuggingFace Spaces.

Time-series explainability remains challenging because discriminative information is often encoded in latent frequency or time-frequency features rather than in the raw signal itself. Existing attribution methods typically operate either in the time domain or in a fixed transform domain, limiting their ability to capture salient information across different representations. We propose XACT, a general framework that learns sparse attribution masks over coefficients from arbitrary invertible time-frequency transforms. We evaluate the framework on the STFT, the continuous wavelet transform, and the discrete wavelet transform. In addition, we extend the virtual inspection layer approach from the STFT to both wavelet transforms, enabling LRP to generate explanations in these representations. On a synthetic dataset, XACT produces precise explanations and is less prone to highlighting spurious features than the tested baselines. Across two real-world datasets, XACT produces sparse and structured explanations, although no method performs best across all quantitative evaluation criteria. These results demonstrate that learning explanations directly in time-frequency representations offers a flexible approach to interpreting deep-learning models for time series data.

Knowledge editing changes what a model knows by modifying parameters so that a requested fact updates while unrelated behavior is preserved. This is usually treated as a write problem, but editing also involves an address problem: deciding which hidden states should receive the new residual. An update that activates too narrowly memorizes one prompt, while one that activates too broadly disrupts neighboring knowledge. Parametric editors encode this scope implicitly, whereas memory-based editors make the selection explicit but keep it outside the edited model. We propose ALOE (Addressed Low-rank Operator for Editing), which learns semantic addresses from paraphrases and hard same-subject negatives, aligns them with autoregressive hidden states through rollout refinement and gate calibration, and embeds the resulting gated low-rank operator within one MLP layer, so that the deployed model runs in a single forward pass with no external retriever or auxiliary router. Evaluated on CounterFact, ZSRE, and KnowEdit across three 7--8B model families, ALOE achieves efficacy between 0.955 and 0.999 and locality between 0.981 and 1.000; mechanistic analyses confirm that the learned geometry separates competing edits and that calibration suppresses out-of-scope activation. The remaining errors concentrate in paraphrase coverage and write fitting.

Temporal knowledge graph forecasting aims to infer future relational facts from the temporal structure of observed events. Existing forecasters mainly summarize history through entity states, relation states, paths, or exact recurrence. These views often miss pair-specific transition evidence, that is, the way prior relations between the query actor and a candidate change the odds of the target relation. We introduce BridgeMem, which estimates this quantity as a residual added to the log scores of a frozen full-vocabulary forecaster. For each candidate, BridgeMem retrieves the pair's events that strictly precede t, encodes their relations, directions, and lags, and converts them into a likelihood-ratio correction. A support-adaptive empirical-Bayes reader trusts exact transition counts where they are abundant and backs off to a learned attention estimator where they are sparse. The backbone's own uncertainty gates the correction, so confident queries and candidates without dyadic history are left unchanged. On five benchmarks, BridgeMem improves on the strongest of nine baselines from 2021--2026 in all 20 filtered MRR and Hits@{1,3,10} comparisons, with MRR gains of 0.0213, 0.0164, 0.0216, 0.0112, and 0.0028 over the best prior result. These results show the value of explicit dyadic transition modeling.

We develop a multi-label Polish content-safety classifier by fine-tuning allegro/herbert-base-cased (124M) across five categories (hate, vulgarity, sexual content, crime, self-harm) using a Focal + R-Drop objective, and evaluate the resulting model against Bielik Guard (Sójka) on the shared out-of-distribution Gadzi Język benchmark. Both systems are given per-category threshold tuning on the same calibration split. Under that matched protocol our model holds a small but statistically significant lead in micro F1, while an apparent macro-F1 lead does not survive: it was an artifact of comparing a tuned model against an untuned one. We also report what that micro figure is worth. Because Gadzi Język is 97% crime-positive, a classifier that flags crime on every input and nothing else already scores 0.910 micro F1 on the same test split, so micro separates neither system from a degenerate strategy and macro is the column that does. Per-category and per-protocol figures are reported in Section 4. The residual out-of-distribution gap is one of calibration rather than discrimination. Ranking quality stays high while positive probabilities collapse, and per-category temperature scaling recovers the loss where Platt scaling and isotonic regression do not. That recovery turns out to be conditional on the calibration set containing safe text. Gadzi Język contains almost none, so thresholds fitted on it flag crime on every safe input, and a balanced refit buys a deployable operating point at the cost of adversarial recall. We report both operating points rather than only the flattering one. Two changes that are standard practice, per-class cost-sensitive weighting and mean pooling, each raise in-distribution macro F1 while lowering the out-of-distribution figure, which indicates that robustness has to be selected for directly rather than inherited from in-distribution accuracy.

Artificial intelligence (AI) models are increasingly deployed through remote services, making model misappropriation a growing concern. Existing approaches, including watermarking, fingerprinting, and model similarity analysis, primarily rely on predefined evidence or direct behavioral comparison and do not explicitly evaluate whether the claimant currently possesses and can utilize model-dependent information relevant to the claimed model identity. In this paper, we propose Third-Party Challenge-Response Identity Verification (TP-CRIV) for AI models. TP-CRIV targets a third-party verification setting in which the verifier has neither white-box nor API access to the claimant's model, can interact with the suspicious deployed service only through its ordinary black-box inference interface, and does not require protocol-specific cooperation from the service provider. Under these constraints, the framework enables the verifier to obtain empirical evidence as to whether the claimant locally possesses a model satisfying a predeclared identity relative to the deployed model. Verification is conducted under fresh, previously undisclosed requirements and network isolation, so that the demonstrated capability cannot rely on online external assistance after challenge disclosure. The resulting evidence is interpreted relative to independently specified and calibrated matching and non-matching operating situations and is statistical rather than cryptographic. We instantiate TP-CRIV for CNN image classifiers using probability-control-based witness generation. Experiments on ten ImageNet-pretrained TorchVision models demonstrate clear same/cross-model separation and finite-challenge verification using independently calibrated thresholds.

Glaucoma is the leading cause of irreversible blindness, and timely identification of fast progressors is essential to prevent disability. Current practice estimates progression by ordinary least-squares regression of mean deviation (MD) on time, requiring 6--10 visual field (VF) tests over several years to obtain a reliable slope. We present GLAM (Glaucoma Longitudinal Analysis Model), a deep learning framework that ingests longitudinal Humphrey 24-2 total deviation sequences with five clinical features and predicts MD and visual field index progression rates using attention-based fusion and aleatoric uncertainty. On the open-access University of Washington Humphrey Visual Field dataset (4,276 patient-eyes), GLAM achieved an MD-rate mean absolute error of 0.139 dB yr$^{-1}$ ($R^2 = 0.927$; 73.5% reduction over a ridge baseline) and an AUC of 0.990 for fast-progressor detection. VF-only deep learning can match multimodal pipelines for progression prognostication using routinely collected perimetry alone.

CAR-bench evaluates whether tool-using agents stay reliable under real-world uncertainty, executing every tool inside the evaluator so that each tool-result exchange is a separate agent round-trip. A conventional next-action agent can batch parallel tool calls, but a chain of dependent calls costs it one model call per round of results. We present a coroutine-bridge harness in which the model's only action is to emit a Python program that blocks and resumes in place across evaluator tool exchanges. This decouples model invocation from tool round-trips: on the public test split the agent uses a median of two model calls against seven agent turns per task, resolving a full multi-turn task in a median of 1.8 s of model latency on Cerebras gpt-oss-120b. Because the action surface is executable code, deterministic CAR-bench policies are encoded directly as logic in the tool layer rather than as prompt rules, enforcing compliance at zero reasoning cost. On the official hidden evaluation the harness won Track 2 with 60.0% Pass^3, 4.5x the organizer baseline, at the lowest estimated cost and the fastest median task latency (3.14 s) of any entry scoring above that baseline; the same unchanged harness reproduced an identical 60.0% Pass^3 on GPT-5.5 in the Open track, matching frontier-model agents. A single static prompt, appended with per-task state at the tail, stays byte-identical across calls and across tasks: the frozen submission prompt served 78% of input tokens from cache (86.6% across its warm tail), against 73% over a three-week development corpus in which prompt edits repeatedly reset the cache. This compounds the few-call design into a small fraction of nominal input compute.

Given a large corpus, the questions one might ask can vary -- from "When was the first human heart transplant?" to "What are all the contradictory claims in this literature?" -- but what makes some questions more challenging than others? In this work, we define a notion of Corpus Task Complexity (CTC) that characterizes tasks by how their difficulty grows with corpus size; for instance, a retrieval query only requires a single linear pass over a corpus, while finding contradictions requires checking a quadratically growing set of claim pairs. Observing that prior work has largely only studied tasks whose difficulty grows linearly with corpus size, which we call low CTC tasks, we introduce 10 new tasks belonging to a class of high CTC whose difficulty grows quadratically or more in corpus size. We find that high-CTC tasks not only grow much more challenging on average at longer contexts for LCLMs, they reverse many modeling conclusions drawn solely from low-CTC evaluations. For instance, efficient block-sparse and hybrid attention approaches consistently match full attention performance on low-CTC tasks, but degrade much more on high-CTC tasks. Large-corpus high-CTC reasoning thus remains an open challenge as full attention is too costly to scale, motivating future research on these tasks. We release our code, data, and 22-task suite (CTC-Bench), to facilitate future research in this area.

Nonlinear contacts and friction strongly influence the vibration response of assembled structures, but their accurate numerical treatment is computationally demanding. The harmonic balance method is widely used to compute periodic steady-state responses, yet the required alternating frequency-time scheme becomes costly for nonsmooth and hysteretic nonlinearities and must be repeated throughout the nonlinear solution process. Here we show that this procedure can be replaced by neural networks that directly map displacement Fourier coefficients to nonlinear force coefficients and provide the corresponding Jacobian through automatic differentiation. The surrounding solver and continuation algorithms remain unchanged for the computation of frequency response curves. The neural networks exclusively learn individual nonlinear elements rather than complete system responses. Physics-based nondimensionalization and phase normalization facilitate the learning process and enable a single trained network to cover a wide range of parameter combinations. Building on the cubic spring, unilateral spring, and Jenkins elements considered here, the approach points toward a reusable library of nonlinear-element surrogates that can be combined in arbitrary number and location within a mechanical system. By bypassing the iterative force evaluation in time domain, the method offers favorable computational scaling for high-resolution analyses and systems with many nonlinear elements.

Text image super-resolution (TSR) aims to recover visually faithful and readable text under unknown degradations. Existing diffusion-based methods typically rely on multi-step prediction of either the high-resolution image or its text prior, resulting in prohibitive computational cost and inference latency. More critically, an erroneous text prior may be repeatedly injected into the denoising process, causing image and text predictions to reinforce each other and progressively amplify an early recognition error into a sharp yet semantically incorrect character. To address these limitations, we propose TOLA, a Text-aware One-step Latent Adaptation framework without iterative image-text diffusion. TOLA consists of two key modules. First, a confidence-weighted text conditioning module constructs the semantic condition only once and suppresses unreliable OCR predictions before they contaminate image reconstruction. Second, a lightweight latent residual correction module explicitly estimates and corrects the structured residual errors to recover missing or distorted stroke details. Extensive experiments demonstrate our state-of-the-art performance across all evaluation metrics on both CTR-TSR-Test ($\times 4$) and RealCE-200 benchmarks. It is worth noting that our TOLA consistently surpasses existing diffusion-based TSR methods by at least 2.72 dB in PSNR on CTR-TSR-Test.

Camera-LiDAR fusion has become a prevailing paradigm for 3D object detection in autonomous driving. However, existing fusion detectors often establish strong inter-modality dependencies by decoding object queries from tightly coupled multimodal representations. Under corrupted driving conditions, such dependencies make the detector vulnerable to unreliable modalities, where degraded observations may interfere with reliable modality-specific evidence and lead to suboptimal predictions. Moreover, modality reliability can vary across both global driving scenes and individual object queries, requiring adaptive fusion decisions at a finer granularity. To bridge this gap, we reformulate robust camera-LiDAR fusion as a scene-aware branch routing problem and propose SARFusion, a robust 3D object detector. Instead of producing detections from a single fused representation, SARFusion decouples object-query decoding into three parallel reasoning branches: a camera branch, a LiDAR branch, and a camera-LiDAR fusion branch. Guided by a Scene Reliability Prior estimated from the global driving context, SARFusion further incorporates object-level evidence to route each query to the most suitable branch. This query-wise routing strategy alleviates harmful cross-modal interference while preserving the benefits of multimodal fusion when complementary cues are trustworthy. On the nuScenes test set, SARFusion achieves strong performance with 72.5 mAP and 74.4 NDS. Extensive analyses demonstrate its robustness under challenging conditions, including sensor corruptions and environmental changes.

We find that language models can transfer capabilities through task-unrelated text. Post-training typically improves language models using task-specific data. Prior work on subliminal learning shows that information about these updates can pass through unrelated generations, but has largely focused on traits or preferences using extensive teacher outputs. We introduce Active Taskless Distillation (ATD), which achieves capability transfer using only a single word from the teacher per prompt. ATD probes the behavioral shadow of post-training by selecting prompts where the teacher and student's shared public ancestor is nearly indifferent between two ordinary words. A student initialized from this ancestor learns solely from the resulting prompt-word pairs, without target-task examples, teacher logits, or teacher parameters. In the primary coding experiment with Qwen2.5-1.5B, 5,664nses yield a 5.34 pp gain on HumanEval+ over an exact nuisance-matched control thadisrupts prompt-resperiments showtransfer in scientific knowledge, commonsense reasoning, and reading comprehensins across additional model generations, sizes, and families. Functional analyses show that the learned sid composable, andthat its strength tracks the teacher's update strength.

End-to-end event extraction remains challenging for large language models as it requires simultaneous identification of event triggers, classification of event types, and extraction of schema-grounded argument spans. We present EAGER, a reinforcement learning framework for generative event extraction that combines fine-grained verifiable rewards with Schema-Contrastive Advantage Estimation to alleviate advantage collapse under sparse binary rewards. Our reward design explicitly targets structural validity, extraction accuracy, groundedness, coverage, over-generation, and span precision. Experiments across seven benchmark datasets show that EAGER consistently outperforms prompting, supervised fine-tuning, and prior reinforcement learning baselines, achieving a substantial improvement over the strongest prior method. Results demonstrate that task-aligned verifiable rewards and contrastive advantage estimation substantially improve structured extraction.

Finite state machine (FSM) and behavior trees (BT) are widely adopted behavioral modeling paradigms for autonomous intelligent systems. While functionally equivalent and inter-convertible in principle, existing transformation methods between FSM and BT face major challenges in preserving behavioral completeness and avoiding model complexity explosion. To overcome these issues, we propose an LLM-driven unified conversion framework that enables automatic, efficient, and semantically consistent transformation between FSM and BT. Specifically, a novel loop execution BT structure is designed for LLM to accurately capture the loop structure in FSM, thereby preserving behavioral completeness. To mitigate the state explosion problem in BT-to-FSM conversion, a depth compression strategy is introduced with LLM prompt to eliminate redundant control nodes, complemented by differentiated hierarchical conversion rules that collectively reduce the number of required sub-FSM. Simulation experiments in multiple autonomous decision-making scenarios demonstrate that the proposed framework enables an accurate and automated bidirectional conversion between FSM and BT. Furthermore, it significantly enhances the scalability and maintainability of generated models compared to traditional approaches, providing a practical solution for behavior model conversion in consumer-grade autonomous intelligent systems such as service robots, game agents, and smart home devices

Diffusion models are powerful priors for linear inverse problems, but the reference guidance methods, Diffusion Posterior Sampling (DPS) and Pseudoinverse-Guided Diffusion Models ($Π$GDM), rely on scalar hyperparameters tuned per task, usually against the ground truth. We introduce FB-GDM, a fully-Bayesian guided diffusion method that removes this calibration step. Starting from the Gaussian approximation of $Π$GDM, we derive a closed-form conditional score that depends on two precision parameters (inverse variances), one associated with the denoising approximation and one with the observation likelihood, and treat them as latent variables inferred by variational inference at each reverse step. A separable factorization makes each update scale linearly with the number of pixels, so the inference stays tractable at full image resolution, at a cost comparable to one $Π$GDM run. FB-GDM requires neither the noise level nor the ground truth: its only inputs are the observation and the forward operator. Experiments on CelebA-HQ inverse problems establish two results. (i) The precision parameters, inferred from the observation alone, allow FB-GDM to outperform $Π$GDM at its nominal setting, even when the latter is given the true noise level, by up to 14 dB depending on the operator, and to match the ground-truth-calibrated $Π$GDM oracle within 0.1 dB. (ii) FB-GDM is robust when the forward operator, the noise level, or the image distribution changes: it stays close to a per-problem $Π$GDM oracle throughout and does not exhibit the hallucinations observed with DPS, whereas DPS substantially degrades at a fixed scale and $Π$GDM stays competitive only if it is re-tuned against the ground truth for each new problem. When the prior is applied to images outside its training set, this re-balancing between data and prior keeps FB-GDM faithful where a fixed face-prior guidance can otherwise hallucinate.

Software requirements are typically incorporated into prompts used in LLM-assisted software development. Recent work has shown that requirement smells can affect automated traceability between requirements and code, but empirical evidence on their effects in code generation remains limited. To address this gap, we build upon a prior study on automated traceability by reusing its dataset and requirement smell taxonomy, while extending it to evaluate the functional correctness of LLM-generated code. Using a benchmark consisting of requirements and corresponding system tests for four applications, we progressively introduced semantic, syntactic, and lexical smells into otherwise clear requirements and analyzed their influence on generated implementations. Our results suggest that increasing \textit{smell density} was generally associated with lower test-suite-based functional correctness, although non-smelly requirements could still produce faulty code. We also found that different smell categories had similar effects. These findings provide additional empirical evidence of the importance of requirement quality in LLM-assisted code generation, while showing that high-quality requirements alone do not guarantee correctness, as these depends on several factors, including the LLM. Compared with previous work, our results suggest that the impact of requirement smells depends on the software engineering task: whereas their effects on traceability were modest, code generation appears more sensitive. Overall, this work motivates further investigation into task-dependent quality effects in LLM-assisted software engineering.

Mobile robots require robust, real-time fault detection capable of continuous adaptation on constrained edge hardware. While deep time-series models excel at unsupervised anomaly detection, their computational cost prohibits high-frequency onboard execution. This paper bridges this gap via a Teacher-Student distillation framework. An offline foundation model (TSPulse) generates pseudo-labels from unlabeled time series augmented with fault injections. A lightweight MiniRocket Student, adapted with a Recursive Least Squares estimator, approximates this complex decision boundary to execute real-time inference onboard. Evaluations on the TSB-AD benchmark and a physical mobile robot demonstrate the Student achieves a 4.30 ms CPU inference latency. During real-world domain shifts, online adaptation enables the Student to recover from unseen mechanical degradation, improving VUS-PR scores from 0.26 to 0.75 without catastrophic forgetting. Crucially, an uncertainty-guided active learning strategy minimizes operator cognitive load, requesting sparse interventions only when encountering novel fault distributions. These results validate the deployment of state-of-the-art anomaly detection on resource-constrained robotics through offline-to-online distillation.

Sensitive information is defined by domain and intent, not a universal category, yet redaction systems such as privacy filters and named-entity recognizers fix a taxonomy at training time, requiring retraining for each new domain. We introduce ASIRF (Agentic Sensitive Information Redaction Framework), which retrieves domain-specific definitions based on the input's domain from a flexible knowledge base at inference time, needing no retraining to adapt. Two architectures, a three-call multi-agent pipeline and a single-agent variant, are evaluated across ten small open-weight models and eight datasets, including out-of-distribution fictional domains, against the OpenAI Privacy Filter (OPF) as a trained-classifier baseline. With only a few dozen expert-authored definitions per domain and no training data, ASIRF's recall exceeds OPF's in 68 of 80 model-domain combinations (85 percent), by at least one of the two architectures, with shortfalls confined mostly to OPF's training-distribution domains.

Scalable oversight aims to verify the behaviour of agents whose capabilities exceed those of their overseers. AI debate has been proposed as an oversight solution in which competing agents help a resource-limited verifier assess claims that it cannot reliably evaluate unaided. Much of its promise rests on incentivizing honest arguments that lead to correct verdicts. Yet a correct verdict need not uniquely determine the arguments used to support it. Agents may retain discretion over which correct claims to present, how to frame them, and in what order to disclose them. This residual freedom can allow agents to shape what the verifier learns beyond the task-relevant conclusion, pursuing latent objectives without compromising verdict correctness. To study this phenomenon, we introduce the framework strategic interactive oversight (SIO), which treats oversight jointly as a verification mechanism and a strategic communication channel. Within this framework, we formalise the notion of task-admissible latent optimisation, which entails the pursuit of latent objectives while maintaining a prescribed task performance. As proof-of-concept, we instantiate SIO in the establish protocol debate with cross-examination and quantify a tradeoff between task success and information disclosure about a hidden variable. The trade-off identifies a strategic window in which substantial disclosure remains compatible with task admissibility. Towards mitigation, we reduce admissible bias by expanding the cross-examiner's role to mitigate persistent disclosure over finite interaction horizons. Our results highlight the need to evaluate oversight not only by the correctness of its verdicts, but also by the information conveyed through its transcripts.

One of the most important problems in medicine is to facilitate prediction. In this study, we propose entropy triangle method, a novel framework for predicting heart rhythms using a novel machine learning technique. This framework includes three steps: feature engineering, entropy triangle oversampling, and disease prediction. The dataset used in this study is a 12-lead electrocardiogram (ECG) arrhythmia research database with 10,646 patients. This dataset contains 11 different heart rhythms (5 sinus rhythms and 6 non-sinus rhythms). In this article, we introduce two firsts in machine learning and medicine that can predict non-sinus rhythm with over 85% accuracy. Our experimental results show, among others, that the most accurate classifier based on entropy triangles and the most useful oversampling are the supported vector classifiers and oversampling techniques for shark scent.

Teachers who prepare lessons on local history and cultural heritage work from material that is hard to use. The primary sources are scanned books without a text layer, and the supporting records are administrative catalogs released as spreadsheets. A general chatbot answers such questions fluently but without a verifiable source, which is the property a teacher needs most. This paper presents HistoRAG, a question answering assistant that answers from one regional collection and cites a volume and a page for every fact. HistoRAG transcribes each page with a vision language model and keeps a line level confidence from the token probabilities. It builds three stores from the same collection: a hybrid text index, a relational catalog database, and a knowledge graph extracted only from entity dense passages. A lightweight router sends each question to the stores it needs, so that counting questions reach the database and relational questions reach the graph. We build a benchmark of 516 questions over a collection of 36 scanned volumes and the heritage catalogs of the same region, covering statistical, factual, temporal, and multi-hop questions. HistoRAG answers more questions correctly than passage retrieval baselines and than a graph based retrieval system, at a far smaller cost per question. The assistant runs behind a chat interface, so a teacher can check any statement against the page it came from.

Some documents that embedding-based topic models initially classify as noise later become founding members of emerging topics. At publication time, however, they appear as scattered points in embedding space and are difficult to distinguish from ordinary noise without the benefit of hindsight. We study whether such anticipatory outliers can be predicted prospectively, using only information available when a document first appears. We derive labels from the subsequent trajectories of outlier documents, distinguishing those that anticipate new topics from those that reinforce existing topics or remain isolated, and estimate label confidence through agreement across multiple embedding models. On two French news corpora, anticipatory outliers prove predictable at publication time. Under cross-validation, $F_1$ rises from about 0.77 over the full eligible population to above 0.90 on high-consensus subsets, and remains at 0.76-0.80 under a strictly chronological evaluation. Predictive performance is driven mainly by geometric features capturing each outlier's position in embedding space.

There are many complex issues in the world of artificial intelligence. Some of these problems are solved using other artificial intelligence methods, which are called artificial intelligence for artificial intelligence. Finding an appropriate classifier algorithm is a time-consuming task. For this reason, an algorithm that can automatically learn the choice of classification algorithms is very important. Classification algorithms are useful in predicting various diseases. Also, Primary Biliary Cirrhosis is one of the most well-known diseases that have been predicted by classification algorithms. This research's most significant achievement and novelty is the automatic increase in learning through a scoring method of reinforcement learning is called square learning (SL). In this research, an algorithm is presented that learns to automatically select the appropriate classification algorithm to predict Primary Biliary Cirrhosis. In this article, with inspiration from four evaluation metrics in classification algorithms, a new reinforcement learning method by the name of Fourth Degree Learning has been presented. In this research, we increased the performance of the classification algorithms used in this method from 63% of accuracy and achieved 98% accuracy.

We propose a compact underwater acoustic classification framework combining multi-representation feature engineering, temporal statistical pooling, and compact convolutional architectures designed for acoustic time-frequency and cochlear representations. We investigate multiple conventional and auditory-inspired representations and first evaluate lightweight classifiers and Conventional Neural Networks (CNNs) on ShipsEar dataset. On the provided split, a two-layer CNN achieves a macro F1 of 0.9918, while a Radial Basis Function Support Vector Machine (RBF-SVM) reaches 0.9883. However, source-recording provenance cannot be reconstructed, preventing verification of recording-independent generalisation. We therefore evaluate on DeepShip dataset using recording-level partitioning before segmentation. Under this protocol, a 157K-parameter compact CNN achieves a test macro F1 of 0.7226, while an 11.17M-parameter ResNet18 provides no improvement in validation performance under the matched setting. These results demonstrate the importance of representation-aware feature and model design, together with rigorous recording-level evaluation, for classification performance and deployability in compact underwater acoustic systems.

Background: Code degradation in large, long-lived codebases is costly to remediate through manual refactoring and opportunistic clean-ups. LLM-based coding assistants can perform mechanical remediation at scale, but their impact on industrial workflows is underexplored. Objective: We investigate how massive AI-assisted code remediation affects build-on-commit continuous integration (CI), code review, and team coordination in a large industrial repository, and which socio-technical bottlenecks constrain such remediation when source editing becomes cheap through AI assistance. Method: We report on a 15-day exploratory single-case field study in which an experienced developer used a command-line AI coding buddy to remediate widespread issues in a closed-source industrial C++ repository. We triangulate Gerrit metadata with a developer diary and team chat, analyzed through descriptive statistics and qualitative coding. Results: AI-assisted remediation rapidly generated hundreds of commits touching thousands of lines, saturating CI and reviewer attention. Naïve per-file commits overloaded build-on-commit CI; Switching to directory-based batching and capping the number of files per change restored throughput, but still required explicit review solicitation, negotiation of acceptable commit granularity, and iterative follow-up to resolve build and static-analysis failures. Conclusion: When mechanical editing is cheap, CI capacity, review effort, and change orchestration become primary bottlenecks. Sustainable AI-assisted remediation in very large repositories requires deliberate control of commit, review, and CI batch granularity and treating semantic change sets, such as ``fix all instances of warning X'', as first-class units of work that can be sliced differently for developers, reviewers, and CI.

We introduce Spot, Separate, and Enhance (SSE), the first multimodal, user-guided generative model for audio remixing and enhancement. SSE enhances video content by rebalancing the audio, removing unwanted audio sources, and reducing reverberation, guided by both video and textual descriptions. To support its training and evaluation, we propose DegradedMix, a new dataset built on the audio remixing benchmark MuddyMix. We also adopt evaluation metrics from generative modeling, which better capture the creative nature of remixing than standard reconstruction-based metrics. SSE outperforms existing baselines in both controllability and remixing quality, as shown by extensive experiments. Project page: https://sse-ai.notion.site

Banking assistants must use account-specific information to answer requests and, in many cases, take actions through tools. Evaluating only the final response misses important errors. An assistant may ask for information it already has, rely on stale context, select the wrong account, or write an invalid value after stating the correct one. We introduce IndicBankBench, a 799-case benchmark for Indian retail banking spanning five operational domains, a capability/refusal domain, and twenty primary axes. Cases are evaluated at four stages: safety, action and tool use, response adequacy, and advisory quality. Tool use and most safety checks are deterministic. A narrow resolver handles only ambiguous confirmation-before-write cases, while a separate LLM judge evaluates semantic response adequacy. We run every case three times and report strict pass^3, which requires success on all trials. Across the eleven evaluated models, strict reliability ranges from 43.7% to 58.2%, whereas at-least-once success ranges from 60% to 74%. This gap shows that at-least-once success can overstate dependable banking behavior. The case-level diagnostics also distinguish systems that ask unnecessary questions from those that act but fail to reconcile customer context or fully resolve the request. We release the cases, mock environment, and evaluation harness.

Physical AI aims to build embodied agents that perceive the world, understand and reason about it, and decide how to act. Yet the field has focused primarily on the last component: the action model that maps observations to low-level controls. The prevailing training recipe can erode the perceptual and reasoning capabilities needed for robust behavior, leaving even strong action models vulnerable to scene perturbations and long-horizon tasks. We introduce HarnessPAI, a model- and embodiment-agnostic Harness framework for Physical AI that treats code as the executable and evolvable interface that organizes the underlying action primitive. The framework separates two timescales: within a rollout, it executes open-loop at the program level, with a fixed program guiding and checking execution; across rollouts, it evolves closed-loop, using execution feedback to revise the program and distill failures into reusable skills. Across desktop robot arms, household robots, a robot vacuum, and a legged walking agent, HarnessPAI improves on both pure action models and code-as-policy baselines without retraining the underlying model: a 61.6-point gain over $π_{0.5}$ on LIBERO-PRO and a 27.2-point gain over WorldDreamer on RoboCasa atomic tasks. Once a program is selected, rollout execution requires no online high-level LLM deliberation. Beyond execution, the converged program is also a cheap and reliable expert-data collector, and fine-tuning $π_{0.5}$ on collected expert data lifts success rate on LIBERO-PRO by 38.8 points. Our results suggest that the frontier of Physical AI depends not only on stronger action models, but also on executable harnesses that integrate perception, task understanding and reasoning, and action execution into a unified, verifiable, and feedback-driven system. Website: https://darwin-agent.github.io/HarnessPAI

This paper presents an Edge AI-based system for detecting sleep and wake states in non-stationary mobile environments using resource-constrained embedded hardware. Conventional approaches relying on accelerometer-based activity metrics are highly susceptible to motion and vibration artifacts and are limited by strict compute and energy budgets of wearable and IoT devices. To address these challenges, a multimodal pipeline is designed and implemented on an ESP32-S3 microcontroller. The system combines inertial sensing for head movement analysis and visual pose classification. A dual-core architecture with FreeRTOS enables parallel execution of real-time data acquisition and on-device inference. Sleep detection follows a two-stage strategy: low-movement detection over a temporal window, followed by visual validation of poses. Experimental results show accuracies of 96.5% for motion-based detection and 89% for pose classification, yielding robust binary sleep-wake classification. Field tests confirmed feasibility in representative mobile scenarios. The results demonstrate that privacy-preserving, local sleep detection is achievable on edge hardware through careful co-design, while highlighting limitations in sensing intrusiveness, dataset scale, and system integration.

Dynamic mode decomposition (DMD) is a data-driven method that computes the best linear approximation of the underlying dynamical system and decomposes the dynamics into a superposition of characteristic spatiotemporal patterns. Originally introduced by the fluid dynamics community, DMD and its extensions have found widespread use in many other research areas such as molecular dynamics, climate science, engineering, finance, and neuroscience. Applications include dimensionality reduction, forecasting, system identification, control, and spectral clustering. In order to apply DMD to partial differential equations, the spatial domain is typically first discretized using finite difference or finite element techniques, thus implicitly rendering the problem finite-dimensional. We extend projected and exact DMD to infinite-dimensional systems. Rather than estimating matrices from vector-valued observations, our DMD variants learn finite-rank operators from functional data such as observables, densities, or wavefunctions. We show that conventional DMD algorithms can be regarded as special cases of their functional DMD counterparts. All results will be illustrated with the aid of guiding examples. We focus in particular on Koopman, Perron-Frobenius, and Koopman-von Neumann operators associated with graphons, ordinary differential equations, and stochastic differential equations.

Long-tailed chest X-ray classification requires visual representations that capture both common abnormalities and subtle, infrequent findings. We propose Med-AR-8B and Med-AR-2B, two radiology-native autoregressive vision-language models pretrained with structured reports, abnormality-focused text, and region annotations. We evaluate the transfer of their visual encoders to multi-label classification against contrastive, self-supervised, and supervised pretrained encoders, including Med-CLIP, CheXFound, EVA-Base, ARK, and BioViL-T, using a common ML-Decoder classification head. To assess fine-grained recognition, we also construct LLM-expanded, report-derived label sets for MIMIC-CXR and CheXpert. Across PadChest, MIMIC-CXR, and CheXpert, Med-AR-8B outperforms Med-CLIP in mean AUROC and AUPRC for head, medium, and tail findings. On MIMIC-CXR, it increases tail-label mean AUPRC from 0.1033 to 0.1441. Med-AR-2B achieves the strongest discrimination results on PadChest. Across the broader encoder comparison, a Med-AR variant achieves the highest mean AUROC and AUPRC in every reported prevalence group on each public dataset. Both Med-AR variants also achieve lower excess area under the risk-coverage curve than Med-CLIP on all three public datasets, indicating improved selective-prediction performance under the evaluated protocol. Internal results are metric-dependent, with Med-CLIP retaining advantages in overall and tail AUPRC and in selective prediction. These findings establish Med-AR as a strong pretraining recipe for long-tailed chest X-ray classification on the evaluated public benchmarks and demonstrate the value of assessing discrimination and selective prediction together.

Large language model agents increasingly rely on natural-language skills to solve complex tool-use tasks. However, such tasks often admit multiple valid solution paths, making it inappropriate to improve skills by forcing failed trajectories to match a fixed successful trajectory. Moreover, failed trajectories are rarely entirely wrong: an agent may first collect useful evidence and make meaningful progress, but later deviate into an erroneous suffix. We therefore argue that skill self-evolution should identify where productive problem solving begins to break down, rather than reflect coarsely over the entire failure. Based on this insight, we propose SkillPivot, a deviation-point-guided framework for skill self-evolution. SkillPivot detects the transition from a useful prefix to an erroneous suffix using execution validity, goal progress, and action diversity. A stronger teacher then continues from the same prefix and produces a successful alternative under the same interaction history. By contrasting the student's failed suffix with the teacher's successful suffix, SkillPivot generates localized skill updates while preserving already effective guidance. Experiments on ToolQA, LogicBench, and WildClawBench show that SkillPivot consistently outperforms competing skill-evolution methods, improves multiple agent models, and produces compact, transferable skill updates.

This paper investigates the joint optimization of the transmit precoder and the transmission/reflection coefficients of a simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) to maximize the weighted sum rate (WSR) in a multi-user downlink. We propose a particle-swarm-assisted gradient meta-learning (PSA-GML) algorithm for this non-convex problem. The original problem is first equivalently transformed via an amplitude-split parameterization and a collapsed precoder representation, which automatically satisfy the energy-conservation constraint and reduce the search dimension. Particle swarm optimization (PSO) then performs a global search over the STAR-RIS coefficients to yield a high-quality, initialization-robust warm start, with the transmit precoder obtained in closed form. Departing from conventional alternating optimization (AO), a coordinate-wise long short-term memory (LSTM) meta-optimizer trained by first-order gradient meta-learning further refines the coefficients and precoder jointly, learning per-coordinate adaptive update rules from data. The meta-optimizer is trained offline and applied to unseen channels without further adaptation. Numerical results show that PSA-GML attains an 11.06 bits/s/Hz WSR at 10 dB with N=32 elements and K=4 users, exceeding AO by 13.1% (and by 6.2% even with multiple random restarts) and the random-phase scheme by 35.1%. In the interference-limited regime it reaches 83.9% of the hand-designed Adam refinement without manual hyper-parameter tuning, and it transfers zero-shot across regimes, indicating that the learned update rule captures the intrinsic WSR landscape structure.

Bangla, the seventh most spoken language in the world, remains under-resourced for neural text-to-speech. Public Bangla speech corpora are dominated by short read-prompt utterances collected for speech recognition, leaving long-form prosody and consistent single-speaker narration uncovered. We present BanglaKontho, a single-speaker Bangla TTS corpus of 20 hours derived from professional audiobook recordings: 7,050 segmented utterances with verified transcripts at 24 kHz. We also release a reusable Bangla text normalizer covering Bangladeshi-style digit grouping, currency and date expressions, Danda punctuation and Unicode normalization, together with the full preprocessing pipeline. An MB-iSTFT-VITS baseline trained from scratch reaches 9.5% WER and 4.46 naturalness MOS, against 16.0% and 3.16 for the same architecture retrained on the 12-hour IndicTTS-Bn corpus. The corpus is released openly under CC BY-NC 4.0.

A generative search answer can cite a supported passage yet omit a source relationship that changes its interpretation. We specify a claim-gated audit of the query-source-answer tuple. An omission is resolved only when relationship evidence, answer adoption, materiality, and disclosure are all observed; incomplete evidence remains unresolved rather than being treated as independence. The specification separates this endpoint from citation support and review priority, and binds decisions to versioned evidence spans. A reference checker makes the record contract executable. On an exhaustive synthetic suite, it reproduces all 81 three-state predicate combinations and rejects 192 deliberately malformed records. Common-guard baselines and predicate ablations isolate endpoint logic from missing-evidence handling, while controlled transitions check support separation and evidence removal. These are finite contract-conformance results, not detector accuracy or evidence of improved user outcomes. We define the independent annotation, held-out evaluation, and paired utility tests still required to establish semantic validity and deployment benefit.

Persistent memory lets language-model agents improve prompts and skills without updating model weights. We show that matching retrieval scope to certification scope enables these edits to support reliable repeated adaptation across recurring task families. We study frozen-model agents on ProcStream-RSI, a 12-round code-repair stream, using Orthogonal Regression Control (ORC), an execution-grounded gate for persistent skill edits. In an intervention that holds proposals and gate decisions fixed, retrieving each accepted skill only for its originating family raises mean hidden trajectory utility from 0.713 under global memory to 0.816 and changes harmful deployments from six of eight to none. In 27 paired randomized-order streams, Scoped-ORC improves mean trajectory utility by 0.063 [0.037, 0.094] over Global-ORC, accepts 63 rather than 12 updates, and produces multiple accepted updates in 19/27 streams, with 0/63 harmful acceptances. The global control reaches 0.713, below the static agent's 0.775, because locally valid edits can interfere with unrelated families. These results establish scope matching as a complementary control for persistent agent memory: certification determines whether an edit is supported, while retrieval scope determines where that evidence authorizes its use.

AI-moderated interviews are emerging as a scalable market-research method for generating consumer insights and building consumer "digital twins." Yet it remains unclear whether they match human-moderated interviews or improve on simpler, static data collection methods. In a pre-registered, between-subjects study (N = 317) with three industry partners, we compare AI-moderated (N = 139), human-moderated (N = 24), and static interviews (N = 154). AI moderation matches human moderation in depth, covers more themes, and, holding budget constant, recovers significantly more customer needs than human moderation or static interviews. However, participants sound more emotionally engaged when speaking to a live human. We then create digital twins using interview data and evaluate each twin against the participant's own held-out responses to six real-world marketing stimuli. We find that digital twins created from AI-moderated interviews predict consumer responses better than demographics-only personas. However, the additional richness from AI moderation does not translate into better quantitative predictions compared to static interviews. By analyzing open-ended thoughts generated from humans versus their twins, we find that prediction errors are connected both to differences in (self-reported) thinking styles between twins and humans, and to gaps between training and validation data (i.e., asking questions that are too far out of distribution).

Direct On-Policy Distillation (Direct-OPD) transfers reinforcement-learning-induced policy improvements from a small model to a larger student by using the token-level log-ratio between post-RL and pre-RL checkpoints as dense supervision on the student's own rollouts. This transfer rewards the policy shift at every state, yet the log-ratio measures only relative change: it can stay fixed even as the probability mass that both checkpoints assign to the student's candidate tokens vanishes. Through an exact construction, we show that the Direct-OPD reward and its update can remain unchanged while the Jensen-Shannon divergence (JSD) and both KL directions between the checkpoints vanish with this mass, and we note that a small JSD bounds how much the teacher's behavior changed. Motivated by this analysis, we propose Selective Supervision for Direct-OPD (S$^2$D-OPD), which ranks student-sampled states by their teacher-reference JSD and masks Direct-OPD supervision at low-divergence states, retaining only the top 10% of states per response. Across two teacher pairs and four student models ranging from 1.7B to 8B parameters, S$^2$D-OPD improves held-out accuracy over dense Direct-OPD on AIME and HMMT benchmarks in seven of eight settings and matches it in the eighth, without extra forward passes. Our code is available at https://anonymous.4open.science/r/S2D-OPD-8868.

Repeated evaluation can estimate a benchmark score accurately while still requiring replication to certify narrow uncertainty. We characterize that requirement on a fixed grid of $M$ tasks with $L$ binary paths per task under the hard budget $(M+t)K$, where each path costs at most $K$ responses or episodes. For fixed $L \ge 3$ and $0 < α\le 1/12$, the optimal expected width on the worst pure cohort is $Θ_{α,L}([M(t+1)]^{-1/2})$ when every task is observed and $Θ_{α,L}([M(t+\sqrt{M})]^{-1/2})$ when omission is allowed. The lower bounds cover adaptive hard-budget policies, and fixed random-subset designs attain both rates through disagreement certificates. A joint mean/disagreement interval turns the task-covering law into practical finite-budget inference. In an equal-budget LiveCodeBench replay with 16 models, 880 tasks, and five outputs per task, the task-covering design reduces median point-estimation MSE by 87.0\% relative to pooled uniform sampling, while the Joint certificate produces narrower confidence intervals in 15/16 panels and reduces median interval width by 30.6\%. Finite-regime analyses identify task coverage as the effective choice at the evaluated scale and characterize how cohort size and within-task agreement determine the useful operating region. Together, the sharp laws and fixed-budget evidence make replication and task coverage explicit design variables for information-efficient repeated evaluation.

Internet texts are replete with format tags that carry structural, semantic, and functional meaning. Current large language model (LLM)-based translation systems struggle to balance translation fluency with tag fidelity when processing tagged text. We argue that resolving this tension requires a systematic approach at three interconnected levels: data synthesis, capability building, and multi-objective alignment. At the data level, we identify and formalize a fundamental trade-off between structural tag diversity and translation naturalness in synthetic data generation; existing methods optimize for one at the expense of the other. We propose a hybrid synthesis strategy (Hy-LST) combining LLM-based synthesis tag method and Two-Stage LLM-based synthesis tag method to produce both diverse and natural tagged data. At the capability level, we decompose tag-aware translation into four sub-tasks of increasing difficulty in a multi-task supervised fine-tuning framework, enabling targeted capability acquisition and knowledge transfer. At the alignment level, we design three complementary reward functions under a group relative policy optimization framework, each targeting a distinct objective (fluency, tag fidelity, and tag-scoped translation quality), and show that joint optimization consistently outperforms single-reward alternatives. Experiments on six language directions (en2zh, en2ja, en2de, en2fr, en2ru, de2fr) demonstrate that each level contributes measurable improvements, and the complete system significantly outperforms existing methods. Qualitative analysis reveals specific error patterns and their mitigation after training with our method.

Programming tutorial videos on YouTube are an important information resource for software developers and students, and their comment sections have evolved into active spaces where viewers ask follow-up questions. The volume of these questions, however, often exceeds what content creators can address, leaving learners without the clarifications they need. We present VidTutorAssistant, a web platform that automates responses to viewer questions on programming video tutorials. VidTutorAssistant implements a retrieval-augmented generation pipeline that extracts a video's transcript, then segments it and embeds it. It then classifies each viewer comment as being a question or non-question, retrieves the most relevant transcript segments to each identified question via cosine similarity, and then generates an answer to the question using an LLM (GPT-4), while grounding the response using the retrieved transcript segments as context. We validate VidTutorAssistant through a study on a subset of 440 user comments selected from a larger dataset of 105,553 comments extracted from 7,522 Python and Java tutorials. VidTutorAssistant is evaluated on various criteria: a) its ability to identify the programming language in a video, achieving a 0.99 accuracy; b) its ability to classify comments into questions and non-questions, reaching a 0.96 accuracy; and c) its ability to produce correct and complete answers to questions, producing 98% correct and 99.5% complete responses, compared with 89% and 90% for the original creators' answers.

In cross-lingual zero-shot text-to-speech, the accent of the reference leaks into the target speech. We propose accent analogy guidance (AAG), a training-free sampler term that subtracts an accent direction estimated from the model's own predictions for one synthetic voice rendered in both languages, so the voice cancels and only the accent remains. By a blind LLM accent judge on real dubbing data, reweighting classifier-free guidance between reference and text, and its variants, stay near one identity-accent trade-off curve; we score a method by its speaker similarity above that curve at equal accent ($Δ$SIM). Across four open TTS models AAG lies above the curve: on OmniVoice $Δ$SIM is +0.11 to +0.27 on three test sets (accent 3.51 to 4.28 on a 1-5 scale at speaker similarity 0.29, where reweighting keeps 0.02); MaskGCT and CosyVoice 2 also lie above their curves, and on F5-TTS it is more native than any reweighting setting. An LLM-free language-ID measure and a twelve-listener panel agree. A premise test and the reach of a model's own curve indicate in advance whether and roughly how much AAG can gain, predicting the one model where it gains nothing (X-Voice).

Audio-Visual Semantic Segmentation (AVSS) aims to identify, segment, and classify sound-emitting objects in video frames. Previous Transformer-based AVSS approaches largely inherit design principles from image segmentation models. Recent studies show that these image segmentation models contain redundant components that contribute little to the segmentation performance. Following this insight, we propose Encoder-only Audio-Visual Segmentation (EASE). EASE runs at up to 365 FPS, 3x faster than prior State-of-the-Art (SotA) AVS models at comparable accuracy, and trains in under 11 GPU-hours. Furthermore, we achieve SotA AVSS performance across different backbones and input resolutions. Our results demonstrate that AVSS can be both simpler and faster, providing a scalable foundation for future research and real-time applications. Code, model weights, and samples are available at https://ease-avs.notion.site

Significant research effort has been directed in recent years towards establishing both asymptotic and non-asymptotic convergence guarantees for two-timescale actor--critic algorithms, where the actor recursion is run on a slower timescale than the critic recursion. This work derives a uniform all-time concentration bound for the actor--critic algorithm with function approximation in the long-run average-reward setting. This bound helps us analyze the behavior of the actor parameter with high probability. We show that, after some finite time, the actor parameter enters a safe region and remains within it thereafter with high probability. Specifically, with probability at least $1-ε_1-ε_2$, the actor error $\Vert θ_k-θ^{*}\Vert$ is $O\left(\frac{n_0^{3/4}}{k}\frac{1}{\sqrt{ε_2}}+\left(\frac{1}{n_0}\right)^{1/4}\log^{1/4}\left(\frac{1}{ε_1}\right)+\left(\frac{1}{n_0}\right)^{1/4}\right)$ for all $k\geq n_0$ and sufficiently large $n_0$. We also present experimental results demonstrating that the aforementioned actor error diminishes with the number of actor-parameter updates.

Reasoning-capable language models often produce long chains of thought when direct answers suffice, wasting inference compute. Many dual-mode models leave this choice to users. Automating it is challenging because routing targets evolve with the policy, initial mode preferences destabilize exploration, and sequence-level objectives entangle routing with response learning. We introduce CounterRoute, an online reinforcement-learning framework that jointly learns routing and modeconditioned responses in one shared policy directly from a native dual-mode checkpoint, without method-specific SFT warm-up. Paired current-policy counterfactual rollouts assign cross-mode credit only to the routing token, while within-mode GRPO trains response tokens. A paired-to-self-routed curriculum stabilizes early training with forced rollouts from both modes, then increases self-routed updates to improve autonomous routing. Across nine benchmarks, CounterRoute better balances accuracy and efficiency than heuristic and learned adaptive-routing methods. Relative to always-thinking checkpoints, it improves macro-average accuracy while reducing mean generated tokens by 51% for Qwen3-8B and 41% for Qwen3-14B. On instruction-following and commonsense benchmarks where direct answering is strong, think rates fall as low as 1% while response quality improves. Despite training only on math and instruction following, its routing behavior and response quality generalize to held-out coding, science, knowledge, and commonsense benchmarks.

European electricity trading in the EU operates as a constrained multi-layer system in which legal design, exchange microstructure, and network physics are executed jointly across forward, day-ahead, intraday, and balancing horizons. This paper develops a functional architecture for AI-supported trading that is aligned with market-coupling mechanics, cross-zonal transfer constraints, and compliance obligations under REMIT, MiFID II, MiFIR, and EMIR. The contribution is a formal system specification composed of a decision-state vector, residual-exposure accounting, constrained optimization objective, executable-action permission gate, and fail-closed AI control logic with auditable records. The analysis maps major Nominated Electricity Market Operator (NEMO) venues and related exchange operators into an operational venue topology and identifies where cross-border coordination fails in practice: interface-level timing, permission heterogeneity, and balancing-layer coupling. The resulting framework proposes how AI can be deployed as a bounded decision component inside regulated market operation with explicit governance, rather than as an unconstrained prediction layer.

3D foundation models recover video cameras and geometry in one forward pass, but some of the strongest are up to scale. Joint people-scene reconstruction then requires two missing outputs: metric scale and persistent person identity. We ask whether one up-to-scale foundation representation can support both through lightweight adaptation. Exact metric labels are scarce, but unlabeled in-the-wild video is abundant. We use people in curated web video to initialise the solution: a posed metric body and 2D keypoints give an approximate, closed-form scale pseudo-label. These pseudo-labels pretrain a Scale Readout, which is then fine-tuned together with a lightweight adapter using exact metric supervision from standard real-video training splits. At inference the head predicts metric scale from foundation-model tokens, without the ruler or its teachers. For person identity, we probe the pretrained foundation model alone and find evidence that its intermediate query-key features encode person correspondence across frames. In most evaluated moving-person clips, a mid-layer token prefers that person over the vacated location and other people. A tiny projection reads this correspondence; together with metric pelvis motion and proposal confidence, it drives dustbin-aware Sinkhorn association of per-frame bodies. WildHSR combines both readouts to reconstruct metric cameras, scene and people from monocular video. Each window is predicted feed-forward; analytic association and Sim(3) composition connect windows. On EMDB-2, WildHSR is the first feed-forward method in the published comparison to beat the best optimization-based WA-MPJPE and RTE while leading feed-forward methods on all three world-frame metrics. On RICH, it leads feed-forward people-and-scene methods on WA-MPJPE and W-MPJPE. The complete pipeline runs at 10.1 fps on one GPU.

Fully continuous diffusion language models (dLMs) denoise continuous representations without intermediate discretization, then decode all response tokens in parallel at the final step. Their performance on challenging reasoning tasks remains less established than that of autoregressive (AR) LLMs and masked dLMs. We scale Embedded Language Flows (ELF) to mathematical reasoning and code generation on GSM8K, MATH-500, HumanEval, and MBPP. We introduce ELF-REG, which improves learning with representation alignment and entanglement (REPA+REG), where a frozen AR teacher supervises intermediate denoiser features and supplies a global representation that is jointly denoised with the response. ELF-REG-L achieves 55.96% pass@1 on GSM8K at 64 network function evaluations (NFE), and 13.39% on MATH-500 and 22.56% on HumanEval at 128 NFE. It outperforms the evaluated comparable-scale dLMs in pass@1 on GSM8K and code, and improves MATH-500 pass@1 from 10.55% for the ELF-L baseline to 13.39% with ELF-REG-L. Without few-step training, the same task-specific checkpoints support strong low-NFE performance through early-stop, which decodes an intermediate clean prediction without completing the denoising trajectory. At 16 NFE, ELF-REG-L reaches 41.21% HumanEval pass@10, outperforming recent continuous dLMs of comparable scale.

Medical Named Entity Recognition (NER) for low-resource languages remains a challenging task due to high linguistic variability and a scarcity of domain-specific annotated corpora. This work presents a comprehensive empirical benchmark evaluating three fine-tuned transformer encoders-BanglaBERT, multilingual BERT (mBERT), and XLM-RoBERTa-against GPT-4o mini under zero-shot and few-shot prompting configurations for Bangla medical NER. In contrast to prior studies that evaluated large language models on limited subsets of only 50 samples, we conduct a large-scale evaluation across the full test set of 3,179 samples, providing statistically robust and reproducible baselines. Our fine-tuned XLM-RoBERTa model achieves an F1- score of 0.5959, establishing a new state-of-the-art and surpassing the previously reported best result of 0.5848. Crucially, we demonstrate that the language-specific BanglaBERT model consistently underperforms its multilingual counterparts with an F1-score of 0.4937, indicating that pretraining domain diversity can outweigh language specificity in highly specialized clinical settings. Furthermore, we present a detailed per-entity-type analysis for this task, revealing that Medicine and Specialist categories are recognized with high reliability, achieving F1- scores above 0.83, while the Symptom category remains the most challenging with an F1-score of 0.4367 despite being the most frequent training class. Finally, fine-tuned transformer models outperform the optimal prompting configuration by a factor of 3.76, confirming that prompt-only pipelines remain inadequate for structured clinical entity extraction in low-resource language environments.

Multimodal training relies on image-text corpora collected from external sources, creating opportunities for attackers to poison the data. Stealthy attacks can preserve plausible image-text pairs while concealing the differences used by detectors, so apparently clean data can still redirect the trained model. We therefore ask which properties a poison set must preserve for the attack to remain effective. A small poison set must still exert enough collective influence during training to induce the attacker's target behavior. We analyze this influence in terms of how often an attack pattern occurs and how strongly the examples carrying it jointly affect the model. This analysis motivates six corpus-level features that examine cross-modal neighborhoods, recurring text, and changes after text-span erasure without training the victim model. We introduce TraceGuard, an adaptive rank-based filtering method that uses agreement among complementary feature rankings to identify suspicious examples. It refines the selected set through shared patterns and adapts the removal threshold to each corpus without knowing the attack or poison rate. Across 19 attack configurations spanning image-text learning, generative vision-language model fine-tuning, and encoder-transfer tests, TraceGuard removes an average of 98.4% of poisoned examples and 5.4% of clean examples. After training on the filtered corpora, the residual attack metric is at most 1% in 13 configurations. Matched-removal controls and ablations support the contributions of sample selection and adaptive removal. Stress tests also identify detection failures under adaptive attacks and unnecessary removal on poison-free corpora.

Post-hoc correction adjusts a forecaster that cannot be retrained, such as a foundation model, but a correction fitted where errors are stable can hurt where they shift. We aim for downside control: not much worse than the starting forecast. We combine the frozen forecaster, a static corrector and an online corrector on the simplex, using only losses that mature after the horizon. Across seven benchmarks and four base models, two of them foundation models, the worst deterioration over 28 pairs at the main horizon is 0.15% and gains reach 11.5%. On day-ahead load for seven European bidding zones it lowers mean MSE in all seven zones, while single correctors raise mean MSE by up to 102% where the published forecast is most accurate. Three empirical conditions on expert speed, stream length and outcome alignment, each fixed by a documented failure, delimit its scope. Learning from the provisional outcome improves four zones on the settled one; learning on the settled outcome restores all seven.

When a tool-using agent's write times out or returns a server error, the action may already have taken effect. Retrying blindly duplicates it -- a second charge, a second announcement, a second deployment -- while giving up skips required work. We ask where exactly-once behaviour should be enforced: in the model, in the agent harness, or in the tool contract. We introduce LIMBO, a deterministic sandbox of six services with realistic contracts (optional idempotency keys, eventually consistent and missing read paths) and twelve fault modes injected at the service boundary, including late commits, redelivery and partial batches; every episode is graded against a ledger of committed effects. Across 25,930 episodes spanning nine recent models, three production agent harnesses, two contract variants and fifteen recovery conditions, the answer depends on the fault. When an immediate read-back can reveal what happened, the model decides: frontier models instructed to act exactly once almost never duplicate a write whose acknowledgement was lost (0.5%), weaker models often do, and the model explains 53% of the explained variance. When it cannot -- the request is still in flight, or the transport delivered it twice -- the same frontier models duplicate in 56% and 74% of episodes, and the contract explains 81%. We prove that no verification-only policy is exactly-once under late commits without a bound on in-flight time. Waiting works when such a bound is short and known, but with heavy-tailed in-flight delays even an hour of waiting per episode falls short of offering an idempotency key on every write, which lowers the duplicate rate from 28% to 4% because agents use keys when they exist. The harness barely matters, a guard that attaches keys transfers across harnesses unchanged, and agents reported success in 90% of the episodes in which they had duplicated an effect.

Vision-based legged locomotion methods assume clean depth at training time and rely on hand-tuned post-processing filters at deployment. However, filter parameters are rarely disclosed, hindering reproducibility, and performance degrades substantially when depth noise is left unaddressed. Building noise robustness directly into the learning pipeline would eliminate this dependency. While such robustness has been explored for proprioceptive inputs, analogous approaches for depth perception remain largely absent in legged locomotion. We propose DAWN (Denoising and Alignment in World models for Noise-robustness), a noise-robust perception framework for legged locomotion, which builds noise robustness directly into a world model via two modifications: (1) feeding noisy depth to the encoder while keeping clean depth as the reconstruction target, forcing the model to implicitly denoise its input; and (2) applying contrastive learning to align the latent states of noisy and clean depth. Importantly, DAWN is not tied to a specific noise model, requiring no manual tuning to the noise distribution at deployment. Furthermore, it incurs no additional inference cost over existing world model-based methods. Without any manual filter calibration -- relying solely on the learned noise-robust representation -- DAWN achieves zero-shot quadruped parkour on a Unitree Go1: traversing stairs up to 18 cm, clearing gaps up to 70 cm, and mounting steps up to 45 cm from raw depth observations. Ablation studies show that denoising and contrastive alignment contribute at complementary levels -- reconstruction and representation, respectively -- and yield additive gains when combined. Videos and code are available at: https://dawn-parkour.github.io/

We replicate the distributional-semantics extractive summarisation method of Mohd, Jan and Shah (2020) and adapt it to Hindi, substituting a Devanagari-appropriate component at every language-specific step. The system is evaluated on two independent corpora --- the Hindi portion of XL-Sum and FIRE ILSUM 2.0 Hindi --- under a Devanagari-aware ROUGE implementation validated against the XL-Sum authors' own multilingual scorer, with all comparisons drawn as 1000-resample paired bootstraps. In its published equal-weight configuration the replicated system is significantly worse than a three-sentence lead baseline on both corpora, trailing Lead-3 by 0.042 ROUGE-1 Fon XL-Sum and by 0.265 on ILSUM. A feature ablation shows that sentenceposition is the only feature that contributes: position alone reproduces the lead baseline exactly, removing position gives the weakest configuration,and a validation-tuned weighting can at best equal Lead-3 and never exceed it. TextRank fails identically, making this a class-level rather than an implementation-level result. A selection analysis shows the remaining features steer extraction towards long, entity-dense body sentences while the references reuse the article lead.Current Hindi benchmarks therefore cannot reward non-lead content selection, motivating purpose-built evaluation resources.

While deep learning accelerates expensive partial differential equation solving in computational fluid dynamics (CFD), existing methods like PINNs and FNOs often struggle with generalization, noise robustness, and physical consistency. We introduce the Transformer-Mamba for Flow Field (TM4FF) framework, a physics-constrained operator learning model with three key innovations: a Residual Wavelet Mamba (RWM) layer for feature denoising, a Transformer-based attention mechanism for enhanced feature fusion, and a physics-informed loss using Fourier derivatives to enforce the Navier-Stokes equations. Experiments on four CFD datasets show TM4FF achieves high accuracy and robust generalization across varying flow conditions.

Developing optimized machine-learning algorithms for edge devices with limited computational and memory resources is challenging, time-consuming, and highly dependent on device-specific constraints. In this work, we streamline an edge ML workflow to enable rapid development, optimization, and deployment of machine-learning (ML) models directly on the WeBe Band, a wrist-worn wearable device designed for multimodal physiological data monitoring. The proposed system automatically generates hardware-efficient ML models that can be easily integrated into the WeBe core firmware, supporting AutoML, hardware-aware quantization, and performance profiling to build models that meet desired latency targets while remaining compatible with device memory and power limitations. The proposed framework tightly integrates the open-source Piccolo AI ecosystem with an automated pipeline that generates deployable firmware artifacts, performs hardware-aware model compilation, and supports over-the-air (OTA) deployment. The system supports multiple lightweight model classes, including classical machine-learning algorithms and neural networks, and provides built-in on-device profiling tools to evaluate inference latency and memory footprint under realistic execution conditions. Experimental results demonstrate clear trade-offs between model complexity and deployability on a microcontroller, showing that classical models offer strong real-time performance while lightweight neural networks require careful resource management. Rather than proposing new learning architectures, the current work mainly focuses on system-level automation, deployability, and enabling researchers and developers to rapidly iterate on models and evaluate them directly on target hardware. Although demonstrated on the WeBe Band platform, the workflow is designed to be extensible to other ML-powered edge devices.

Predicting blood-brain barrier (BBB) permeability is critical for central nervous system drug discovery. Using the MoleculeNet BBBP dataset (n = 2039), this study systematically ablates molecular feature spaces to isolate featurisation from model architecture. We evaluate three feature families (Morgan fingerprints, RDKit physicochemical descriptors, SMILES bigrams) across four learning algorithms. Results demonstrate that predictive performance depends jointly on feature representation and algorithm. Dynamic Random Forest using combined features achieved the highest mean AUC (0.970, 95% CI: 0.963-0.977). Second, this optimal representation enables exploratory estimation of heterogeneous associations between molecular structure and BBB permeability using Generalized Random Forests. Constructing a pseudo-treatment from a LogP median split, we applied double/debiased machine learning to account for confounding. Orthogonalization substantially attenuates the heterogeneity detected by naive causal forests; no conditional effects remained significant after false discovery rate correction (smallest adjusted p = 0.082). Furthermore, orthogonalized feature importance shifted toward residual structural information in SMILES bigrams. Ultimately, once observed confounding is properly accounted for, evidence that LogP-BBB associations vary systematically across chemical space is insufficient. This underscores that feature representation and model architecture are coupled design choices, and that unorthogonalized causal forests risk overstating genuine treatment effect heterogeneity.

Cancer registrars, including Oncology Data Specialists (ODSs), must interpret complex and frequently updated coding and staging standards. We developed CRISS (Cancer Registry Intelligent Support System), a retrieval-augmented generation (RAG) conversational assistant that provides rapid, citation-supported access to registry guidance. This study evaluated whether CRISS could (1) support accurate and citation-supported responses, (2) improve access to and interpretation of relevant guidance, and (3) support training/helpdesk use while preserving human oversight of final abstraction decisions. We built a domain-specific knowledge base from national cancer registry standards, segmented into metadata-tagged passages and indexed as dense embeddings. Retrieved passages were used to generate citation-grounded responses through a large language model (LLM). Open-weight, proprietary, and non-RAG baseline models across Gemini and GPT families were evaluated on easy, medium, and hard registry questions using an LLM-as-a-Judge protocols. RAG configurations consistently outperformed non-RAG approaches, especially as question difficulty increased. Mean grounding scores for RAG were 0.62/0.56/0.59 across easy/medium/hard tiers versus 0.29/0.26/0.29 for non-RAG. RAG models also achieved higher semantic-similarity scores overall. Proprietary RAG models performed strongest on easy and medium questions, while local RAG models ranked highest on hard questions and proprietary models were generally more cautious. Domain-specific RAG improved evidence grounding and response quality for cancer registry questions while enabling citation-supported assistance across complexity levels. CRISS demonstrates the potential of human-centered, citation-grounded AI to support cancer registrars while preserving human oversight for final coding decisions.

We introduce BranchShine-CR, a 25M-parameter model for multilingual transcription into the International Phonetic Alphabet (IPA). It combines log-mel features, a rotary-position E-Branchformer encoder, intermediate self-conditioned connectionist temporal classification (CTC), and consistency regularization across augmented views. On 16,646 shared IPApack++ test utterances, it achieves 4.47% IPA character error rate, a 22.3% relative reduction from ZIPA-CTC-NS, with approximately one-twelfth as many parameters while being trained from scratch. BranchShine-CR also outperforms a similarly sized NeMo Conformer baseline across all 41 dataset language labels. Ablation studies indicate the individual components synergetically acting in model performance contribution. These findings support compact IPA recognition capabilities under limited compute budget, for applications in low-resource on-device pronunciation assessment.

The purpose of this research is to design, develop, implement, and provide preliminary validity and reliability evidence of the Software Engineering Self-Efficacy Scale (SESES). Framed by a conceptual framework using guidance in software engineering curriculum and concepts along with the notion of self-efficacy, we generated an initial item pool of n = 87 items to operationalize and measure software engineering self-efficacy among undergraduate computing students. The conceptual framework traces five dimensions: 1) Requirements Engineering, 2) Teamwork and Collaboration, 3) Software Quality Management, 4) Software Design and Architecture, and 5) Software Agile Methodologies. We pilot tested the SESES with n = 527 undergraduate computing students who had completed a software engineering course in the current semester or a previous academic semester. We employed Exploratory Factor Analysis (EFA) with the Principal Axis Factoring method and an oblique (Promax) rotation to examine the underlying structure of the SESES, resulting in the same five internally consistent latent constructs in the conceptual framework with minimal cross-loading and a simple structure in the pattern matrix, explaining approximately 57% of the variability in these data. Our findings suggest that software engineering self-efficacy is a multidimensional construct of five theorized and correlated, yet distinct latent factors. We unpack the limitations and delimitations of the research while exploring undergraduate computing students' software engineering self-efficacy using necessary domain-specific measurements.

The proliferation of photorealistic AI-generated images demands robust detection methods that generalize across diverse generative models. While existing approaches target manipulation-based forgeries with local artifacts, generation-based images (e.g., from diffusion models) lack such traces, posing a fundamental challenge. We observe that generative models prioritize global semantics at the expense of local texture fidelity, making low-texture regions key indicators of synthetic origin. To exploit this, we propose EIB-Net, an Entropy-guided Information Bottleneck Network. EIB-Net introduces a novel Image Entropy (IE) metric to automatically select the most informative (lowest-entropy) patch, then processes it with a Variational Information Bottleneck (VIB) to learn compact, generalizable features. Extensive experiments on DIFF, DiffusionForensics, and GenImage benchmarks demonstrate state-of-the-art performance: EIB-Net achieves 85.7\% accuracy using only 2\% of training data, outperforming full-image baselines by over 15\%, and maintains robust cross-generator generalization (83.5\% average accuracy on GenImage). Furthermore, our entropy-guided patch selection (EGPL) consistently enhances diverse backbones (CNNs and Transformers), proving its practical value for data-efficient detection.

Automation systems must adapt to changing tasks, equipment states, and staffing conditions while providing evidence for human review. This study presents a multi-line task-adjustment system integrating a local large language model, a digital twin, and human decision-making. A Propose-Verify-Decide workflow translates operator intent into structured requirements, generates a bounded set of candidate strategies, and checks semantics, simulation execution, and operational constraints. Linked records preserve traceability from requests to verification evidence and decisions. Thirty fixed test records were evaluated using four virtual surgical-instrument sorting lines: 28 assessed the workflow and two assessed model generation. Eighteen workflow cases met expectations; autonomous strategy-workflow success was 3/10, and correct rejection of invalid inputs was 7/8. All four cases that passed preceding checks, produced complete evidence, and reached final engineering review (CP6) passed that review. Together with the correct blocking of strategies that failed throughput constraints, this supports the effectiveness of staged screening and confirmation within the tested setting. Mean placement-validation pass rate across eight simulation evidence records was 97.50%. Mean times to the first reviewable response and simulation verification, excluding startup, were 12.94 and 164.39 s, respectively. Remaining failures involved semantic distortion, incomplete evidence, and missed invalid inputs. The results demonstrate a traceable strategy-review workflow, but do not establish overall reliability or long-term stability. Broader testing and physical evaluation are needed to assess generalizability.

Transformers achieve remarkable performance by jointly learning broad families of tasks during pretraining and adapting to unseen tasks from only a short prompt. Yet a rigorous mathematical and statistical understanding of this phenomenon remains limited. This paper aims to study how Transformers exploit shared cross-task structure and how this structure affects the sample complexity of in-context learning (ICL). Specifically, we characterize task-space complexity through covering numbers under a prescribed metric, thereby quantifying the low-dimensional cross-task structure without requiring an explicit parametric representation. The resulting cover provides a set of anchor functions, which we use to introduce a task-identification-and-evaluation procedure: context observations localize an unseen task among the anchor functions, and the response at a query is predicted by aggregating the corresponding anchor function query evaluations. For approximation, we explicitly construct a Transformer with Softmax attention to approximate this procedure. For generalization, we derive an error bound that separates the effects of the number of pretraining tasks and the prompt length. The scaling with respect to the number of pretraining tasks is governed by the intrinsic dimensions of the task space and input domain; once sufficiently many tasks are available, the dependence on the prompt context length becomes dimension-free. To the best of our knowledge, this is the first work to quantify cross-task complexity for general nonlinear task families and explicitly construct a Transformer that exploits their low-dimensional structure to perform ICL. Our theory provides a quantitative explanation of how joint pretraining across related tasks improves in-context generalization.

Emotion dynamics are critical for understanding crisis-support conversations, yet most computational work treats emotion as static utterance-level labels. We introduce EMPATH, a framework for understanding affective dynamics in mental health dialogues across three granularities: turn-level labels, transition probabilities, and global conversation archetypes. Applying EMPATH to text-based crisis conversations with self-identified Black texters discussing grief, we find persistent negative affect, gradual hope-ward transitions, distinct texter-volunteer emotional roles, and heterogeneous recovery trajectories. These results highlight the informative patterns that emerge from computationally understanding crisis support and expressions of grief as dynamic processes within conversations, as well as the overall value of emotion-dynamic analysis for analyzing and comparing affect in dialogues.

On-policy self-distillation (OPSD) has become a popular recipe for post-training LLM agents. It supervises the agent model at the token level with a stronger teacher view of the same model, obtained by conditioning on privileged information (PI). In this work, we show that in multi-turn agents, this paradigm teaches the student to act with confidence but without the information behind it. The trained agent behaves as if it had privileged information it never observed, and its performance falls well short of plain RL, in the worst case below the untrained base model. Therefore, we propose Privileged Self-Practice (PSP), which keeps the PI and moves it from the loss to the sampler. When the student's rollouts on a task mostly fail, we inject a short per-task instruction written by an analyzer model, sample the task again with the instruction in context, and train on the result with an unchanged GRPO objective. The privileged information stays in the prompt and never enters the loss. Across AppWorld and SWE-bench Verified, with three different student models, PSP obtains the best average score in every setting and is the only method that consistently outperforms plain GRPO, improving task-goal completion by up to 65% on AppWorld and the resolved rate by up to 61% on SWE-bench Verified.

Tool-calling agents produce heterogeneous outputs, interleaving structured tool invocations with user-facing natural language summaries. This output heterogeneity presents a structural failure mode in standard on-policy Reinforcement Learning (RL): algorithms like GRPO indiscriminately broadcast a homogeneous trajectory-level scalar advantage to all tokens. Consequently, gradient noise from summary generation leaks into tool-decision tokens, causing cross-segment credit misattribution and brittle optimization. In this work, we propose SLCA-GRPO, a framework incorporating Segment-Locked Credit Assignment (SLCA). To enable scalable exploration without costly real APIs and stable training, we first construct the Schema-Guided LLM Simulator (SGLS) as foundational training infrastructure. Building on this, SLCA decouples advantage estimation at the structural segment level within a single group of rollouts, without requiring additional rollouts from intermediate states. Supported by Hierarchical Rewards (HierR), SLCA routes execution advantages to tool tokens and preference advantages to summary tokens, eliminating advantage contamination (the dominant cross-segment credit misattribution channel) within each policy update. On a 7B backbone, SLCA-GRPO accelerates convergence and outperforms standard GRPO, ToolPO, and RLTR by +2.53 pp on in-domain evaluation, +1.36 pp on the Berkeley Function-Calling Leaderboard (BFCL), and +9.15 pp on $τ^2$-Bench under the same training budgets, achieving higher accuracy with reduced tool redundancy and costs.

Unified vision-language models (VLMs) that tokenize images through a vector-quantized (VQ) codebook routinely hallucinate objects on grounded yes/no benchmarks, yet existing decoding-time fixes treat this as generic miscalibration without an architectural account. Using activation patching across twenty-five models spanning eight LLM families, we identify an early-layer ($L_0$) attention routing circuit shared across VQ-tokenized VLMs and propose a three-gate diagnostic that distinguishes the models carrying it from those that do not. The diagnostic isolates ten positive models (five natural unified-VQ VLMs across three LLM families and five induced variants) and rejects the remaining fifteen. A single-variable architectural swap (LLaVA-1.6 CLIP+MLP $\rightarrow$ VQ+Linear) installs the circuit, while a matched-compute MLP control on identical data does not, isolating vector quantization as the source of the pathological signal; the routing pathway that carries it is one that the backbone already provides. Against tuned VCD and DoLA baselines, tuned DoLA wins on binary calibration, but \textbf{only $L_0$ ablation reduces object hallucination in open-ended generation} (CHAIR$_i$ reduces by $31\,\%$ relatively, whereas tuned DoLA and VCD leave it unchanged or worsen it). These results recast object hallucination in unified VQ VLMs as a property of architecture and pretraining, and yield a targeted intervention that mechanism-agnostic decoding cannot replicate.

Open-weight LLMs give downstream users control over the inference stack, but this flexibility can undermine post-release guarantees that sensitive knowledge has been modified or removed. Model editing and machine unlearning are used to modify or remove targeted knowledge without retraining models from scratch. However, existing security evaluations of these techniques face two critical limitations. First, they typically require access to either the original pre-edit/unlearning model or auxiliary classifiers to detect modifications or reconstruct pre-edit behavior. Second, they evaluate modifications under the canonical tokenization of an input, implicitly treating tokenization as a benign preprocessing step. We show that this assumption creates a security gap: the same input string can be represented by alternative valid tokenizations that induce different computational trajectories, allowing an adversary to bypass localized modifications and recover information intended to be suppressed. We introduce Toketive, a simple yet powerful reference-free attack that exploits the tokenization-based side channel to (i) detect modified knowledge and (ii) reconstruct the corresponding pre-edit response. It operates solely on the released model and requires neither the pre-edit model, training data, shadow models, nor auxiliary classifiers. Across five LLMs, six datasets, and six editing and unlearning techniques, we find that 38.6% of alternative tokenizations bypass the modification and recover the pre-edit response. Toketive detects modified facts with an F1 score of 84.2%, a 26.2% relative gain over the strongest baseline, and reconstructs pre-edit responses with 74.5% top-5 accuracy, 21.7% higher than the best baseline. Our results show that localized modifications should not be treated as robust knowledge-control boundaries without adversarial evaluation over alternative representations.

Pilot-aided channel estimation is a decisive block in orthogonal frequency-division multiplexing (OFDM) receivers for both 5G New Radio (5G-NR) and Long-Term Evolution (LTE). A large body of estimators exists, from simple least-squares (LS) interpolation to statistically optimal linear minimum-mean-square-error (LMMSE) variants and, more recently, deep convolutional denoisers, yet no single estimator is uniformly best: the winner depends on the propagation scenario, the numerology, the operating signal-to-noise ratio (SNR), the mobility (Doppler), and the antenna configuration. In this paper, we quantify this fact through a unified study of eight literature estimators evaluated over the 3GPP TR~38.901 Urban-Macro (UMa), Urban-Micro (UMi), and Rural-Macro (RMa) channels generated with NVIDIA Sionna, for both 5G-NR and LTE numerologies, in single-input single-output (SISO) and $8\times2$ multiple-input multiple-output (MIMO) settings. We then propose a \emph{condition-adaptive multi-agent orchestrator} that treats each estimator as an independent agent and dispatches, per operating condition, to the agent that is best on a validation split without any genie knowledge. The orchestrator tracks the per-realization oracle to within $1.07$~dB and improves the normalized mean-square error (NMSE) over the best \emph{fixed} strategy by up to $3.6$~dB at high SNR, where the low-SNR champion is no longer optimal. Because the agents are independent, running them concurrently delivers this best-of-eight accuracy at essentially single-estimator latency: a data-parallel partition scales the wall-clock nearly as $1/K$ with $K$ workers (up to $6.9\times$), whereas naive by-algorithm partitioning is Amdahl-limited by the heaviest agent. The results substantiate multi-agent orchestration as a practical route to robust channel estimation across heterogeneous 5G-NR/LTE deployments.

General Purpose Service Robot (GPSR) tasks, as defined in the RoboCup@Home benchmark, require robots to interpret diverse natural language commands and generate multi-step action sequences in real home environments. Conventional Single Prompt (SP) approaches suffer from context bloat and the "Lost in the Middle" phenomenon, leading to unreliable task planning. We propose an LLM chaining architecture that separates instruction classification and action generation into two specialized stages, reducing per-inference prompt length by approximately 45% while improving planning consistency. We evaluate our method using 100 randomly generated GPSR commands across three language models spanning local open-source and frontier cloud deployment contexts. Results show consistent planning improvements over SP across all models, with gains of up to +37 percentage points on local models. Further, real-robot execution experiments on the Toyota Human Support Robot (HSR) reveal that planning success alone does not guarantee task completion, with 6 of 10 tasks completing successfully and execution-layer failures identified as the primary remaining bottleneck.

Federated learning (FL) lets EEG decoders learn from recordings of several subjects without pooling them. We consider two light EEG decoders, the Riemannian SPDNet and the Euclidean EEGNet. Both split into a trunk, which builds a latent representation, and a head, which classifies it. Inter-subject variability, however, makes a single shared FL model a poor fit for each subject. Personalised FL addresses this: all subjects learn a common trunk, and each subject keeps its own head. We adapt it for SPDNet and study its effects against standard FL and centralised training, with EEGNet as a Euclidean baseline. Experiments cover three motor-imagery datasets that span diverse regimes in channels, subjects and classes. We observe that personalised SPDNet reaches higher accuracy than both standard FL and centralised training, while converging in fewer rounds and communicating fewer parameters than standard FL. It also outperforms every EEGNet configuration on two of the three datasets, although centralised EEGNet outperforms centralised SPDNet.

Sparse activation reduces mixture-of-experts computation without eliminating the need to store all experts. We present Routide, a Swift/MLX runtime that executes the text path of a pinned public Qwen3.6-35B-A3B quantized checkpoint while keeping expert weights in iPhone storage and a byte-budgeted subset in memory. We characterize cache-policy sensitivity, numerical comparison boundaries, and measurement limits. Across five recorded 128-token workloads, fixed-route replay gives 0.00% demand hits with a 512 MiB LRU cache, 18.80% with seeded random eviction at the same budget, and 38.58% with 576 MiB LRU. The apparent capacity cliff is therefore a policy/workload interaction, not a universal memory requirement. Same-runtime Mac controls preserve generated sequences across eviction and asynchronous prefetch, including 2,560 exact token comparisons and 10,334 speculative loads. In contrast, complete resident-Python versus recorded-phone sequences disagree on all five tested cases, precluding a general numerical equivalence claim. Two separately scoped iOS 27 memory protocols observe sampled process-footprint peaks of 1.87-2.32 GiB on short prompts and 2.39-2.73 GiB on one longer prompt. We retain a thermal stopping event, negative timing comparisons, and a single qualified whole-device power estimate. These results establish bounded feasibility and identify limitations that a deployment claim must not hide.

Onboard vision-language models could enable satellites to answer queries directly, but exhaustive tiled inference over high-resolution imagery is slow and energy-intensive. We identify answer-invariant token redundancy (AITR): image tiles and vision tokens that can be removed without changing the final answer. We present Rift, a two-stage system that performs query-conditioned tile pruning followed by elastic prefill to reduce token budget. We evaluate it on LLaVA-1.5 7B running on Jetson AGX Orin. Compared with exhaustive tiled inference, Rift reduces energy by 78% and latency by 69%, while increasing accuracy from 45% to 73%.

Atmospheric observations are sparse, heterogeneous, and unevenly distributed, whereas many generative atmospheric models learn distributions over regularly gridded multivariate states. Once pretrained, diffusion models can supply atmospheric priors that can be combined with observation-derived likelihood factors in a Bayesian formulation. However, these observation sources differ substantially in geometry and sampling density, complicating the consistent use of their observations within a common inference framework. Here, we formulate this reconstruction problem as generative atmospheric super-resolution and introduce composable observation interfaces for conditioning a single pretrained 13-variable atmospheric diffusion model. The interfaces convert sparse radiosonde (R), clustered aircraft (A), and dense irregular surface-station (S) observations into source-specific likelihood factors that specify where observations constrain the gridded state, how residuals are counted under uneven sampling, and how strongly each source guides posterior sampling. We developed the aircraft and surface observation interfaces using 2019 observations and evaluated the selected interfaces throughout 2020 without further tuning. Compared with reconstructions conditioned only on radiosonde observations, the composed R+A+S interface reduces RMSE evaluated against ERA5 by $9.24\%$ across all 13 state variables over the CONUS domain. The aircraft and surface factors provide complementary improvements in upper-air and surface variables. The R+A+S combination also lowers the Continuous Ranked Probability Score (CRPS), while evaluations at held-out aircraft and surface-station observations show reduced prediction errors. Together, these results demonstrate a modular route for conditioning a pretrained atmospheric generative prior on heterogeneous in situ observations without retraining the underlying model.

Natural load-bearing and transport networks are not assembled in a single step; they emerge through a temporally ordered process of growth, branching, reinforcement, and loop formation. Inspired by this developmental logic, this work introduces a morphogenetic graph-generation framework for mechanical lattices in which a discrete dot matrix provides potential nodes and the final architecture is created by sequential cross-layer and intra-layer growth. The same rule is visualized in two dimensions as a leaf-vein-like developmental sequence and implemented in three dimensions on a 3x3x3 nodal matrix containing 27 candidate nodes. A dataset of distinct three-dimensional lattices was evaluated by beam-based finite element analysis and represented directly as graphs. A graph convolutional neural network (GCNN) with three graph-convolution layers and dual global pooling learns the topology-property mapping and predicts effective compressive stiffness. Coupling the GCNN surrogate with rapid structural sampling enables inverse design: for a target stiffness of 1000 MPa, the selected design was predicted at 1042.43 MPa and validated by finite element analysis at 1027.49 MPa. Beyond straight members, the framework has also been extended to parameterized horseshoe-shaped curved beams made of nonlinear materials, enabling topology-geometry design toward prescribed deformation shapes. Our work provides a paradigm for augmenting the database of mechanical metamaterials, and the resulting perspective links biological morphogenesis, graph learning, and nonlinear shape programming in a unified generative design framework for architected materials.

AI-driven scientific discovery accelerates research by autonomously developing solutions and designs. Large language model (LLM) agents support this process through iterative generation and evaluation. Yet these iterations alone do not ensure cumulative progress or establish which directions to pursue next. Costly evaluation further constrains the scope of exploration. Neural architecture discovery brings these challenges together, coupling open-ended design with resource-intensive experimentation. We introduce EvoTreeNAD, a genealogy-guided evolutionary algorithm that constructs trainable architectures without a supplied seed or a hand-specified search space. Starting from an empty root, it grows a persistent genealogy in which each new node represents a complete architecture. Top-percentile values computed from each node and its descendants guide lineage selection. Using the selected design history, an Idea Agent proposes a variant and a Code Agent implements it. Each evaluated variant becomes a child node, expanding the genealogy while providing evidence for subsequent lineage selection. Our theoretical analysis establishes the existence of stationary variation regimes as the genealogy grows. Under specified variation assumptions, sustained top-percentile family values quantify the probability of generating high-reward architectures in these regimes. EvoTreeNAD discovers architectures that outperform the compared NAS and NAD baselines, achieving CIFAR-10/100 test errors of $2.05{\pm}0.06\%$ and $15.09{\pm}0.22\%$. On all six MedMNIST-v2 tasks, the discovered architectures surpass the strongest listed baselines. A controlled CIFAR-10 study further shows that EvoTreeNAD outperforms direct generation, best-of-$N$ greedy continuation, and full-family-mean routing.

Decentralized LLM-based multi-agent systems coordinate through local interactions, but an agent can remain responsive while its task-solving quality persistently degrades. Such gray failures require protecting current tasks before sufficient evidence exists to alter future routing, while still allowing recovered agents to rejoin. We introduce MeshHeal, a fully decentralized self-healing framework that couples ability-matched peer review across two timescales. At the fast timescale, an adaptive hierarchy escalates uncertain or low-scoring outputs from repeated single-reviewer evaluation to committee deliberation and, when needed, correction before use. At the slow timescale, a task- and ability-conditioned peer-relative detector aggregates scores to distinguish persistent degradation from ordinary output variation, trigger mandatory committee review, and eventually exclude degraded agents from ordinary routing; recovery probes provide fresh evidence for reintegration. To faithfully evaluate routing, we introduce Model-Backed MAS Evaluation, which ties ability assignments to execution models, since prompt-based ability assignments alone can leave routing errors hidden. Across BBH, MATH, and MMLU-Pro, MeshHeal achieves 0.839 degraded-phase accuracy using 51k total model tokens per task, versus the strongest baseline Symphony's 0.807 accuracy using 115k per task. Under staggered degradation and recovery, MeshHeal isolates degraded agents, keeps them excluded from ordinary task execution until recovery, and returns them to normal routing.

Large language model (LLM)-based multi-agent systems can automate alpha factor mining, but their reliance on external APIs limits control over cost, availability, and confidentiality. Long research loops also tend to revisit a few successful economic mechanisms that lead to research path collapse. To address these limitations, we propose AlphaDiverse, a framework that integrates a multi-agent alpha research system, diverse research path collection, and post-training for local agents. We let the research system generate complementary plan portfolios and vary research environments across loops to collect diverse research paths. Using these diverse traces, we warm-start local Planner and Realizer agents with supervised fine-tuning. Then, we propose a joint GRPO method to optimize both of them using predictive quality and diversity of contributions. Research feedback is confined to inner period data, while a frozen final model is evaluated on a later outer period data, thereby avoiding test-set tuning. Experiments across four Chinese stock universes show that AlphaDiverse can combine competitive prediction with broader exploration.

Tool-using agents are continually updated with new interaction data. After each policy update, however, previously estimated action credits may become stale. Recomputing them from scratch can require many additional tool calls and environment interactions, making repeated updates increasingly expensive. We ask a simple question: when does historical action credit actually need to be updated? Our key observation is that a change in action value does not necessarily imply a change in the decision. Historical credit can still be useful as long as policy-induced drift is too small to overturn the existing action ranking. Building on this idea, we introduce pairwise branch sensitivity to capture how strongly a policy update affects the downstream regions that distinguish two candidate actions. We then derive a first-order anchored credit-transport estimator that updates historical credit using old interventional trajectories, and propose a Decision-Sufficient Credit Gate (DSC-Gate) that chooses whether to reuse, transport, or resample credit. Experiments show that branch sensitivity explains credit drift substantially better than global policy distance. With sufficient historical data, credit transport reduces estimation error, while its benefit to decision making is concentrated on updates that affect action-distinguishing branches. On a fully independent test set, DSC-Gate changes mean regret by only +0.00004 relative to a gap-based gate while reducing mean new tool steps from 472 to 286, a 39.4% reduction. We observe the same pattern after a real tool-agent parameter update. Overall, our results show that agents do not need to recompute action credit after every policy update: much of the historical evidence can be reused or cheaply corrected, reducing the additional interaction required to keep action decisions up to date.

Robot policies deployed in real environments naturally accumulate mixed-quality experience, including successful executions, partial progress, and failures. Although these rollouts provide valuable information for further learning, directly incorporating them into imitation learning may reinforce undesirable behaviors, while offline reinforcement learning often suffers from unreliable value estimation under sparse rewards and limited data coverage. We consider a practical post-deployment setting where learning relies only on naturally accumulated autonomous rollouts, without additional human corrections or exploratory interaction. To effectively exploit such experience, we propose Predictive Action Chunk Learning (PACL). PACL first learns a predictive chunk-level critic that evaluates temporally extended action sequences and augments temporal difference learning with future latent prediction, providing richer supervision for long-horizon value estimation. The learned critic then converts chunk-level Q-values into discrete quality conditions, which guide a diffusion actor to learn jointly from these mixed-quality experiences without treating all behaviors as equivalent supervision. At inference, the actor generates multiple action chunks and the critic selects the highest valued candidate. Experiments across simulated and real-world robot manipulation tasks show that PACL consistently improves the pretrained policy and outperforms strong imitation learning and offline reinforcement learning baselines.

Despite strong performance on standard benchmarks, it remains unclear whether large language models (LLMs) evaluate social pragmatics in ways that align with human judgments. We evaluate LLM politeness judgments using two English-language datasets with complementary annotation formats: continuous human ratings and three-way categorical labels. Across the seven evaluated models, we find that inter-model agreement is stronger than model--human agreement. Strategy-level analyses suggest that model--human alignment is associated with explicit linguistic cues, while some rapport-building strategies occur more frequently in misaligned cases. In the categorical task, model predictions exhibit systematic neutral compression, characterized by the overproduction of Neutral labels and the underprediction of Impolite labels. This pattern persists when expert consensus is used as the reference on a diagnostic subset. Our findings highlight the need for pragmatic evaluations that go beyond aggregate agreement metrics by examining directional patterns of model--human disagreement across different human references.

Low-rank adaptation (LoRA) has become a popular parameter-efficient fine-tuning method for large language models. A key challenge in LoRA is how to determine the rank of each adaptation matrix, as rank directly controls its capacity and efficiency. Existing adaptive-rank methods typically allocate ranks according to manually designed importance scores, which are not directly derived from an optimization objective. In this work, we propose $\ell_p$-LoRA, a principled rank-allocation method based on $\ell_p$ regularization with $0<p<1$, which is a classical sparsity-inducing technique in signal processing and statistics. Specifically, we regularize the energy of each rank-one LoRA component, encouraging redundant components to vanish while preserving important ones. We derive the corresponding proximal subproblem and reduce the matrix optimization to a two-dimensional problem, leading to an implicit thresholding criterion for identifying redundant components. Experiments on natural language understanding and question-answering tasks demonstrate that the proposed method achieves competitive performance with existing LoRA baselines.

Video understanding is increasingly performed by multi-stage LLM agents that separate temporal grounding, visual observation, and reasoning. Yet these stages are typically evaluated on different benchmarks and distributions, making it difficult to determine where hallucinations originate. We first organize existing benchmarks around these stages and show that their scores provide inconsistent diagnostic signals: stronger stage-level performance does not reliably imply lower downstream hallucination, and even benchmarks targeting the same capability can disagree. We therefore introduce a causal stage-intervention protocol that overwrites individual stages while holding the downstream task fixed. Across 60,008 runs on three video-agent architectures, we find that grounding is the dominant source of downstream error, with roughly four times the causal impact of corrupting visual observations. Successful grounding depends primarily on locating the correct region rather than precise temporal overlap, explaining why standard mIoU metrics poorly predict downstream reliability. We further find that incorrect evidence is substantially more harmful than missing evidence. Finally, auditing existing benchmarks against these interventions reveals that their scores do not reliably predict causal cascade sensitivity and can fail under distribution shift. These results motivate intervention-based, stage-aware evaluation for trustworthy video agents.

We present a personalized Korean visual speech recognition (VSR) system and quantify, on the nine-camera OLKAVS corpus, the gap between the population-level benchmark score and an individual user's error. A video-only Conformer initialized from English-trained weights attains 9.95 - 12.19% character error rate (CER) under the corpus protocol against the published 26.64, and 19.00 - 21.52 on unseen wording. Per speaker, CER spans 1.0 to 52.2%, with seen wording lowering CER by 7.0 - 9.0 points and professional delivery and spontaneous speech raising it by 8.5 - 10.5 and 12.7 points. A low-rank adapter with 4.6% of the parameters, trained on 4 to 29 minutes of the user's frontal video, lowers the CER of twelve high-error speakers by 2.13 to 3.58 points, transfers to every camera without loss, and keeps 85% of the full fine-tuning gain at 12% of its cost to other speakers. Cameras above the mouth plane add about six CER points as a constant offset that training on all views keeps small.

Cross-embodiment learning has shown that a single model, such as a vision-language-action (VLA) model, can learn state representations and manipulation skills that can be applied across heterogeneous robots to accomplish various tasks. We hypothesize that the same holds for safety enforcement. The reasoning required to satisfy a safety constraint, such as detecting an obstacle, recognizing that it should be avoided, and selecting a safe abstract action, is largely shared across robots. What differs across embodiments is how the abstract safe action is realized: morphology, kinematics, and dynamics determine which actions are safe and feasible. Consequently, the same action can be safe for one robot and unsafe for another. This is especially important for generalist manipulation policies that operate in a common end-effector action space without explicitly capturing how safety depends on the robot's morphology and kinematics. We propose embodiment-conditioned safety filtering, in which a Hamilton-Jacobi reachability-based value function and its corresponding safety-maximizing policy are shared across robots. Using a morphology-aware latent representation of the robot and its environment, we perform Hamilton-Jacobi reachability analysis directly in latent space so that the learned safety concepts can generalize across embodiments while remaining explicitly conditioned on each robot's morphology and kinematics. We evaluate our approach across five bimanual robot embodiments and five manipulation tasks with whole-body collision-avoidance constraints. Our results show that a single policy, jointly trained across five manipulation tasks and four embodiments, exhibits zero-shot generalization to a held-out embodiment, reducing the nominal policy's collision rate. They also show that training using more embodiments improves generalization.

We study spectral graph neural networks built from Hermite polynomials and propose HermNet, a simple model that combines a nodewise predictor with normalized Hermite propagation. Its sparse recurrence requires neither eigendecomposition nor a learned basis. We distinguish the basic model from optional coordinate calibration, response normalization and Gaussian derivative regularization. Hermite and other complete polynomial bases span the same degree-bounded filter space, but their coordinates can produce different optimization behavior under limited training budgets. We analyze this behavior through spectral signal energy, label sampling, changes in learned features and the bias--variance trade-off of regularization. Controlled synthetic experiments identify a regime in which plain HermNet outperforms matched polynomial-basis alternatives, including with a jointly trained nonlinear predictor. Curvature regularization further improves HermNet when the same functional penalty is available to every comparator. Fixed-predictor controls support the advantage under short training budgets, but longer training removes the plain-model lead. Matched real-data comparisons show accuracy deficits, and architectural and numerical studies identify further limits. Together, the analysis and experiments clarify when Hermite propagation is useful and how calibration and regularization affect its performance.

Post-training quantization (PTQ) reduces the cost of on-device text-to-speech (TTS), but published evaluations cover one system or method. We evaluate PTQ across TTS architectures under one protocol with three core models, weight and activation ablations of eight more, and two held-out models quantized blind. Four-bit per-channel weights reduce UTMOS, a predicted mean opinion score, by 2.8 on Supertonic and 0.07 on Kokoro, and per-tensor scaling can cause severe degradation even at 8 bits. The same bit width yields different outcomes, because the sensitive component is model-specific and not reliably predicted from the model class. A staged ablation procedure identifies it, and per-layer GPTQ can restore it to within 0.1 UTMOS. Real int8 and int4 kernels reproduce the simulated ordering at hardware-dependent cost. On a Mac mini, a 4-bit weight kernel runs Supertonic at 0.60x the fp32 latency while int8 is slower, so each configuration requires validation on the target runtime.

Cross-country recommendation on modern e-commerce platforms is typically deployed with disjoint user and item ID spaces across markets, removing the shared anchors that conventional cross-domain methods rely on. Generative recommendation (GR) mitigates this by mapping items into a shared token space and training a unified model, but existing approaches keep behavior sequences strictly country-specific, so knowledge transfer occurs only at the parameter level and remains absent at the data level. Inspired by code-switching corpora in multilingual natural language processing, we propose CMRec, a cross-country GR framework that injects cross-country supervision at the data level via dual-constrained, context-aware code-mixing. CMRec first learns a shared semantic codebook from multi-modal content and behavioral co-occurrence across countries. It then uses this codebook to synthesize mixed-country sequences via token-level substitutions that satisfy both static (content) and dynamic (e.g., price, audience, popularity) constraints. Finally, it introduces a context-aware loss that reweights mixed samples according to their plausibility in the current sequence. Experiments on two real-world multi-country datasets and an online A/B test show that CMRec substantially improves recommendation quality in data-sparse countries while preserving performance in data-rich countries, achieving +1.77% advertising revenue and +2.64% orders on a large-scale e-commerce platform.

Group-based reinforcement learning (RL) methods, such as GRPO and its variants, have become a leading paradigm for training reasoning and agentic large language models (LLMs). While their group-normalized advantage estimation is reliable at the response level, it becomes systematically biased at the step level, since coarse-grained trajectory-level advantages are hard to accurately reflect the contribution of individual steps (i.e, failed trajectories may contain valuable steps). Revisiting the foundational RL definition, we notice that GRPO's success on single-turn tasks stems from its advantage estimation strategy, which adheres to the basic definition: the mean reward of multiple actions sampled from the same state constitutes a credible state-value estimate. Extending the faithful estimation to step-level would in principle demand sampling multiple actions from each intermediate state, which is too costly on a per-state basis. To mitigate this issue, we propose a Graph-based Faithful sTep-level credit-assignment framework (GRAFT) that grafts all rollout trajectories into a trajectory graph, recovering node state-values via Bellman iteration on the graph, and assigning credit to each edge by the node value difference. Theoretically, the estimated step-level advantage faithfully adheres to the basic advantage definition in RL. To further ensure the reliability of step-level advantage estimation, we further propose Graph GAE, which extends GAE to the trajectory graph for reducing the impact of state-value estimation bias. Experiments across a range of multi-turn agentic benchmarks show consistent gains over GRPO and superior performance compared to recent agentic RL algorithms. Code will be available at https://github.com/xcyao00/GRAFT.

Misinformation is widely reported to propagate faster on engagement-based platforms, yet prior work largely focused on empirical analysis, without identifying a specific algorithmic mechanism that results in this phenomenon. Thanks to the open-sourcing of X's recommendation algorithms, we conduct what is, to our knowledge, the first component-level study of the recommendation algorithm deployed by a social media platform, which examines how each of its components affects misinformation propagation. Specifically, we identify the engagement fungibility mechanism in the algorithm, where the final recommendation score is constructed as a weighted sum of all predicted user activities. As a result, a tweet can be repeatedly recommended simply because it is predicted to draw many instant reactions (e.g., likes and retweets), even when it is not expected to draw thoughtful responses (e.g., replies and quotes). Since misinformation typically draws a larger share of its engagement from instant reactions, this mechanism enables it to receive more recommendation exposure and to propagate faster. To empirically validate this mechanism, we re-implement X's recommendation algorithm on the USC X 2024 election corpus, and build a calibrated simulation study to analyze the impact of different scoring rules. We find that re-tuning the metric weights has little or even a negative impact on reducing the credibility exposure gap, while those scoring rules that set a precondition of thoughtful engagement for amplification would be able to alleviate the gap significantly, across 46 robustness checks. Our diagnosis, therefore, yields a simple and deployable fix, a reflective-threshold gate that withholds amplification until a tweet is predicted to draw thoughtful engagement, which we find to reallocate exposure away from low-credibility content at no cost to mainstream exposure and with no loss of engagement.

Personalized value alignment has become increasingly important as large language models (LLMs) are expected to accommodate diverse user preferences. However, existing methods typically align model outputs with a static value profile across prompts, overlooking that the salience of value dimensions varies substantially across contexts. Inspired by Lewin's Field Theory, which views human behavior as jointly shaped by personal dispositions and situational constraints, we model personal values as priors and context-dependent preferences as posteriors. We propose BaCVA, an inference-time Bayesian Context-aware personalized Value Alignment method that approximates posterior personalized preferences by integrating static personal values with scenario-specific value salience. BaCVA first estimates contextual value salience from generally normative responses, and then employs a dual-view personalization module to infer posterior preferences from complementary personal-value and scenario-driven perspectives. This Bayesian formulation enables more accurate and adaptive personalized value alignment while improving data efficiency via prior values. Extensive experiments on benchmarks demonstrate its superiority over strong baselines.

Autonomous penetration-testing harnesses use large language models (LLMs) for reconnaissance, exploitation, and reporting, but often rely on those same models to confirm findings, grade severity, and select agents. This can lead to false positives, inflated severity, and wasted compute. We examine how System One decision models, lightweight non-generative classifiers that return typed, calibrated verdicts, can support these decisions. We make five contributions. First, we define four decision points: finding adjudication, severity recalibration, agent pruning, and confirmation loops. Second, we present an exploratory NeuroSploit case study comparing one run with TypeSafe System One (Jev) and one without it against a web target containing 13 vulnerabilities. Differences in severity distribution, runtime, and grading by exposed data type motivate the architecture but do not establish statistical significance. Third, we review published specifications for Jev, Jev-Ultrafast, and the open-source Laya without assuming that results from other benchmarks transfer to penetration testing. Fourth, we discuss RLHF, RLAIF, RLCD, and RLHV as training approaches and their implications for trust in security decisions. Finally, we propose Rave, a domain-adapted System One model, and outline its training data, evaluation protocol, and potential effect on harness assurance.

Vibrational spectral prediction can become inaccurate when localized stereoelectronic environments perturb intermediate response states and high-risk response units dominate characteristic spectral fingerprints, making prediction across external chemical space difficult. SO(3) Equivariant Neural Kalman Networks (SENK) form a response-state cascade that combines an equivariant transformer backbone for Hessian, dipole-derivative and polarizability-derivative learning, an Equivariant Neural Kalman bridge for state-dependent refinement and reliability sensing, and an NBO-informed electronic-prior pathway coupling consistency regularization with bounded, branch-specific guided spectral calibration. SENK outperforms DetaNet on QM9S and QMe14S while preserving full-spectrum IR and Raman fidelity from small molecules to drug-like systems. SENK remains stable and selectively improves spectrally sensitive features in biomolecular systems with complex stereoelectronic effects. It therefore integrates tensor prediction, reliability diagnosis and physics-informed calibration, supporting transferable vibrational spectroscopy from molecular systems to functional molecular materials.

Protein modification requires navigating an immense sequence space, yet wet-lab validation remains low-throughput and costly. Although computational paradigms including protein language models (PLMs), large language models (LLMs), and LLM-based agents have shown promise in protein modification, their relative efficacy across realistic experimental decision-making settings remains unclear. To bridge this gap, we introduce PFArena, a benchmark comprising four controlled task interfaces that cover single-mutant generation and multi-mutant ranking. By providing varying levels of mutation fitness data, PFArena reflects four representative research scenarios characterized by differing degrees of prior experimental context. We assess six PLMs, six LLMs, and five LLM-based agents using complementary metrics to measure both peak and overall protein modification performance. Our evaluation reveals that model performance shifts systematically with the availability of target-specific experimental evidence: PLMs demonstrate proficiency in open-ended single-mutant generation by leveraging protein-specific priors, whereas LLMs and agents perform strongly in multi-mutant ranking, particularly when target-specific fitness data are available. Nevertheless, all model families face fundamental challenges with increasing search-space size and mutation depth. We release our code and benchmark suite to facilitate reproducible research in model-assisted protein modification.

Harnesses, the products that run AI coding agents, are multiplying, and enterprises are rolling them out to their employees: what started as pilots with a few hundred seats is scaling to tens of thousands. Most enterprises do not build these harnesses but buy them from large vendors, such as Anthropic's Claude Code or OpenAI's Codex. A harness decides which model answers, what the model reads, how the prompt cache is used and which subagents run, so it picks the rate on the price sheet and sets the volume bought at it. Enterprises that keep a proprietary or untuned harness at its defaults inherit these choices and their bill. We build a fast, customisable router in which Jev, a classifier with calibrated probabilities, labels every prompt against a bring-your-own taxonomy of agentic requests. Because one user turn is many requests over a prompt cache that belongs to one model, the router moves work only where no running conversation has to rebuild its cache: at session start, in side lanes and at subagent launch. From the price sheet we derive when a mid-task switch pays back, and a crossover: on long tool-heavy sessions the highest-priced model costs less than the next tier, as repricing about 10,000 real sessions from public datasets confirms. In an emulated enterprise of 10,000 seats with user behaviour taken from these datasets, the router recovers 14 to 21% of model spend at Anthropic's list prices of 21 September 2026, \$3.3M to \$5.0M a year. The paper also maps the risks across twenty harnesses, prices the dependence on one vendor's models, and proposes a control plane that enterprises can run from within, starting now, with a ladder for deciding later whether to own the harness.

LLM agents are deployed into infrastructure that grants them broad host authority, yet existing agent-security benchmarks and defenses operate almost exclusively at the application telemetry layer: the served tool manifest, the user prompt, and the model's messages. Some threats, however, smuggle malicious instructions and actions past the application boundary, leaving them invisible to that layer. In this work, we bridge that gap by pairing application-level agent telemetry with kernel-level syscall traces to present the first paired-evidence characterization of kernel-level versus application-layer signal for agent security. To quantify the value of the enhanced telemetry, we introduce Agent Cross-Layer Evidence (ACE), a paired-session corpus of 4,047 sessions and 17 threat models spanning six delivery-vector families and 14 of the 25 OWASP LLM and agentic threat categories, organized into 12 attack mechanics with per-mechanic characterization of where the most discriminative evidence lies. Across four distinct detector families, we find that kernel evidence is discriminative on its own and that composing it with application-layer evidence generally outperforms either single-layer view, revealing complementary signals that single-layer analyses can miss. We further demonstrate generalization to unseen attack families and transfer to an alternate agent runtime. Together, these findings establish the value of cross-layer evidence for agent security.

Effective robot assistance beyond narrow roles and repetitive tasks requires robots to be proactive - to decide what needs to be done rather than waiting to be told. While proactivity is increasingly explored, it lacks a unified formulation, and work in the domain is typically evaluated offline against static human models that cannot capture the effect of a robot's actions on the environment and the user's own behavior. We introduce a unified formalism for proactive robot assistance, organize it into three levels, and provide a framework to address the highest level of unprompted proactive assistance. We then show that offline evaluation overstates performance in this setting, and contribute a closed-loop evaluation with a human model that adapts to the robot. Finally, we present a method, GAP, that instantiates our framework, learning from passive observation to anticipate user goals and act. Under closed-loop evaluation, prior state-of-the-art methods collapse, in some cases adding more work than they save, while GAP remains robust and substantially outperforms them.

Agent behavior depends on the harness surrounding a language model, but it remains unclear whether language models can reliably improve such harnesses for hardware-design tasks. We study automatic harness evolution around a fixed subject model on 12 proprietary design-verification root-cause localization tasks. Across five trials per task, automatically evolved harnesses increased completed attempts by 71-76% and any-hit task coverage by 80-100%, while total correct attempts improved by only 18-24%. The strongest success reproducible at least twice result improved by one task, and later candidates exchanged gains across tasks rather than preserving them. An auxiliary candidate improved on a four-task validation set excluded from search but tied its baseline on a subsequent 12-task replay containing both search and validation tasks, so the selected gain did not persist across the full pool. Across the tested lineage, useful search, evidence, and finalization behaviors appeared in different candidates but did not consistently consolidate into a single harness that dominated across tasks and metrics. In a separate CVDP cross-benchmark case study, an automatically evolved defined-width repair harness produced 35.6% more functional passes than its 142-task reference baseline; the final functional verifier scored completed outputs but was not shown to the subject agent during repair. These results support archive-aware selection when evolution yields complementary specializations without consistent consolidation.

Automated Program Repair (APR) benchmarks have traditionally been constructed as static datasets whose characteristics are inherited from the defects they contain. While this paradigm has enabled decades of progress, finite corpora provide limited experimental control, become increasingly susceptible to contamination as they are reused, and cannot be systematically regenerated or adapted as evaluation requirements evolve. We propose specification-driven benchmarking, a paradigm in which benchmarks are defined by executable specifications and realized through benchmark generation. The specification explicitly declares the intended properties of the benchmark (including program context, fault taxonomy, difficulty, validation strategy, and corpus constraints) while a generation pipeline realizes those requirements through independent generation, validation, and corpus management components. We develop the conceptual foundations of this approach by introducing a taxonomy of benchmark specification dimensions, establishing how each specification dimension maps to deterministic architectural responsibilities, and arguing that independent validation is a structural requirement for trustworthy benchmark generation. An end-to-end example illustrates how specification choices propagate through the pipeline to produce benchmark instances whose properties are independently verifiable. By treating the benchmark as an executable specification rather than a static dataset, the proposed paradigm shifts benchmark construction from artifact curation to declarative experimental design.

Reliable intervention-oriented uncertainty quantification from Earth observation (EO) remains challenging when continuous treatment shifts, spatial dependence, limited support, and satellite-outcome uncertainty must be addressed simultaneously. Existing causal, conformal, and spatial approaches address parts of this problem, but their direct combination does not generally recover the appropriate interventional reference law because candidate reassignment jointly alters treatment likelihood, standardized residuals, and graph-dependent residual likelihood. This study presents GeoDose-CP, a support-aware conformal framework for localized stochastic potential outcomes under continuous or mixed continuous-atomic treatment. Its central methodological contribution is a graph-local target-orbit law that jointly represents intervention-induced treatment shift, the inverse outcome-scale Jacobian, and spatial residual dependence. The framework further provides exact weighted candidate inversion, a scalable sparse approximation with explicit discrepancy accounting, and refusal under inadequate support. Evaluation used controlled known-truth experiments, MineDoseBench, treatment-density sensitivity analysis, external conformal comparators, and a multi-mine New South Wales (NSW) study. In MineDoseBench, GeoDose-CP achieved mean selective coverage of 0.9692 across 27 configurations and a minimum local q0.05 of 0.8951; exact-sparse auditing produced nine inclusion disagreements over 2,700 targets. In the NSW study, the absence of an auditable longitudinal rehabilitation treatment rendered treatment-dependent inference nonoperational rather than forcing inference through a proxy exposure.

Audio-language models can produce confident answers unsupported by the audio, motivating uncertainty estimates that identify unreliable responses. We compare probability-based, sampling-based, self-verification, evidential, and contrastive measures across four open-weight models and five audio QA benchmarks. In multiple-choice evaluation, first-token measures are strongest overall, with top-1 probability achieving a mean AUROC of .740, compared with .708 for ten-sample discrete semantic entropy, while requiring no additional model calls. Across four benchmarks, shifting from multiple-choice to open-ended evaluation lowers mean accuracy from 57.6% to 36.6%, yet uncertainty remains predictive of errors: semantic entropy, maximum token entropy, and semantic agreement achieve mean AUROCs of .697, .694, and .693, respectively. To test whether uncertainty reflects the evidence available to answer the question, we perform input ablations that remove either the audio or the question. Across top-1 confidence, entropy, and sampling-based measures, removing audio reduces error-detection AUROC by .101 on average, compared with .010 when removing the question. Together, these results establish efficient uncertainty baselines and show that uncertainty in audio-language models depends substantially more on available audio evidence than on question text.

New words are invented every day. A human listener can learn a new word by hearing it clearly once and inferring its usage from sentence context. This paper proposes granting ASR a similar ability to learn the contextual representations and spellings of new words from unlabeled test data at test time. A frozen CTC acoustic model provides spellings, a frozen language model provides contextual evidence for out-of-vocabulary (OOV) word detection, and an adaptation module expands the vocabulary by learning the lexical token representations with distributions over CTC-generated candidates. The spelling model of each token is optimized by minimizing a Kullback-Leibler divergence (KLD) objective. We demonstrate that the CTC-weighted language model log likelihood ratio can be interpreted as the KLD between the unknown correct ASR and the unsupervised learned ASR, and that, using a Pinsker bound, the square root of KLD can be interpreted as an upper bound on the total variation distance between the true and estimated spelling of the unknown word. Experiments show relative OOV character-error-rate reductions of up to 14.97% on LibriSpeech and 6.67% on dysarthric Speech Accessibility Project data for recurring OOV words, relative to the corresponding rescoring system.

We introduce Forecast-Dojo, a replayable environment for benchmarking and training LLM forecasting agents. It combines resolved prediction-market questions with dated news, allowing agents to research an event and revisit their predictions at successive historical dates. The same tasks and tools support repeated evaluation, collection of training interactions, and feedback from recorded outcomes without waiting for new events to resolve. Forecast-Dojo contains 1,568 Polymarket events, split by time into training and evaluation periods, and 18.8M dated news articles. In an evaluation of 12 models, research tools lower Brier score for all 12. Forecasts also improve as events unfold, with the largest gains at steps where more newly dated evidence is recorded. Every model still trails historical market forecasts in both Brier score and accuracy. A belief notebook carried between dates lowers research cost but does not consistently improve forecast quality. Beyond evaluation, Forecast-Dojo provides interaction trajectories and outcome feedback for agent learning, with supervised fine-tuning as a proof of concept.

Long-running LLM applications repeatedly send growing context, making prefix caching critical for reducing prefill cost. Yet prefix-cache behavior under agentic workloads remains poorly understood. We study production traces from two companies and evaluate 14 eviction algorithms across HBM-constrained and large memory-pool settings. Despite a large gap to Belady, sophisticated policies designed for traditional caches provide little benefit over LRU. The reason is structural: prefix reuse is dominated by the regular pacing of active sessions, making recency unusually predictive. Prefix caching nevertheless introduces new challenges, including heavy-tailed session footprints and highly variable miss costs as attention computation grows with sequence length. We introduce the compute-savings ratio and two offline oracles to quantify these effects. Our results show that effective prefix-cache management should retain recency as its foundation while selectively adding quick demotion for one-hit prefixes, compute-aware partial eviction for expensive misses, and capacity-dependent eviction granularity. We will release the traces and simulator to support future research.

Neural fields for scientific tomography are optimized from 2D images, but the actual quantity of interest is often a latent 3D physical field. Because the forward map is many-to-one, low 2D image error need not certify a correct 3D field. Moreover, the latent field is not directly supervised during training, and its error cannot be evaluated against truth at deployment. We develop CoroNeRF to jointly optimize 3D electron density and temperature fields directly from multiview, multiline intensities through a differentiable atomic-emission renderer. Using solar coronal tomography as a controlled testbed, we evaluate physical-field recovery and test whether cross-seed instability provides a ground-truth-free-at-inference indicator of local physical-field error. We underscore the following two observations. (i) Image fidelity is not field fidelity: spectral ablations show that limited-channel reconstructions can fit their available observations well while recovering substantially worse fields, whereas evaluation on a common richer probe exposes the discrepancy. (ii) Cross-seed instability ranks local physical-field error across tested matched-model conditions, supported by sparsification and physical signal-strength controls. Seed-deviation projections provide complementary directional validation, but shared forward-model mismatch can still produce incorrect cross-seed consensus. These results characterize joint thermodynamic recovery and the usefulness and limits of seed-based error localization in a controlled, single-scene solar tomography testbed.

GPU acceleration is now routine across robotics, but cloud-hosted GPU continuous integration (CI) runners are expensive, resulting in severe under-testing of GPU-accelerated code. We present pytest-gpu-proof, an open-source pytest plugin offering a practical middle ground. Tests can be run on a local machine, signed with a receipt of exactly what ran and what it produced, and integrated into standard CPU CI workflows (e.g., GitHub Actions). The tool is open source and on PyPI, and we are actively integrating it across our lab's software stack.

Textual descriptions can reduce ambiguity in medical image segmentation by specifying the finding and location to be delineated. Existing text-guided methods mainly improve where image and language features interact but generally retain a single learned update pathway across all image-text pairs. We propose MRSeg, a parameter-efficient framework that uses each image-text pair to route the adaptation of visual and textual features before dense prediction. Frozen ConvNeXt-Tiny and PubMedBERT encoders provide multiscale visual features and clinical text tokens. A joint router uses the deepest visual feature and pooled text to predict a sparse mixture over low-rank adapter bases. The resulting route is shared across separate adapter banks for two visual scales and text, coordinating their adaptation while keeping the feature-specific parameters separate. Region Bridge uses text-derived queries to aggregate dense visual tokens into latent regions, refines these regions through self-attention and text cross-attention, and redistributes the refined information back to the feature maps. Finally, a multiscale decoder combines refined semantic features with shallow image evidence. On QaTa-COV19 and MosMedData+, MRSeg achieves 90.90/83.32 and 81.53/68.82 Dice/mIoU, respectively, with 7.11M trainable parameters and 7.60 GFLOPs. Code: https://github.com/maklachur/MRSeg.

Large language models are increasingly used as inexpensive judges to evaluate outputs, label data, and assess whether a system meets a desired quality standard. Yet using AI judgments for formal statistical inference is fundamentally different from simply treating them as ground-truth labels: AI evaluations can be biased or noisy, and rigorous hypothesis testing requires explicit control of type-I and type-II errors. We study how to use AI judgments, together with selective human verification, to conduct a valid hypothesis test at minimum cost. We consider a population of items with hidden binary labels. After choosing a fixed pool of items, the decision maker can selectively query AI, send an item directly to a human, escalate an AI-scored item to a human after observing the AI report, or stop once sufficient evidence has accumulated. We derive an information-theoretic lower bound that captures the minimum cost of achieving prescribed testing errors and characterizes the value of AI information and human verification through a report-dependent information frontier. Motivated by this characterization, we develop SCALE, a sequential cost-aware policy that combines selective AI scoring with adaptive human escalation. SCALE is valid at finite sample sizes and matches the lower bound to first order as the target error probabilities vanish. We further extend the framework to an unknown AI-output model using paired AI-human pilot data. Numerically, SCALE approaches Human-only or AI-only testing when one source clearly dominates, while achieving its largest savings when inexpensive AI judgments and selective human verification are both valuable.

Language-model agents increasingly answer questions over customer-relationship management (CRM) records, such as whether to qualify a sales lead. We identify a failure mode not addressed by a stronger model: when the context contains an assertion by a party with an incentive toward optimism - here the sales representative, a witness recorded in the CRM - the model treats the assertion as evidence and clears deals the company's own records deem unacceptable. Across 100 lead-qualification tasks from CRMArena-Pro, the representative asserts an acceptable timeline in every call and an acceptable budget in 76; on the 31 tasks where such an assertion contradicts the price list and installation policy, a model reading only the transcript clears the deal in 29 of 31 cases. The signature is consistent across seven models from four providers (misled on 87-97%); scale and explicit reasoning confer no resistance. Only 3 of 35 genuine failures involve no assertion: the failure is persuasion, not missing information. We contribute a diagnostic method rather than an architecture: (i) a bucket analysis that separates persuasion from information gaps, (ii) a same-information control showing that supplying the records to the model lowers strict accuracy from 41 to 18 while raising recall - precision collapses - and (iii) a compute-step control that holds extraction fixed and varies only who computes Budget and Timeline. The margin ranges from 42 points on an inexpensive model to 2-5 points on models that already compute correctly; on the strongest models the arms are within confidence intervals, so the pattern is a consistent direction and a soundness property, not a proved performance floor. We pre-specify a generalization test that returns a negative result, characterize the precondition (a policy exactly specified in the inputs), and release all evaluation artifacts.

Reproducing a machine learning paper involves most research steps, from installing software and debugging to running experiments, work that AI agents increasingly do. We introduce RECLAIM, a benchmark of 100 NeurIPS 2025 papers that can be rebuilt yearly from new conferences. For each paper we fix in advance the result to reproduce, what counts as a successful reproduction, and a GPU-hour budget. An agent must reproduce that result using the paper and whatever its authors released. What the authors released decides the difficulty tier. Run-tier releases include code, data, and weights; Retrain-tier releases lack weights, so the agent trains the model; Reimplement-tier releases lack code, so the agent writes it. A separate language model grades runs from logs and outputs rather than agents' reports. We run four agents once per paper; the best agent in each tier reproduces only 41% of Run-tier papers, 27% at Retrain, and 15% at Reimplement, where every agent does worst. Failed attempts use on average 29% of their budget, so most stop with budget left. The most common agent error is writing the method without checking any part against the paper's numbers, in 63 of 400 runs.

On-policy distillation (OPD) corrects a student on the responses it writes, but its signal is the teacher's next-token distribution: it tells the student what the teacher says but misses how it thinks. Latent supervision promises the missing part by aligning the student's latent states to the teacher's. Recent methods such as OPRD bring this signal into on-policy distillation. However, we observe two failures of this recipe when distilling Qwen3-4B and Qwen3-8B into Qwen3-1.7B-Base. Early gain, late collapse: latent supervision alone lifts MATH-500 accuracy from 25 to 46 in 10 steps, but subsequent training degrades performance down to 11 with no recovery. Better alignment, worse behavior: although the alignment metric steadily improves throughout this collapse, the most aligned model turns out to be the worst performing. Further analysis suggests a mismatch in how the latent signal is applied: layers paired by depth play different roles in the two models, so continued alignment may pull the student toward teacher states it cannot understand. To address this, we propose LastOPD, which applies the latent signal only at the last-layer state, the common interface both LM heads read, and only during a 10-step crossfade into token-level OPD. This keeps the useful part of the latent signal and hands the student to token-level supervision before the collapse sets in. Extensive experiments show that LastOPD improves MATH-500 over token-only OPD by 5.55 and 4.02 points with the 4B and 8B teachers, leads on most held-out datasets, and reaches the final score of token-only OPD in about half the steps. Code is available at https://github.com/Muyiiiii/LastOPD.

Blockchain and artificial intelligence (AI) are converging into a single infrastructural layer for securing data sharing, model integrity, and autonomous decision-making across distributed systems. This paper presents a meta-synthesis that draws together four constituent studies covering adversarial machine learning, AI-powered anomaly detection in cloud environments, automated vulnerability patching by multi-agent large language model (LLM) pipelines, and the broader landscape of securing AI systems across their lifecycle and situates their findings within the emerging literature on blockchain-enabled AI and autonomous AI agents. Each constituent study addresses a distinct point of failure in modern AI-driven security operations: the integrity of training data and model behavior, the reliability of real-time monitoring, and the trustworthiness of automated code remediation. We argue that blockchain's properties of immutability, decentralized consensus, and verifiable provenance directly address a gap common to all three: the difficulty of establishing trust in data, models, and autonomous agents that operate without a central authority. Building on real-world research on blockchain-secured data sharing, federated learning, and multi-agent coordination, we propose a layered reference architecture that couples adversarially hardened models, blockchain-anchored data provenance, AI-driven anomaly detection, and smart-contract-governed multi-agent remediation. We conclude by identifying open problems in scalability, privacy-transparency trade-offs, and the governance of autonomous agents that must be resolved before such integrated systems can be trusted in production-critical environments.

Online reinforcement learning fine-tuning of pretrained flow-matching vision-language-action (VLA) policies promises robots that keep learning after deployment, but continued updates often destroy competence on individual tasks while the aggregate still looks healthy. We study this failure mode, which we call task collapse, under a matched small-compute budget on LIBERO-10 with a 450M-parameter SmolVLA policy trained by PPO with stochastic (SDE) sampling. Three exploration-noise policies differ in one live variable: a fixed noise scale, a ReinFlow-style learned noise network, and an uncertainty-gated controller that redistributes exploration across task streams from task-agnostic novelty and competence signals, without task labels or episode boundaries. Under the pooled definition, fixed noise collapses tasks in two of three seeds and learned noise in every seed measured to iteration 200, while the controller collapses none in any of its three seeds. Measured parameter displacement shows the controller's action expert keeps changing, while its mean applied noise is close to the fixed scale in the available logs. The matched comparison supports the controller's effect on task preservation; the separate contributions of its adaptation across states and over time are not disentangled. A lower fixed scale slows the decline but does not stop it. No arm improves on the behavior-cloning baseline in this budget. Two properties of that regime are measured beside this result, not offered as its cause: following the reference recipe, training runs in bfloat16 with no fp32 master copy, under which 96.02% of the action expert's elements stay bit-identical across three consecutive iterations, and an fp32 master copy at the reference learning rate collapses both arms in a single-seed observation. We release tools measuring per-task collapse under four definitions, rescoring noise and instrument tares.

While various multimodal methods combining imaging and tabular data for Alzheimer's disease (AD) diagnosis were proposed, they are often limited in generalization across cohorts. In-context learning (ICL) has demonstrated excellent generalization performances and high flexibility in foundational tabular models such as TabPFN. To extend TabPFN's ICL to multimodal AD analysis, the main obstacle is that TabPFN is meta-trained on synthetic tabular priors that do not naturally match the statistical structure of image-derived features. We propose M$^2$PFN, an end-to-end framework that turns this tabular foundation model into a multimodal AD predictor. M$^2$PFN (i) performs differentiable inference through TabPFN's transformer, back-propagating task gradients into 3D-MRI and tabular encoders; (ii) aligns the two modalities into a shared subspace, via disentanglement and a contrastive objective, matched to the ICL engine's prior; and (iii) folds in a frozen tabular-only prediction through a learnable gated shortcut. Because the ICL engine stays frozen, its in-context mechanism is preserved for test-time generalization, while end-to-end training shapes the encoders into features it can exploit. On ADNI ($n=2240$, three-class CN/MCI/AD), M$^2$PFN attains $65.55\%$ macro-F1 and $82.21\%$ macro-AUC, surpassing a comprehensive set of unimodal and multimodal baselines. By swapping only the head for a TabPFN regressor, the same architecture regresses baseline MMSE on a $1250$-subject sub-cohort to test MAE $1.743$, outperforming every multimodal baseline. On two external cohorts (OASIS-3 and SCAN) with no retraining, M$^2$PFN achieves the best AUC and the lowest MMSE MAE across all baselines, and transfers even when the cognitive instrument changes.

Reconstruction-based unsupervised learning can fail in two opposing ways: a model may reconstruct anomalies too accurately or discard valid nominal variation. Using the Pursuit of Subspaces hypothesis, we characterize these failures through the meet, union, and join geometries induced by the nominal components. Excess learned range produces join blindness, while insufficient capacity produces meet preference and loss of nominal fidelity. We show that the compact nominal union is optimal among nominal faithful ranges and generally requires a nonlinear reconstruction map. Based on this geometry, we introduce Dynamic Push and Pull, which learns from controlled perturbations without anomaly labels, and nested manifold carving, which applies the same principle recursively in latent space. Experiments confirm the predicted changes in latent geometry across every tested Push and Pull configuration. The proposed methods improve reconstruction-based anomaly detection across standard benchmarks and unseen image degradations, while also improving pretrained ECG representations for downstream classification. These results connect reconstruction failures to identifiable geometric conditions and provide practical mechanisms for learning compact representations.

Machine translation (MT) for Indian languages remains constrained by the limited availability of high-quality, Indic-centric parallel corpora and evaluation benchmarks. Existing multilingual resources are largely constructed from English-pivot content and often fail to capture the linguistic diversity, cultural complexity, and domain-specific characteristics of Indian languages. We present COILD, an Indic-centric parallel corpus comprising over 1.16 million human-translated and human-verified sentence pairs, covering 20 Indian language pairs across the Indo-Aryan, Dravidian, Tibeto-Burman, and Austro-Asiatic language families. The corpus is built entirely from original Indian language sources collected from licensed repositories spanning eight domains with direct real-world applicability. Furthermore, we introduce a domain-centric benchmark comprising 2,000 expert-verified sentences to enable consistent multilingual and cross-lingual evaluation across Indian language pairs. To validate the effectiveness of COILD, we fine-tune two representative multilingual neural machine translation models, IndicTrans2-Distilled and NLLB-200. Experimental results demonstrate consistent improvements across language pairs, domains, automatic evaluation metrics, and human evaluation, highlighting the effectiveness of high-quality Indic-centric supervision. COILD provides a valuable training and evaluation resource for advancing multilingual machine translation and future multilingual language models for Indian languages.

Variadic generics are a powerful tool for type-safe meta-programming. Yet in most widely used languages, they remain an "expert-only" feature due to their reliance on complex patterns such as recursive decomposition or expansion expressions that do not compose naturally with ordinary control flow. In C++, for example, accessing elements of parameter packs has traditionally relied on unintuitive recursive patterns that "peel off" elements. This paper presents Pack Iteration, a feature introduced in Swift 6.0 that allows developers to iterate over parameter packs using a familiar, imperative for-in loop. By treating pack expansion as a first-class source for iteration, Swift bridges the gap between high-level expressiveness and advanced generic programming. We detail the design and implementation of this feature within the Swift compiler, focusing on the challenges of bridging static type-checking in the constraint system with dynamic execution in the Swift Intermediate Language. Unlike traditional models that expand packs at compile time, Swift's implementation supports on-demand evaluation, enabling efficient dynamic iteration and short-circuiting control flow. Our empirical evaluation confirms that pack iteration provides performance comparable to - and sometimes significantly better than - the complex workarounds previously required.

Generalization in robotic manipulation requires policies to perform tasks across diverse unseen object instances that vary in shape, size, and pose. However, conventional behavior cloning (BC) methods often overfit to instance-specific geometry and appearance, limiting transfer to novel objects. We introduce KeyGen, a framework that learns canonicalized semantic 3D keypoints from point clouds and uses them as structured object-centric representations for policy learning. A visuomotor diffusion policy conditions on these keypoints together with object-centric geometry to predict full manipulation trajectories, enabling consistent geometric correspondence across object instances. To evaluate category-level generalization, we construct a photorealistic simulation benchmark with three manipulation tasks and a planning-driven data generation pipeline that produces expert trajectories across diverse object instances. Experiments show that KeyGen significantly outperforms prior methods on both seen and unseen objects under pose variation, scales effectively with additional demonstrations per object, maintains robustness to object rescaling, and achieves strong performance in both simulation and real-world manipulation.

MultiLevel software Modeling (MLM) suggests that conceptual modeling in broad subject domains might require abstraction of multiple classification levels. The MLM approach relies on philosophical arguments, claiming that faithful modeling of real-world domains involves repeated type classification as in ontologies of natural kinds. MLM leveled architecture is interwoven and defined by instance-of interlevel relationships between clabject classes in lower levels to classes termed category classes, in upper levels. The instance-of relation denotes membership of clabjects as type objects in their (powertypes) category classes, and is not transitive. All MLM approaches support forms of deep characterization, i.e., category classes can influence classes in lower levels. Deep characterization is an essential feature of superclasses and contradicts the non-transitive membership meaning of instance-of. In this paper, we introduce the Category-Based MLM (CatMLM) model, in which category classes have dual superclass and powertype facets, based on the distinction between category features that do not participate in deep characterization, and object features that do. This distinction clarifies the role of levels, provides a clear quantifiable criterion for leveling, and yields a decision rule between the subclass and instance-of relations. The contribution of this paper is to introduce a well-defined MLM model that (1) is based on simple, quantifiable level decisions; (2) clarifies how leveling emerges from domain needs; and (3) analyzes gains and losses of MLM vs. plain OO modeling.

Mechanistic interpretability seeks to make verifiable statements about the internal behavior of large language models (LLMs). Many interpretability techniques struggle to scale with the increasing size and depth of architectures. Our solution to this is to introduce smaller models with structures that lend themselves to interpretability. In this work, we introduce the Stream Recursion Model (SRM), a modification of the Hierarchical Reasoning Model (HRM) designed to expose internal computational structure while remaining scalable. SRM organizes computation into multiple interacting latent streams that are updated through recursive refinement, enabling direct analysis of stream dynamics, causal contribution, and routing behavior. SRM achieves performance comparable to GPT-2 on a per-parameter basis. Our analysis reveals consistent and distinct behavior across streams, indicating structured specialization and interaction. These results suggest that SRM provides a practical architectural foundation for scalable mechanistic interpretability and opens up promising avenues for future research in both reasoning performance and interpretability.

Full-duplex dialogue systems, which listen while speaking, must distinguish a completed turn from a pause within a turn and an interruption that requests a turn from a brief acknowledgment or speech addressed to a third party. Yet existing conversational corpora provide limited control over these events and limited labels for their intent. We present a pipeline for synthesizing intent-labeled, two-channel conversational speech from relational event lists. An LLM authors each event's speaker, text, conversational act, and attachment to an earlier event without predicting absolute timestamps. Events are synthesized independently, aligned with their source text, and placed on a shared clock, so turn-taking landmarks are measured from the rendered signal while silence durations are specified or sampled from turn-taking distributions. The pipeline covers 42 phenomena across eight families in English and Mandarin, derives frame-level system actions from authored intent, and promotes diversity using small, diverse sets of prior examples and batch prompts that request alternatives with self-reported probabilities. Ablations show gains in each targeted diversity dimension. On a four-action label space for taking, holding, releasing, and not holding the conversational floor, a semantic voice-activity detector using only current and past audio reaches start-speaking and start-listening F1 scores of 0.819 and 0.802. When generating its own responses, the full-duplex speech model Moshi takes 0.85 of the reference turns after fine-tuning on the generated corpus, compared with 0.44 before fine-tuning. Its frame-level precision for predicting system-floor occupancy rises from 0.46 to 0.88. With reference context at each step, its frame-level floor F1 rises from 0.893 to 0.962. These results show that controlled synthesis can provide learnable and transferable supervision for full-duplex turn management.

Current automated gait analysis for clinical applications relies on uninterpretable black-box classifiers. Although Vision-Language Models (VLMs) offer strong reasoning capabilities, applying them directly to gait videos often leads to hallucinations, because they struggle to measure subtle geometric deviations from raw visual contexts. To address this, we introduce DrGait, a training-free agentic framework that shifts the VLM's role from a direct visual reasoner to a clinical planner. DrGait decouples semantic reasoning from geometric perception through a structured Triage-Verification-Synthesis (TVS) workflow. Given an input video and a set of basic spatiotemporal metrics, the DrGait agent first performs a heuristic triage to propose diagnostic hypotheses, which are then verified by autonomously calling deterministic biomechanical tools that operate on reconstructed 3D mesh trajectories, segmented 2D pose tracks, and event-centered video evidence. Finally, a closed-loop mechanism recursively updates the agent's reasoning context based on the feedback. By anchoring VLM's reasoning in verifiable geometric and temporal measurements, DrGait reduces hallucinations, achieving competitive diagnostic accuracy while generating transparent and audit-ready clinical reports.

Mapping the distribution of traffic dynamics at high spatiotemporal resolution is a fundamental question in transportation research. Distributed acoustic sensing (DAS), an innovative seismic observation tool, emerges as a promising solution for real-time urban traffic monitoring at high spatial and temporal scales. Distributed acoustic sensing repurposes existing underground fiber-optic cables as dense, continuous sensor arrays, enabling passive and privacy-preserving monitoring of roadway traffic activity at meter-level spatial and second-level temporal resolution. This study examines whether integrating DAS and deep learning models can serve as a continuous and efficient urban traffic observatory for revealing urban traffic dynamics (i.e. traffic volume and congestion, event-driven changes) at high spatiotemporal resolution. Using a DAS deployment along a roadway network in the City of College Station, Texas, USA, this study develops a deep learning-empowered analytical framework that converts raw ground vibration waveforms into spatiotemporal representations, detects vehicle trajectory, and infers traffic states from aggregated traffic volume and speed. A hybrid training strategy combining synthetic and manually annotated DAS images is used to improve vehicle detection under noisy and congested conditions, with model outputs further aggregated to characterize system-level traffic dynamics.

Robust average-reward Markov decision processes provide a fundamental framework for long-term performance optimization under uncertainty, and can have optimal long-run rewards that depend on the initial state. This state dependence requires a vector Bellman theory that accounts for both recurrent-class rewards and transition uncertainty. We develop such a theory for finite models with compact, post-action $(s,a)$-rectangular ambiguity. A gain-first, bias-second optimization principle yields a coupled vector gain-bias system, and every finite solution identifies the optimal robust gain and supplies stationary saddle strategies against history-dependent opponents, simultaneously from all initial states. We further characterize solvability through stationary gain conditions and a uniform bound on canonical transient corrections, and give sufficient conditions that permit distinct recurrent-class gains. The certificates also yield asymptotically affine trajectories of the robust Bellman operator, based on which we design a robust approximately shifted Halpern planning algorithm. Under finite Bellman solvability, the gain estimates and Bellman displacements converge to the optimal gain vector, and every extracted greedy controller is average-optimal after a finite, instance-dependent budget. These results thus connect finite Bellman certificates to undiscounted planning for state-dependent robust average rewards, providing theoretical understandings.

In this paper, we investigate how script knowledge is distributed across the layers of LLMs using two complementary interpretability methods: logistic regression probing and logit-lens analysis. Our probing experiments reveal a clear asymmetry: both the input script and the instructed output script are encoded in the earliest layers of the network, while, in contrast, commitment to the actual output script emerges only in the final layers, with the model's intermediate representations defaulting to Latin throughout most of the layers. This two-stage process is confirmed by logit-lens analyses, which show that script commitment consistently occurs at the very last layers of the LLMs. Together with the weaker script-following performance observed in smaller models, these results form a converging body of evidence linking script commitment to model depth, with broader implications for the design of sufficiently deep, inclusive multilingual architectures.

In scientific machine learning, $Δ$-learning trains models on residual errors relative to physical baselines, assuming that more accurate baselines with smaller residual scales inherently improve downstream performance. Here, we demonstrate that residual scale alone is an insufficient heuristic for learnability. Evaluating molecular graph neural networks on total energy targets, we show that complex local descriptor baselines can yield small residual targets that are disproportionately rough within architecture-informed proxy spaces and harder to learn relative to their scale. Conversely, semi-empirical baseline reduces both scale and normalized roughness, improving in-domain and out-of-domain prediction. We introduce scale-normalized graph Dirichlet roughness ($D_{\text{IQR}}$) as a pre-training diagnostic for residual learnability and establish baseline complementarity as a core target-design principle, elevating target space formulation alongside model architecture as a key axis for scientific machine learning.

Audio-language models (ALMs) can exploit textual shortcuts to answer questions while overlooking acoustic evidence, weakening audio understanding. On-policy distillation (OPD) trains compact ALMs by supervising student-generated responses with teacher predictions, but does not explicitly distinguish acoustic support from linguistic predictability. We propose Reward-Tilted On-Policy Distillation (RT-OPD) to strengthen acoustic grounding. Given the same question and student-generated text, a frozen teacher predicts the next token with and without audio inputs. Their log-probability contrast defines a reward that reshapes the teacher distribution for reverse-KL distillation, emphasizing the additional evidence provided by audio. Across two compact students and three benchmarks, RT-OPD consistently outperforms Vanilla OPD. Experiments with silenced and replacement audio further suggest that RT-OPD strengthens the student's reliance on acoustic evidence. Our 3B model achieves 72.72% accuracy on MMAU, the highest among the compared 3B models and competitive with several 7B and 8B models. Code and model checkpoints are available at https://github.com/KaiyangLi1992/RT-OPD.

We propose a framework that learns cross-task relationships in multi-task models by approximating the joint distribution of task labels through targeted pairwise relationships. This approach improves performance via transfer learning and enhances information extraction without the intractable complexity of modeling the full joint space. Although our framework applies to any multi-task system, we demonstrate its efficacy within YouTube's production recommendation systems. Experiments across the Notifications, Homepage, and Watch Next surfaces show improvements in both accuracy and user satisfaction metrics. Finally, we propose a workflow template to facilitate broader future implementation.

Ultrasound imaging increasingly targets portable, point-of-care, and wearable settings where constraints on power, bandwidth, and hardware complexity often necessitate sparse data acquisition in spatiotemporal scanning. However, image reconstruction using the sparse data can introduce insufficient phase information in coherent beamforming process, resulting in grating-lobe artifacts that degrade imaging contrast resolution. We present a physics-guided, data-driven framework for sparse-to-dense radio-frequency (RF) reconstruction that aligns training with downstream image formation. Our approach trains an end-to-end interpolation network using a hybrid supervision scheme that combines an RF-domain and a beamforming-domain loss with exponential moving average (EMA) to stabilize the multi-objective training. To improve generalization under variable acquisition layouts, we also introduce a random-skip masking strategy that varies sparsity patterns during training so a single model can handle diverse decimation factors and irregular channel configurations. We evaluate the framework on a held-out test set using the mean structural similarity index measure (SSIM) between reconstructed and ground-truth beamformed images. Across decimation factors $\times 2$ to $\times 13$, the best-performing configuration maintains mean SSIM around 0.95. Overall, the results show consistent gains in RF reconstruction and post-beamforming image quality across diverse acquisition conditions. This approach enables robust, high-quality ultrasound imaging at resource-constrained settings by allowing more sparse scanning in spatiotemporal domain.

Large language models (LLMs) have demonstrated strong capabilities in financial analysis and reasoning, inspiring recent advances in agent-based trading frameworks. While these systems show promise, prior approaches either emphasize long-horizon forecasting or operate as stateless analyzers, limiting their applicability to the demands of trading in complicated settings. To address these gaps, we introduce META (Memory Enhanced Trading Agent), the first RAG-like episodic-memory-augmented multi-agent framework for financial decision making. META integrates a family of specialized indicator agents (e.g., Trend, MACD, Stochastic, RSI, SMA, AVWAP, Heikin-Ashi) with a Decision Agent that fuses their reports, and a Memory module that retrieves and updates past trading episodes encoded as market state embeddings with outcomes and reflections. By recalling relevant experiences and adaptively reweighting signals under similar market regimes, META achieves improved directional accuracy and robustness under short-horizon evaluation. Our results demonstrate that episodic memory provides a powerful mechanism for regime-aware, interpretable, and low-latency decision-making in trading and decision making. The code of this project is released on GitHub.

Reinforcement Learning with Verifiable Rewards (RLVR) performs well on problems with clear rewards, such as mathematics and coding, but whether it also works where the reward is less clear remains open. The reason-over-search recipe applies RLVR to open-domain question answering, where retrieval grounds the answer and a match against the reference supplies the reward. So far it has been demonstrated on large models, and below one billion parameters only with distillation from a larger teacher. We test the recipe on a small model. We train Qwen3.5-0.8B with Group Relative Policy Optimization (GRPO) and an interleaved Wikipedia-search tool on MuSiQue, varying only the reward across three shapes over three seeds each, and we evaluate every checkpoint held-out on a seven-benchmark question-answering suite. The recipe works: the best run reaches 0.352 average exact match against a 0.092 untrained floor, a 3.8-fold gain, with no distillation step in the training loop. The reward shape also matters. The Search-R1-faithful exact-match-only reward is the worst of the three at every seed at the matched training horizon, and it is worst even on exact match, the metric it directly optimises. We conclude that the sparse exact-match reward, RLVR's default in mathematics and code, is the wrong starting point for models of this size. The reason-over-search setting can supply a suitable reward for RLVR on small models, but small-model RLVR needs its own reward-design study rather than a scaled-down copy of a large-model recipe.

We design, implement, and evaluate KathDB-FAO, a new query evaluation subsystem for our KathDB multimodal DBMS. KathDB-FAO takes as input a query in natural language (NL) and converts it into a query execution plan where each operator is a function whose body is synthesized during query evaluation, which allows powerful query-specific optimizations. To generate accurate and efficient plans from NL, KathDB-FAO first extracts fine-grained atomic actions for correctness, then establishes contracts on the inputs and outputs of those actions and groups them for efficiency, and finally synthesizes the function for each group on the fly. On SemBench, KathDB-FAO cuts execution cost by 58.8% on average across scenarios compared with the next best system, at comparable or better quality.

We describe our submission to the Unsupervised Speech in the Wild (UPS) Challenge at Interspeech 2026, a bidirectional Mamba-2 (BiMamba2) encoder trained with masked discrete-unit prediction following the HuBERT-style paradigm. The 47.88M-parameter model is trained on 250 hours of speech across 67 languages from the MLCommons Unsupervised People's Speech dataset, with no labeled data. The objective combines masked k-means pseudo-label prediction with language identification supervision and VICReg regularization. On official evaluation, the system achieves an Adjusted Rand Index of 0.735, exceeding four baselines on speaker clustering. Language identification macro-F1 (0.073) and character error rate (0.870) remain below supervised baselines. We analyze a local-official discrepancy in metric scale and checkpoint ranking, highlighting limitations of in-distribution diagnostics for predicting Dynabench probe outcomes.

An estimated 1 billion people worldwide live with vision impairment, yet current vision-language models (VLMs) produce descriptions too vague for safe navigation by blind and low-vision (BLV) users. Large VLMs can generate high-quality audio-description-compliant narrations but cannot run on mobile devices; small VLMs offer competitive latency but lack spatial detail, directional cues, and hazard awareness for navigational assistance. We present Smol-VL-BLV, a compact VLM for blind and low-vision users that closes this gap using a 500M decoder transformer model and two post-training mechanisms: (1) teacher-student distillation and (2) Group Relative Policy Optimization (GRPO) with a composite BLV reward targeting directional language, metric distances, and hazard detection. Because multi-stage post-training can induce catastrophic forgetting, we add a lightweight finetuning stage after the last stage GRPO finetuning to recover general descriptive quality while preserving BLV-specific spatial grounding. Our best model substantially outperforms the baseline across various benchmarks, including tasks: VQA, BLV captioning, OCR, and latency. Compared with the baseline for relative improvement, it improves the Spatial score gain of 19.3%, and the Social score gain of 14.8%. It also increases OCR-Bench by 101.5%, and raises TextVQA accuracy by 44.2%. These results show that BLV-focused post-training improves both accessibility-specific spatial grounding and general visual-text reasoning. Deployed on a mid-range Android smartphone via Mixed-Precision Quantization, the model remains approx. 450 MB and runs entirely on-device, offline and without network dependency, generating descriptions with latency dependent on host hardware capabilities. Our model, dataset, and code is publicly released at https://smol-vl-blv.github.io/Smol-VL-BLV-website/

Deep clustering is a powerful approach for discovering meaningful structures in high-dimensional data by learning a low-dimensional latent representation prior to clustering. Despite its empirical success, assessing the statistical reliability of the resulting clusters remains challenging. Testing discovered clusters on the same data induces selection bias and invalidates classical $p$-values. Selective inference (SI) provides a principled framework for correcting this bias, but existing methods focus on clustering performed directly on the observed features. In this work, we develop an SI framework for deep clustering with a fixed pretrained encoder. The key challenge is that cluster assignments are determined through a nonlinear transformation from the original data space to the latent space, resulting in a substantially more complex selection process than in conventional clustering. Our method provides a computationally tractable way to account for this process and enables valid statistical testing of differences between clusters identified in the latent space. Synthetic experiments demonstrate that the proposed method controls the Type I error rate while achieving higher power than valid but conservative baselines, and genomic applications show that it can identify significant cluster differences while appropriately accounting for selection bias. Our framework provides a principled approach to quantifying the statistical reliability of structures discovered by deep clustering.

Existing state-of-the-art static taint flow analyses for imperative programming languages can scale to large applications by using precise user-provided taint flow models of library methods. However, manually and precisely modeling a method's taint flows is tedious and potentially unsound. Furthermore, automatically modeling the method via an inter- procedural taint analysis can be inefficient. To solve this problem, we propose a guess-and-check approach: (1) an LLM agent that generates a precise taint flow model of a method and (2) a symbolic algorithm to check the soundness of the model. The algorithm deduces which taint flows must not occur in the method for the LLM's taint flow model to be sound, and uses lightweight static analyses (e.g., type system and pointer analysis) to prove these must-not-flows. When these analyses are insufficient, the algorithm deduces maximally-general callee models and recursively verifies their soundness, avoiding a full inter-procedural taint analysis in most cases. Since a more precise model requires fewer must-not-flows to be verified, the precision of the LLM's model directly determines the efficiency of our approach. We evaluate our approach on 97 LLM-generated taint flow models for methods in 6 large Go codebases and prove the models sound for 93% of the methods they cover. The proven-sound LLM-generated models are also precise, resulting in no new false-positives when proving taint flow properties.

Diffusion models have shown strong potential for kilometer-scale precipitation downscaling, but their performance in geographically unseen regions and event regimes remains insufficiently understood. Building on the wavelet diffusion model (WDM) framework, this study evaluates cross-region and cross-event generalization. Six 3 x 3 deg U.S. regions represent convective, winter, tropical, and atmospheric-river precipitation regimes. Low-resolution inputs are generated by block averaging NOAA Multi-Radar/Multi-Sensor (MRMS) composite reflectivity fields. A WDM trained only on Oklahoma (OK) samples and a WDM trained on all six regions are compared with nearest-neighbor and Bicubic interpolation. Model performance is evaluated using three metric families that measure image-domain reconstruction, spectral and distributional fidelity, and bin-wise precipitation detection. The OK-trained WDM remains competitive outside OK. Although the all-region WDM delivers the best and most consistent overall image-domain and detection performance, its gains are uneven across precipitation intensities. Bin-wise critical success index (CSI) over 5-dBZ reflectivity bins shows that WDM improvements concentrate in localized higher-reflectivity structures, which image-domain metrics partly obscure. In addition, the performance differences among samples are strongly associated with the spatial organization of the precipitation field, quantified by Moran's I as the spatial autocorrelation of each reflectivity bin. The sample-level Moran's I-CSI correlation stratified by sample intensity reaches 0.901 in all six regions, including regions unseen during training. Overall, these findings support future efforts to transfer downscaling models to regions with limited local training data and to generate globally consistent, high-resolution precipitation products.

A language model's confidence in an answer is often read as a proxy for how well it knows the corresponding fact. This manual documents an open toolkit built to test that reading directly: a small causal language model is fine-tuned on a corpus that consistently asserts one fabricated arithmetic answer for each of the 81 single-digit addition pairs, and its post-fine-tuning confidence in each fabricated answer is compared against its own pre-fine-tuning confidence in the corresponding true answer, using an unchanged measurement procedure throughout. We describe and justify every pipeline stage, fact-space generation, token-length-aware confidence measurement, baseline validation, corpus construction, fine-tuning, and paired before/after comparison, together with the confound each is meant to rule out, among them tokenization asymmetry between single- and double-digit answers and the difference between an answer merely losing its edge and one being actively suppressed. This manuscript is a methodological and implementation reference: it documents the instrument and does not report or interpret the outcome of any specific run. The toolkit and its pinned dependency environment are archived separately (Section 9) under a persistent identifier, to be cited as an instrument by work that produces and interprets empirical results with it.

Automatic speech recognition models are audited for demographic fairness at full precision, yet the models that ship to production have been quantized, pruned, and distilled. We ask whether post-training weight compression, which alters model weights rather than the audio signal or its feature representation, redistributes error burden across demographic groups. Across the Whisper family on Fair-Speech, Common Voice 25, and AfriSpeech-200, 50% Wanda pruning of Whisper-large-v3 sharply widens the Black/AA-vs-Asian temporal-taxation differential on Fair-Speech: the absolute word-error-rate gap between the worst- and best-served groups more than doubles; at an assumed cost of five seconds of correction effort per transcription error this is a rise from 30 to 64 seconds of correction time per minute of speech. This +111% relative increase is invariant to the assumed per-error cost, survives an audio-quality control, and is only partly mitigated by beam-search decoding, which still leaves an +86% increase. At edge model size, INT4 HQQ quantization compounds catastrophic transcript loops on West African accents by factors of five to seven. Distillation, by contrast, narrows demographic gaps in 21 of 27 evaluated settings (teacher-student pair, precision, and dataset), with the exceptions concentrated on a single model pair. We cast the temporal-taxation construct of Choi and Choi (2025) as a quantitative metric, and show that single-snapshot fairness audits on full-precision models do not capture the deployment-time burden that compression places on already-marginalized speakers.

Biological agents do not learn under conditions of unlimited computation. For humans, learning and choice are shaped by constraints on perception, attention, and working memory, which limit how much state information guides behavior and therefore bound policy complexity. Standard reinforcement learning models typically optimize reward without explicitly representing these internal costs, making them less suitable as models of biological intelligence. We derive MI-SARSA, an on-policy temporal-difference algorithm that incorporates mutual-information regularization through a learned marginal action prior and a penalty on state-specific deviations from that prior. This yields a sequential learning model in which state information is used selectively when its expected return benefit justifies the added informational cost. Critically, the same state-specific information cost that governs policy compression also generates trial-level predictions for reaction time, distinguishing MI-SARSA from most reinforcement learning models, which predict choices or returns but not latency. Empirically, MI-SARSA produces a reward-complexity tradeoff, and stronger information penalties produce simpler policies with lower control costs and faster reaction times. Under environment shift, increasing regularization reduces post-switch performance degradation but also lowers asymptotic return, revealing a robustness-capacity tradeoff. Together, these results position MI-SARSA as a model of bounded sequential learning under cognitive constraints.

The ongoing digital transformation of work, administration, health, mobility, and social interaction is profoundly reshaping everyday life, steadily shifting control from individuals to large platform providers. Although data is often labeled the "gold of the 21st century", its real value is realized through services that access, combine, and exploit it. Today, individuals have little sovereignty: life events (e.g., changing an address, insurance, job, or marital status) require fragmented, repetitive interactions across numerous systems, leaving users overwhelmed rather than empowered. We argue for a fundamental rethinking of this situation and propose a virtual, trustworthy platform, called "MyVirtualME" that acts on behalf of the human individual towards companies, administrations, and other actors. This platform centers services, data, permissions, and data usage around humans, not foreign actors, allowing genuine control and transparency. Our vision goes beyond a pure data focus: supported by trusted services ranging from basic notifications to intelligent assistants, MyVirtualME aims to reduce digital bureaucracy, improve and even automate interactions, and support informed oversight of an individual's health, financial, and administrative situation. We firmly believe that a human-centered MyVirtualME is essential for restoring personal sovereignty in our digital future.

Contextual biasing improves rare-word recognition in speech large language models (SpeechLLMs), but efficiently exploiting large bias lists remains challenging. We propose PTC-Bias, a two-stage framework based on phoneme-level temporal competition. At the prefill stage, PTC Retrieval performs frame-synchronous phoneme decoding and temporal competition among candidate pronunciations, producing a compact bias-word shortlist and corresponding speech intervals. After SpeechLLM decoding, PTC Correction conducts a second local competition between the retrieved candidates and mismatched transcript spans within these intervals. Selective correction reduces near-homophone and word-segmentation errors while preserving correct transcriptions. Both stages share the same phoneme posteriors and require no additional SpeechLLM forward pass. Experiments on LibriSpeech show consistent gains across two SpeechLLMs and bias lists of up to 2000 words. With Prompt-SLAM-ASR-7B and 2000 bias words, PTC-Bias reduces B-WER by 23.4%/23.9% relative to CTC-Filter on test-clean/test-other, while keeping U-WER nearly unchanged.

Machine learning-based Network Intrusion Detection Systems often report near-perfect performance on IoT benchmarks. However, whether these models learn generalizable attack behavior or exploit spurious dataset shortcuts- such as static testbed IP/MAC addresses and chronological recording artifacts-remains an important question. We evaluate the CyberFlowIoT-GICAP benchmark, containing 3,617,388 flow records across 126 PCAP sessions with 849,395 benign flows. Four learning paradigms are evaluated across four feature configurations using PCAP-disjoint splits; LightGBM is additionally evaluated using conventional random-flow splitting. When only statistical flow behavior is used (Fbehav), LightGBM (92.58% +/- 8.18%), Random Forest (92.59% +/- 8.18%), and Deep MLP (92.55% +/- 8.18%) achieve nearly identical Macro-F1, indicating that performance is constrained by feature representation rather than model complexity. With raw timestamps (Ftstamp), tree-based models reach 99.28% Macro-F1, while the linear model remains at 90.62%, showing that nonlinear models can exploit dataset-specific temporal structure. Attack detectability is highly asymmetric: high-rate and active attacks maintain >99.8% recall from flow behavior alone in nonlinear models, whereas the DNS Beaconing drops from 27.78% to 0.00% recall when contextual features are removed. Conventional random-flow splitting increases attack recall by up to 14.00%, highlighting the effect of placing flows from the same sessions in both training and test sets. We conclude with a 4-point protocol checklist for realistic IoT NIDS evaluation.

While Federated Learning (FL) has been widely adopted for protecting user privacy in machine learning, it remains vulnerable to various robustness challenges, including performance-impairment risks, information-stealing threats, and aggregation vulnerabilities. This work offers a holistic synthesis of FL robustness along three tightly coupled angles: (i) a threat-centric view of robustness that categorizes the multifaceted attack surfaces, (ii) a structured taxonomy of robust aggregation strategies distinguishing outcome-centric approaches from security-centric strategies, and (iii) a layered taxonomy of defensive strategies. We rigorously examine current evaluation practices for FL robustness and identify major applications and open research challenges to guide future research.

We study Bayesian linear bandits with an isotropic Gaussian parameter, independent Gaussian candidate arms, and Gaussian reward noise when the horizon is proportional to the dimension. The normalized posterior uncertainty has an explicit limit that is uniform over all causal policies. Gaussian posterior identities then determine the limiting parameter overlaps without an assumed closure of the adaptive recursion. These results yield exact regret curves for Thompson sampling, posterior-mean greedy selection, and a family of policies that scale the posterior sampling covariance. The normalized realized cumulative regret converges in L1, uniformly on compact proportional-time intervals. A policy-uniform lower bound identifies the limiting optimal Bayes regret and proves that posterior-mean greedy selection attains it. Thompson sampling incurs a strictly larger leading regret; its instantaneous regret ratio relative to greedy selection lies between one and two and approaches two at long proportional horizons. Closed-form cumulative curves also identify a different comparison in the vanishing-noise limit. Finally, the instantaneous regret converges to a nondegenerate Gaussian decision-loss distribution, rather than to its mean. The analysis separates the amount of information acquired by a bandit policy from the quality of the decisions made using that information.

This paper investigates temporal neural networks for \mbox{end-effector} position \mbox{estimation} of an aerial continuum manipulator (ACM) operating under aerodynamic effects induced by the unmanned aerial vehicle (UAV). An experimental dataset is collected under stationary (\mbox{rotor-off}) and \mbox{free-hovering} conditions across continuum robot (CR) configurations and UAV altitudes, providing \mbox{end-effector} position measurements with and without aerodynamic residuals. To establish a nominal framework, \mbox{strain-parameterized} kinematic models with progressively richer strain bases are evaluated to balance model complexity and prediction accuracy. The selected nominal model then serves as the baseline for 3D position residual estimation using a \mbox{closed-form} \mbox{continuous-time} (CfC) neural network, with a multilayer perceptron (MLP) and a gated recurrent unit (GRU) used for comparison. On unseen test experiments, the CfC achieves an RMSE of \(22.00\pm1.70~\mathrm{mm}\) over five random seeds, compared with \(36.38\pm3.58~\mathrm{mm}\) for the MLP and \(27.72\pm2.92~\mathrm{mm}\) for the GRU, corresponding to reductions of \(39.52\%\) and \(20.62\%\), respectively. These results demonstrate the effectiveness of \mbox{continuous-time} learning for \mbox{end-effector} position estimation under aerodynamic disturbances relative to static and \mbox{discrete-time} learning methods.

Self-supervised learning (SSL) countermeasures (CMs) have shown strong performance in recent years. However, they often show degraded performance while facing unseen spoofing attacks and mismatched conditions. This study examines the Voxtral audio-language model (ALM) framework for spoofing detection, as a step toward combining CM capabilities within the ALM framework. We analyze how Voxtral captures spoofing cues through audio-text processing and propose an instruction-guided approach that uses label-sequence likelihoods to evaluate bonafide and spoofed speech. Experiments on the ASVspoof databases show that without task-specific adaptation, the LLM layers emphasize semantic representations, reducing the separability of spoof-discriminative acoustic cues compared to the Whisper-based audio encoder. Consequently, spoofing-related information becomes less separable after language-model processing. We also applied lightweight adaptation using weight-decomposed low-rank adaptation (DoRA) to the Voxtral model and propose the Spooftral model, achieving an equal error rate (EER) of 4.25% on the ASVspoof5 evaluation set.

Hate speech on social media poses serious risks to social harmony, mental well-being, and public safety, making its timely and accurate detection essential for content moderation systems. Most existing studies focus on binary classification, evaluated their frameworks on a single dataset, and provide limited insight into how decisions are made, which limits their real-world applicability. In addition, limited work is done on the explainability of their predictive inference. To address these challenges, this study proposes a multilevel and explainable hate speech detection framework. The proposed model integrates DistilBERT (Distilled Bidirectional Encoder Representations from Transformers) embeddings with a Bi-LSTM (Bidirectional Long Short-Term Memory) model, and an attention mechanism to capture both contextual meaning and sequential dependencies in text. To enhance trust and transparency, LIME (Local Interpretable Model-agnostic Explanations) is employed to explain model predictions by highlighting influential textual features. The framework is evaluated on two benchmark datasets using both binary and multi-class classification to examine robustness and generalization. In addition, an ablation study is presented to highlight the significance of various components of proposed framework. For binary classification, the proposed model achieves F1-scores of 96.78% on the Davidson dataset and 99.53% on the SMHS dataset. In the multi-class setting, it attains F1-scores of 97.00% and 94.99% on the Davidson and SMHS datasets, respectively, outperforming existing baseline approaches. The results demonstrate that multilevel evaluation improves the reliability that the proposed framework effectively balances performance and efficiency. This makes the framework suitable for practical hate speech moderation systems that require accurate, generalizable, and explainable decisions.

Scientific tasks specify a desired capability, but realizing it often requires building a computational system tailored to the task---acquiring data, designing representations, training models, implementing tools, and deciding how they are used at inference. We present LabFactory, a framework in which an AI builder turns a scientific brief into an executable AI lab: a task-specific solver that integrates models, knowledge resources, tools, and a controller behind a fixed interface. The builder develops and packages the lab in a metered workspace; a separate host then executes the delivered artifact on held-out inputs, with reference labels kept outside the solver's input interface, and scores its outputs under the task's protocol. This makes the delivered system, rather than the builder's account of its progress, the object of evaluation. We document 28 selected constructions across seven scientific task categories---from molecular and genomic prediction to physiological signals, clinical decision support, and biomedical text---whose delivered labs exceeded their configured reference values on all 33 subtests under host-side execution. Ten contain predictive models fitted during construction; the others assemble retrieval systems, executable analysis environments, and tool-driven workflows around a fixed platform LLM. Together they show that an AI agent can carry a scientific brief all the way to a working lab that can still be invoked, inspected, and checked after construction ends.

This work presents a federated framework for training Averaged $n$-Dependence Estimators (AnDE) in distributed environments. The proposed method focuses on the discriminative setting, where model weights are learned locally and aggregated globally, supporting any dependency order $n$. This design allows federated training without transmitting semantically meaningful parameters, improving privacy. Additionally, generative AnDE models are federated to provide a comparative baseline, with optional differential privacy applied to the aggregation of probability tables. Experiments on 12 discrete datasets show that discriminative models with $n \geq 1$ consistently outperform federated Naive Bayes (NB, $n=0$), and that privacy-preserving aggregation is effective with limited accuracy loss. These results establish federated AnDE as a viable and privacy-preserving framework, showing that probabilistic models remain applicable in modern federated learning settings.

Large Language Model (LLM) agents struggle to scale safely when exposed to vast enterprise toolsets. Providing an agent with access to every internal tool leads to oversized context windows, degraded tool selection, and severe governance vulnerabilities - as system policies defined purely in prompts remain probabilistic advice rather than hard constraints. Existing mitigations, such as multi-agent domain delegation, decentralize audit logs and fail to guarantee policy compliance across sessions. We introduce skilder, a framework that packages capabilities into roles: bundles of skills, tools, and instructions, together with the limits that bound them. An agent begins with a minimal role catalog, learns the roles a task requires, and receives each role's skills, instructions, and tools through a single MCP server. Because tools reach the agent only inside learned skills, the same server enforces the scope of what was learned deterministically. We evaluate skilder against flat-context tool selection and multi-agent orchestration across 13 tasks using six models (10 runs each). Our results show that, when models completed discovery and issued a governed call, the skilder simulated authorization layer enforced governance boundaries: no unauthorized tool call or parameter violation (e.g., a spending-limit breach) executed. Aggregate task pass rates also reflect whether each model followed the discovery protocol and satisfied response-quality checks; those misses are not authorization failures. Furthermore, by allowing agents to dynamically acquire cross-role capabilities mid-task, skilder preserves problem-solving flexibility while providing hard system-level enforcement.

Artificial Intelligence agents based on large language models provide convenient natural language interfaces to scientific software, but reliability is not automatic. Here we introduce the Epydemix Agent Framework, an additive layer over Epydemix, an open-source Python library for stochastic compartmental epidemic modeling. The framework extends the library with four capabilities to facilitate interaction with an AI agent: discovery of available models and parameters, preventive validation of a declarative scenario specification, execution through tested library code, and inspectability of results. These capabilities let an agent handle the entire modeling process, from the natural-language description of the scenario to quantitative results, figures, and interpretation of findings without writing custom code. Each step reads input files and saves results in a separate output bundle, making the process auditable and reproducible. First, we show the end-to-end workflow with a case study comparing vaccination strategies for a novel respiratory virus. Second, we assessed the framework across 50 agent sessions and five modeling tasks by comparing the agent use of the framework against the direct use of the Python interface. The framework reduced turns, output tokens, and cost on most tasks, unless it trades resources for per-point reproducibility.

Faithful user simulation is fundamental to building, evaluating, and improving interactive AI at scale. However, plausible individual responses do not ensure that simulated users reproduce the intent evolution and outcomes observed in real interactions. We propose TRACER, a multi-turn user simulator that explicitly models users' evolving intent and learns to align simulated behavior with real interaction trajectories. TRACER is trained in two stages: supervised fine-tuning on real user dialogues, followed by multi-turn reinforcement learning. The RL stage combines hierarchical outcome- and trajectory-level rewards with deviation-aware advantage modulation, jointly mitigating reward sparsity and credit assignment in long dialogues. On real customer-service sessions organized into reference cohorts, TRACER-7B surpasses the strongest baseline by 11.4 conversion F1, while also achieving the lowest group-level conversion-rate error and semantic trajectory distance, and generalizing to out-of-distribution scenarios. Human Turing tests yield identification accuracy close to chance, supporting the perceived naturalness of generated conversations. Building on this simulator, we further introduce the Dynamic Marketing Benchmark, which jointly evaluates persuasion effectiveness and response quality of LLMs through simulated interactions, revealing that higher response quality does not necessarily correspond to higher conversion rates.

Encoding input coordinates with sinusoidal functions into multi-layer perceptrons (MLPs) has proven effective for implicit neural representations (INRs) of surfaces defined as zero-level sets. However, existing methods often struggle to balance training efficiency, rendering speed, and noise robustness: single-MLP approaches are expensive at inference, grid-based representations are fast but can limit surface smoothness and overfit input noise, and previous multiscale approaches frequently capture noise and produce artifacts due to hard spectral truncation. To address these limitations, we propose M-plicits, a multiscale framework that models surfaces as a residual sum of MLPs trained via a sequence of nested neighborhoods. Unlike existing residual approaches that rely on standard domain-wide sampling and require costly mesh extraction for visualization, our method strictly localizes supervision to narrow bands around the previous zero-level sets. This nested design naturally provides robustness against noisy input data: the coarse network acts as a low-pass filter that establishes a clean geometric prior, while subsequent residuals progressively refine the geometry without fitting to high-frequency artifacts. We further introduce a multiscale sphere-tracing algorithm and a GEMM-based analytical normal computation that bypasses auto-differentiation entirely, yielding high-fidelity real-time rendering. On Stanford and Thingi32, M-plicits achieves the best mean Chamfer distance in the coarse configuration and the best median Chamfer distance and IoU in the fine configuration, with substantially better noise robustness than iNGP, BACON, and IDF, while using an order of magnitude fewer parameters than grid-based baselines. Code, models, and data will be released at https://github.com/dsilvavinicius/m-plicits.

Post-training hybrid reasoning models in NoThink mode has attracted growing interest as a way to improve performance while keeping inference fast. However, these gains may draw on thinking behavior already accessible through the base model's Think mode. We formulate this thinking leakage in a causal mediation framework and audit its contribution using bidirectional interventions along a simple base-derived activation direction. Across three models and three post-training methods on competition math benchmarks, we find that leakage is real, causal, and substantial: behavioral and representational analyses reveal shifts toward Think, steering the base model along this direction reproduces most of the post-training accuracy gain, and counter-steering a checkpoint removes a substantial share of what it gains. Across nine aligned checkpoints with positive NoThink gains, the resulting leakage ratio ranges from 42% to 79%. These interventions support a substantial causal contribution of thinking leakage. Our findings show that a post-training method's apparent advantage can therefore reflect greater drift toward Think, obscuring whether it improves capability within NoThink or more effectively re-invokes existing Think behavior.

Large Language Models (LLMs) are increasingly deployed as argumentative agents in persuasive dialogues, necessitating rigorous evaluation of their debating competence relative to human interlocutors. In this study, we focus on character attacks (ad hominem arguments), traditionally dismissed as fallacies, which play a pivotal role in political persuasive dialogues where ethos often rivals propositional content. Specifically, we investigate whether modern LLMs can replicate human competence to strategically use and respond to such attacks. We analyse a corpus of natural language political dialogues to identify defensive strategies human interlocutors naturally employ in ethos-centred debates and structure them into a dialogue game. Empirically, we benchmark LLM-generated dialogues against the ElecDeb60to16-fallacy corpus of U.S. presidential debates, contrasting human debaters' repertoire of defensive strategies with those of artificial agents. Results reveal a substantial difference: most LLMs rigidly prioritise logical defences, failing to exploit ethotic counterattacks as valid moves in political discourse. We argue that current safety fine-tuning constraints the strategic action space of these LLMs, making them unable to fully engage in naturalistic interactions within domains where character contestation is a normative expectation rather than a mere fallacy.

Graph-based world models have recently emerged as a means of learning transitions over relational state representations. However, existing approaches are largely limited to fixed-topology graphs or deterministic, fully observable environments. We propose the Graph Dynamics Model (GDM), a world model for graph-structured observations that is designed to handle the more general setting of evolving topologies in stochastic and partially observable environments. The GDM uses a sparse recurrent adjacency matrix to model topology updates and perform message passing, together with a recurrent state-space architecture for modelling stochastic transitions. Furthermore, we identify a gap in the evaluation of graph-based world models, as existing methods do not provide a means of comparing predicted and true distributions over the joint graph state comprising the interdependent topology, node features, and graph features. We therefore introduce the Graph Distribution Distance (GDD) metric, which uses maximum mean discrepancy with a graph kernel to comprehensively compare joint next-state distributions. We evaluate the GDM across several environments, including stochastic and partially observable settings. We demonstrate that GDM outperforms baseline models and displays zero-shot generalisation on large graphs.

A virtual screening campaign may produce thousands of promising candidates, but only a small number can be purchased, synthesized, or tested. The practical question is how to select a set of compounds that both rank well and are diverse enough: this poses a genuine tradeoff, where selecting the highest-scoring molecules yields limited diversity, while diversity selection sacrifices some well-scoring molecules. We introduce OPDiv, a diversity selection and evaluation algorithm solving this tradeoff by finding an optimal subset of molecules using integer optimization. We demonstrate the selection algorithm in practice with fingerprint distance, shape and electrostatic diversity and compare the resulting diversity spectra. We argue that virtual screening is not merely a ranking problem, but also an implicit constrained optimization task: when redundant chemotypes are undesirable, pipelines should be compared based on the top-k compound selections satisfying the desired diversity constraints. OPDiv makes it possible to find the optimal compound set under a given diversity threshold efficiently and serves as a fair benchmark of the best diverse selection achievable by a given structure-based or ligand-based virtual screening pipeline, molecular search or generative model.

Object permanence and solidity are hallmarks of human cognitive priors. Recent studies show that video generation models, a paradigmatic class of current world models, have begun to show emerged reasoning abilities, making them ideal candidates for building human-like physical intelligence. Do video models have emerged object permanence in them? If not, could we train them with a core-cognition inspired dataset? We introduce WROP (World Reasoning with Object Permanence), a data infrastructure of 150 hand-designed cognitive science inspired tasks, divided into six cognitive categories. We build Blender generators that randomize speed, lighting, camera angle, and other nuisance parameters while preserving each task's cognitive structure, yielding 10,000+ samples per task. We release a 1.5M-sample training corpus and a 300-question exam. On this exam we evaluate 14 video models: 3 reference-to-video, 7 edit, and 4 continuation, among which PWM-WROP, our 16B world model. In a blind pairwise Elo study, PWM-WROP ranks first among continuation models and third overall, behind only a statistical tie between two reference-to-video models. We release the data, exam, model answers, scores, weights, and PWM, our native-PyTorch training stack on AWS Trainium2.

Retrieval-augmented question answering requires control decisions about when to decompose a question, search, reformulate, extract evidence, synthesize facts, verify progress, and stop. We study whether trajectory fine-tuning can improve small language models (SLMs) as next-action controllers. We additionally evaluate a low-resource setting in which a single SLM serves as both the controller and the final-answer generator. From accepted teacher search traces, we build a seven-way action-prediction task, where the model predicts the next structured teacher action from the current trajectory state, and evaluate LoRA-supervised fine-tuning across SLMs and xSLMs as controllers. On 1,646 held-out action examples, Granite 4.1 3B trained on 13,194 actions reaches macro-F1 0.6536, compared with 0.1736 for zero-shot prompting of the same model and 0.5399 for a TF-IDF logistic-regression baseline. In an end-to-end controller/generator swap evaluation over 149 held-out trajectories, using the fine-tuned model for both roles improves Exact Match from 0.7530 to 0.7946 and token F1 from 0.7783 to 0.8295 compared with using the base model as both controller and generator. The cross-role conditions show that the fine-tuned controller increases evidence-fact recording when the generator is fixed, while controller-only final-answer gains are not statistically clear. Overall, trajectory supervision improves action prediction and evidence-recording behaviour in this evaluated pipeline. Code is available at https://github.com/padas-lab-de/agent-action-controller

Despite the importance of reinforcement learning with verifiable rewards (RLVR), the extent to which it can learn new reasoning capabilities remains debated. Here we study the optimization landscape of RLVR on algorithmic tasks, such as iterated group and quasigroup multiplication. To this end, we map entropy-regularized RLVR over myopic tabular policies onto an energy-based (spin-glass) model over deterministic policies. This mapping upper-bounds what RLVR can achieve, and lets us rigorously characterize the landscape in this tabular setting. We show, both theoretically and experimentally, that for a wide class of models and tasks with uncorrelated inputs, this landscape is benign, containing no local minima that could trap RLVR training. Rather, the practical difficulty of these tasks appears to stem, at least in part, from issues such as diffusive barriers and gradient-estimation error in traversing the landscape. These are genuine obstacles that can prevent a solution from being found, but they are distinct from the landscape itself being rugged. We show that these obstacles can often be mitigated through the choice of entropy regulator. Consistent with this theory, we find that a transformer trained from scratch, using only last-token rewards, successfully learns an algorithmic chain of thought for iterated non-Abelian group multiplications.

Autonomous research agents can design experiments, evaluate results, and write reports, giving them control over both a scientific result and the evidence used to support it. This creates a risk of reward hacking: meeting the reward criteria without achieving the intended goal. We study (1) how often models reward-hack without instructions to do so, (2) how effective and detectable their methods are when hacking is allowed, and (3) how they adapt when an LLM review panel returns its decision and reasons. Across 17 language models and 38 tasks, the spontaneous reward-hacking rate is 30.5% on open-ended research-pipeline tasks and 2.9% on task-specific kernels. When hacking is allowed on tasks whose pass thresholds exceed our best compliant baselines, 505/677 attempts (74.6%) are confirmed reward hacks: they both clear the threshold and receive mechanism-verification panel confirmation of an evaluation exploit. An LLM panel reviewing only submitted code and reported scores misses 33/505 confirmed hacks (6.5%). Direct methods that achieve the highest scores are often easy to detect, while less direct methods evade more often. In a five-round loop, the number of model-task pairs with an evasion rises from 7 to 56. Among 79 pairs evaluated under two feedback conditions, cumulative evasion reaches 40.5% with detailed feedback and 20.3% with generic rejection. The detailed condition includes the review decision, reasons, and attempt history, so this comparison does not isolate the effect of explanations. These findings highlight the need for stronger defenses, including metrics kept outside the agent's control and independent recomputation on data chosen to expose likely exploits.

Most studies of prompt injection focus on generative agents, leaving their effects on models with schema-defined outputs unclear. We examine these effects in Jev, a non-generative decision model, using 510 reconstructed InjecAgent cases. Malicious content shifts action probabilities but rarely causes Jev to select the attacker's target. Override markers reduce this influence, while claims of contextual relatedness have small effects. Adaptive attacks using score feedback double the mean highest attacker-target probability found during optimization, while success on fresh validation calls rises from 1.8% to 3.5%. Exploratory analysis links these successes to small initial decision margins or greater attacker control over the observation. Together, these findings show that schema-defined outputs change but do not eliminate prompt-injection risk, highlighting the need to evaluate how untrusted content influences choices within the allowed action set.

Benchmarking is an increasingly critical part of research in machine learning and the domains where it is applied, including healthcare. Yet, despite the steady development of new ultrasound foundation models in recent years, the development of well-designed benchmarks to evaluate them has lagged behind. This deficiency has led to fragmented and inconsistent evaluations of competing models, making it difficult to measure progress. To address this issue, we introduce UltraBench 2, a comprehensive benchmark with wide anatomical and task coverage, and a focus on standardization, reproducibility, and ease-of-use. Using this benchmark, we compare existing vision foundation models for ultrasound image analysis. Our analyses demonstrate that ultrasound-specific pretraining still leads on classification, but that state-of-the-art general-purpose models have drawn level on segmentation.

Role-playing agents based on large language models have been widely applied in areas such as personalized assistance and social simulation. Recent RL methods typically train on a fixed scenario pool collected before learning begins. This creates a distributional bottleneck: as the agent improves, the scenarios where it performs poorly also change, while the training distribution remains static. Therefore, we propose AdvRole, an adversarial context rewriting framework that turns role-playing RL into a closed-loop curriculum. AdvRole alternates between an Actor that learns to role-play and a Rewriter that edits character profiles and dialogue contexts into actor-specific hard scenarios. The Rewriter is trained with a performance-gap reward, which favors rewrites that reduce the current Actor's score relative to the original scenario. As a result, the scenario pool evolves with the Actor and continuously targets under-mastered regions of the character-context space. Experiments on three role-playing benchmarks covering English and Chinese, as well as a new multilingual benchmark we release, show that AdvRole consistently outperforms baselines.

Removing CPython's Global Interpreter Lock (GIL) exposes native code to concurrency absent from ordinary C types. Mutation or re-entry can revoke a borrowed object, storage pointer, traversal state, or lease between acquisition and use while its owner remains alive, causing native memory errors and runtime-state corruption. Race analyses track conflicting accesses. Python/C lifecycle analyses track individual object states. These reporting units leave implicit owner-subject-storage relations disconnected from later uses under parallel and re-entrant events. We present CONCURDEP, a source-level static analysis of dependency invalidation. Its key insight is to represent the runtime property a native use requires and ask which target-matched event can revoke it within the dependency's live region. CONCURDEP recovers runtime-semantic dependencies, connects them to events through an event-aware native concurrency dependency graph, and applies property-specific state and protection transfers through a shared engine and six mechanism plugins. CONCURDEP correctly classifies all 180 matched semantic-conformance cases and analyzes each of three production CPython releases with five-run medians of 22.13-27.66 seconds and 670-784 MiB peak resident memory. Source auditing confirms 1,094 of 4,273 unique production fingerprints (25.60% confirmation yield). Removing derived relation recovery loses 25-44 represented roots per release; removing cross-entry events loses 73-94. The study identifies 144 distinct bugs across free-threaded and conventional-GIL builds, including 95 previously unreported in public sources. These results show that explicit dependency, event, and property semantics expose consequential runtime failures across API boundaries and execution modes at release scale.

Intermittent time series are common in spare-parts demand and retail sales. Since the cost of forecast errors is typically asymmetric, decisions such as inventory control require the full predictive distribution rather than a point forecast. Many probabilistic forecasting methods have been proposed; their implementations, however, are scattered across different software frameworks, making it difficult to compare them systematically. We introduce fable.intermittent, an R package that implements several probabilistic forecasting methods for intermittent series within the fable framework. The package allows several models to be fitted and evaluated on a collection of time series through a single, simple forecasting pipeline. We also introduce TWEES, a new exponential smoothing model with a Tweedie predictive distribution. Fitting TWEES requires repeated evaluation of the computationally demanding Tweedie density. We also release the R package tweedieDistr, whose implementation of the Tweedie distribution is substantially faster than the existing one while preserving the same numerical accuracy. We evaluate the methods implemented in fable.intermittent on four datasets, also released in the package.

The Factivity Inference Evaluation 2026 (FIE2026) classifies Chinese context-hypothesis pairs into nine ordered factivity intervals. Its evaluation metric rewards both exact predictions and proximity to the correct interval, while 64.1% of the 566 training examples belong to a single class. In preliminary experiments, several mDeBERTa classification models predominantly predict the dominant class, whereas a Huber-regression baseline produces more predictions near the correct interval but fewer exact matches. We introduce Utility-Oriented Factivity Inference (UO-FIE), a parameter-efficient system that combines exact-label supervision with graded utility. UO-FIE predicts a distribution over the nine classes and combines hard-label supervision, utility-based soft targets, scheduled class weights, and an ordinal loss. We evaluate expected-utility decoding in controlled comparisons and use ordinal calibration selected on out-of-fold predictions for the submitted system. Based on Qwen3.5-9B with LoRA, UO-FIE ranks first in the fine-tuning track with a macro utility of 0.8316. A separate prompt-based ensemble ranks third in the non-fine-tuning track with a macro utility of 0.8450.

Scientific instruments require accurate calibration to convert detector signals into reliable physical observables. Conventional calibration procedures typically rely on dedicated calibration measurements, analytical response models or labelled reference data, limiting their ability to adapt to changing operating conditions and detector aging. We present a physics-informed self-supervised learning framework that jointly performs wire calibration and interaction position reconstruction in Multi-Wire Parallel Plate Avalanche Counters (MWPPACs) without requiring labelled position measurements or dedicated calibration runs. The method formulates detector calibration as a latent optimization problem in which global wire gains and event-wise interaction positions are estimated simultaneously using supervision derived exclusively from detector geometry and charge-energy consistency constraints. A detector-independent neural network reconstructs sub-wire interaction positions from local charge distributions, eliminating the need to assume analytical induction profiles by learning the detector response directly from experimental data. The end-to-end differentiable framework enables continuous detector self-calibration while improving the uniformity and accuracy of position reconstruction. Experimental evaluation on the entrance MWPPAC tracking detectors of the VAMOS++ magnetic spectrometer demonstrates stable convergence, improved spatial homogeneity and enhanced position resolution. Beyond the detector studied, the method establishes a general framework for physics-informed self-supervised calibration of scientific instruments and is a step toward autonomous intelligent instrumentation capable of continuous adaptation during operation. In this paradigm, detector calibration is no longer a prerequisite for an experiment but an integral part of the measurement process itself.

Recently, Large Language Models (LLMs) have been increasingly able to solve advanced mathematical problems, including many that have been open for decades. This opens the door to expansion of mathematical knowledge at unprecedented scale. Yet, while LLMs may be able to conjecture and prove more and more theorems, it remains open whether this new mathematical knowledge is interesting or useful. We define intrinsic interestingness of a theorem as the ratio between the length of its proof and the length of its statement. We show that this correlates strongly with an extrinsic measure of the downstream utility of a theorem. We identify the difficulty of a proof conditioned on a set of premises as a useful primitive for computing these metrics, and train a 27B model that predicts proof difficulty more accurately than frontier general-purpose models. Optimizing for our metric creates a model capable of producing more interesting theorems, while also reducing substantial or full overlap with Mathlib from 91.9% to 30.6%, showcasing the creation of more out-of-distribution math. We show that our system can generate candidate theorems, select the most interesting among them, and iteratively build on a self-expanding mathematical library. These metrics provide a practical and quantifiable signal for ranking conjectures and guiding proof search within formal mathematical libraries. Our framework provides a path towards self-expanding, machine-verified mathematical libraries that can choose worthwhile statements without relying on human-supplied targets.

Benchmarking and routing platforms increasingly act as intermediaries connecting large language model providers with end-users. However, providers on these platforms typically use a fixed price per token, preventing users from achieving the most competitive price for their tasks. In this work, we design a procurement platform where token prices for each task are driven by provider competition, enabling users to secure competitive pricing for guaranteed quality levels. To this end, the platform sequentially routes queries via a reverse second-price auction that incentivizes model providers to truthfully bid their best estimate of the average cost to serve a user's query. As it routes queries, the platform learns the quality offered by each provider and progressively routes queries to the most cost-competitive provider among those meeting a desired quality threshold. To validate our design, we conduct experiments with multiple LLMs from the Llama and Qwen families on popular mathematical reasoning and question-answering benchmarks. The results show that the pricing margin of the most cost-competitive provider on our platform varies significantly---from $10\%$ to $71\%$---depending on the task and quality threshold. This suggests a substantial inefficiency in the current fixed-price market, and it demonstrates that our platform may enable users to capture maximum savings whenever competitive market conditions permit.

Machine-learning (ML) emulators for atmospheric processes have advanced rapidly in recent years, transforming weather forecasting. Although early ML ocean forecasting models now exist, they remain less developed than their atmospheric counterparts. Unlike the atmosphere, much of the ocean's kinetic energy resides in mesoscale eddies whose characteristic spatial scales are approximately an order of magnitude smaller than those of comparable atmospheric features. Moreover, complex coastlines, narrow straits, and ice-covered seas make boundary representation a central challenge that atmospheric models do not face. Consequently, numerical ocean simulations commonly use locally refined or even completely unstructured meshes. However, their data-driven counterparts have so far been built around latitude-longitude grids. We present HClimRep-Ocean, an ocean emulator that operates directly on the native unstructured mesh of FESOM2. The emulator is trained on a 209-year AWI-CM3 control integration and is run without atmospheric forcing, receiving the atmospheric state only at initialisation time, which isolates the predictability carried by the ocean state itself. Skill is strongly field-dependent: for currents, HClimRep-Ocean outperforms every reference at 30 day forecast, whereas for temperature and salinity a damped-anomaly persistence forecast remains the more accurate estimator. This behaviour is physically interpretable: current variability is largely geostrophic and internally generated, whereas sea-surface temperature and salinity fluctuations are driven by atmospheric forcing through weather state. Evaluated independently on the OceanBench benchmark, a reanalysis-trained variant of HClimRep-Ocean achieves the lowest RMSE against GLORYS reanalysis among all assessed systems, confirming the competitiveness of the native-mesh approach.

Verification and validation practices (V&V) at NASA's Jet Propulsion Laboratory (JPL) have diverged over the past decade, creating fragmentation that increases overhead, reduces cross-project efficiencies, and inhibits institutional knowledge transfer. We present a unified V&V activity schema developed through human-centered design workshops involving 29 practitioners across multiple mission types and disciplines. The schema builds on a relationship-based architecture that allows for separating methods (Test, Analysis, Inspection, Demonstration, and Review of Design) while maintaining a common attribute set. Formalized as a platform-agnostic SysML model, the schema defines bidirectional relationships between requirements, V&V activities, venues, and evidence. Implementation in JPL's Jama platform demonstrates controlled customization through templates and modular item types, balancing rigor with agility while enabling automations, pattern reuse, and digital thread integration.

Flipping 60\% of training labels from a single Byzantine client using label-flipping model poisoning self-degrades an attacker's own federated detection accuracy, $99.96\%$ (at no poisoning rate) to $84.33\%$ in a three-client federated IDS. Where the Federated global ensemble maintains stable accuracy across all tested poison rates, without a defense mechanism in place and without coordination between attackers. In this paper, we present empirical results quantifying the impact of label-flipping poisoning attacks on a three-client federated IDS trained on CICIDS2017 with non-IID attack subtype distributions across clients. We demonstrate that the signal of the adversarial self-compromise represents a detectable anomaly for exploitation for Byzantine client identification in the absence of target data exfiltration. We note that the aggregation step uses a Federated Forest (tree concatenation) rather than a parametric FedAvg; the results therefore measure the impact of poisoning on per-client performance under ensemble aggregation, and extension to genuine FedAvg with a parametric classifier is planned for future work.

Background & Problem: Thyroid Fine-Needle Aspiration Biopsy (FNAB) cytology based on the Bethesda System plays a pivotal role in early thyroid cancer detection; however, deep learning approaches face substantial challenges regarding high false-negative rates and overconfidence under clinical domain shift. Methods: In this study, we propose TAM-Chain, a multi-scale (10x, 20x, 40x) thyroid cytology classification framework leveraging Absorbing Markov Chain theory combined with Shannon Entropy-based Uncertainty Quantification. The framework dynamically models multi-magnification feature extraction as an absorbing stochastic process, enabling optimal stopping criteria and a human-in-the-loop referral mechanism to strictly suppress critical diagnostic errors. Results: Extensive evaluation on an internal test set (N = 235) demonstrates a Macro F1 score of 0.9741 with an absolute False-Negative Rate (FNR) of 0.00%. On an independent external validation set (N = 1015) presenting severe domain shift, TAM-Chain maintains superior stability and classification performance (Macro F1 = 0.7026) by adaptively adjusting the expected stopping step and triggering specialist referrals, significantly outperforming single-magnification baselines. Conclusion: The TAM-Chain framework proves to be a highly effective, safe, and adaptable solution for digital pathology workflows, successfully harmonizing automated diagnostic efficiency with stringent biological safety.

Large language models can interpret natural lan- guage, yet robust decisions remain challenging. Jev-like models expose structured choices, but these interfaces do not directly provide numeri- cal values at a requested precision. We propose NUMERICJEV, a training-free numerical decod- ing algorithm that enables numerical output from any LLM with a Jev-like structured-choice in- terface. Surprisingly, on our arithmetic bench- mark, it outperforms direct selection from a can- didate list containing the correct answer by 2.93 percentage points (Figure 1). Our motivation comes from the observation that numerical range selection is itself a decision problem that Jev- like LLMs can address. NUMERICJEV recur- sively refines a range through a multiway deci- sion tree while retaining the original question in context, without parameter updates or hidden- state access. On a 100-value grid, a ten-way tree requires only two decision rounds. Range- normalized MAE is 1.84% versus 5.18% for di- rect choice. A separate three-date historical- index study yields 4.58% mean relative recall er- ror and 0% readout error when the value is sup- plied. Code is available at https://github. com/Bring-AI/jev-numeric.

Coding-agent approval interfaces bind a human decision to a command or tool call, while developer tools execute the transitive workflow that invocation activates. Package installation can run lifecycle hooks and write files; an MCP call can exercise network authority. We call the resulting record-coverage failure approval laundering: the durable record names the entry invocation but omits effects exercised by its workflow. We present the first systematic security analysis of this record-to-closure relation in agent systems. We formalize closure-bound approval over six effect classes and derive an information limit: identical policy-visible fields can require different effect-specific decisions, so no record-only policy can guarantee both. The Approval-to-Action Security Benchmark binds approval objects and decision-time metadata to post-execution evidence. Across 111 fixed approval-object/trace pairs, residual records fall from 40 under explicit fields to 17 with command semantics and 13 with decision-time metadata. Across 11 fixed-SHA executions, the ladder reaches zero metadata residuals; two exact mappings recur across three product frontends. For prospective recovery, effect-bound records commit frozen, source-backed predictions and provenance before authorization. On 17 prespecified holdout workflows, predictions achieve 0.926 macro recall and 0.941 macro precision; binding them cuts residual effects from 10 to 3. A Claude Code PreToolUse integration carries the frozen record through the permission path without automatic approval. These results establish approval laundering as a measurable, recurrent record-coverage failure despite truthful invocation identity. They motivate binding each invocation before authorization to a source-backed prediction of its workflow's transitive effect boundary and preserving that binding with the decision.

Multi-step tool-calling LLM agents rely on host runtimes to preserve state across turns. When a runtime carries an external tool return into later model inputs, providers meter it again. An admitted malicious or compromised tool can thereby convert untrusted data into recurring victim-billed processing without victim credentials or local runtime privilege. We call retained content persistent billable state and formalize the host's decision over whether and how it enters later billable context as the persistent billable-state boundary. We present the first systematic security study of this post-admission lifecycle. We derive six denial-of-wallet attack vectors and build DOW-BENCH, an end-to-end harness evaluated across six model families. Across 243 executions, usage telemetry shows that the maximum per-session cumulative input reaches 14,293x the session's first-call input. Controlled history-policy reruns isolate raw retention's contribution: retaining raw history increases mean effective session cost by 21.2-35.9%. Compression succeeds on 10/12 and 11/12 history-dependent tasks, versus 2/12 under deletion for each provider. To govern this boundary, we combine deterministic history transformation with four host-side invariants that bound prompt mass, context growth, recursive opportunity, and cumulative spend before reingestion. The kernel contains every recurring attack in the 123-evaluation replay corpus. Across 24 Mistral Small 4 workflows, a progress-authorized policy achieves 22/24 oracle-verified task successes with no pre-completion interruptions, versus 13/24 under a fixed cap. Only 71 of 3,830 scanned MCP server and transport repositories expose any code-visible safeguard proxy, and none cover all four safeguard families. These results establish persistent billable state as a first-class security object and pre-reingestion as its host-owned control point.

Advances in generative modeling have recently been extensively employed in robotics for policy learning. In particular, Conditional Flow Matching (CFM) trained with expert demonstrations has been shown to outperform existing methods on robot manipulation benchmarks. While prior work has mainly focused on single-task settings, we study the problem from a multi-task perspective, as training independent models for each task is computationally expensive. Multi-Task policy learning comes with its own set of challenges, as naively training on a concatenated dataset of demonstrations would either require increased model capacity to accommodate the added complexity or result in drops in performance. We propose to distill knowledge from single-task CFM experts into a shared multi-task policy by transferring their learned velocity fields. We combine this distillation signal with the original CFM objective to retain fidelity to the demonstrations. Experiments on RLBench show that our approach improves multi-task policy performance over naive training while maintaining a fixed model size.

We propose LAYERSCOPE, a label-free, layerwise framework that aims to characterize a model's learned representations in video and multimodal settings. Evaluating downstream performance using representations from final or intermediate layers typically requires large amounts of labeled data, repeated task-specific evaluations, and substantial computation. To address these limitations, LAYERSCOPE uses local, global, distributional, and correspondence-based geometric metrics to compare layerwise representation structure within and across models without requiring task-specific labels. We evaluate seven architecturally diverse models across video and multimodal classification, clustering, and text-to-video retrieval tasks from MVEB/MVEB+. We find that intermediate-layer representations can outperform final-layer and model-default outputs. We also find that no single geometric metric consistently predicts downstream performance, but note that distinct layerwise geometric signatures emerge across model families. LID shows task-dependent relationships with performance, while RankMe provides the strongest measure for classification and clustering, but is not a universal layer selector. We also find that pairing-aware metrics explain retrieval better than distributional distances alone. LAYERSCOPE therefore offers a framework for comparing representations across models and layers, enabling a more systematic evaluation in video and multimodal settings.

The recent emergence of Time Series Foundation Models (TSFMs) has significantly advanced multi-step forecasting performance, enabling accurate predictions over extended future horizons. However, existing TSFMs often suffer from significantly inherent uncertainty, which typically manifests as derived forecast branches emerging at each time step and spreading to subsequent steps; different forecast branches often exhibit varying forecasting performance, thereby undermining the credibility of TSFM forecasts. In this paper, we propose the Slicing-Graphing-Alignment (SGA) method to quantify the uncertainty of multi-step TSFM forecasts. The proposed SGA first characterizes the topology of all potential forecast branches using a directed acyclic graph, such that the graph complexity bounds the uncertainty of multi-step forecasts, and then precisely measures the graph complexity by integrating both topological information and TSFM-inherent stochasticity. Experimental results conducted on 11 TSFMs and 27 datasets demonstrate that (i) SGA achieves the best performance when ranking predictive errors with uncertainty estimates; (ii) SGA works with a more extensive and more precise sampling coverage than those of existing UQ methods, deriving a quantification mechanism fundamentally different from those of established ones; and (iii) larger model scales of TSFMs correlate with lower uncertainty estimates of multi-step forecasts, suggesting another empirical scaling law for uncertainty quantification of multi-step TSFM forecasts.

Reinforcement-learning (RL) policies are often distributed as opaque neural checkpoints, while training logs show that a run occurred without explaining what the policy learned. We study whether independently trained policies can be represented and composed through auditable discrete behavioral rules. We define auditability as six separately testable predicates: trace integrity, lossless coding, rule coverage, behavioral agreement, composition quality, and value-model reliability. Our protocol uses a shared frozen symbolizer, passive rule extraction, an append-only hash-bound ledger, exact environment replay, and offline confidence-ranked arbitration with an explicit blind-spot fallback. The results place strict limits on this description layer. Rule-set overlap does not imply behavioral agreement: policies may share symbolic rules while choosing near-chance-matching actions on fresh states. The fused policy therefore selects among existing rules rather than generating a new skill. On a conflict-dominated task, an apparent fusion failure is traced to an induction/deployment mismatch: rules induced from sampled actions were evaluated under argmax actions, and deployment-consistent re-induction reverses the arbitration ordering. A fitted-Q generalized-policy-improvement diagnostic also fails in both environments, limiting claims that rule fusion is superior to value-based composition. One exploratory comparison favors rule fusion, but its comparator is post hoc, the task is partly saturated, and the fused policy remains below the strongest held-out actor. We contribute an evidence-bounded audit and composition protocol, not a claim of universal interpretability or autonomous skill generation. Future work must add temporally extended skills, cross-skill interfaces, composition search, and independent novelty audits.

The increasing adoption of electric vehicles (EVs) and rooftop photovoltaic (PV) systems is reshaping residential electricity demand and creating new challenges for demand-side management (DSM), tariff design, and low-voltage network planning. Much of the existing literature examines EV charging or PV generation in isolation, leaving the behavioral dynamics of household co-adoption less understood. We develop an integrated, two-part workflow to analyze advanced metering infrastructure (AMI) data. A discovery component applies dynamic time warping (DTW) k-means with DTW barycenter averaging to cluster daily import or export profiles into interpretable behavioral archetypes, while a predictive component trains a bidirectional long short-term memory (BiLSTM) model on 21-day windows and benchmarks it against tabular baselines for PV/EV activity detection. The EV activity labels are inferred from charging-like load signatures because charger measurements are unavailable. Using half-hourly AusNet residential data from Victoria, Australia, the clustering uncovers distinct patterns across PV-only, EV-only, co-adoption, and neither cohorts; for co-adopters, a midday-centered weekday export archetype accounts for approximately 50% of days. At validation-tuned thresholds, both BiLSTM and XGBoost achieve strong discrimination. BiLSTM obtains 0.991 for the area under the receiver operating characteristic curve (AUROC), 0.906 for macro-F1, and the highest recall on the most difficult class (0.836 for EV-only recall). Tree-based baselines remain competitive. Performance remains stable across plausible labeling rules (macro-F1: 0.894--0.914) and strictly forward temporal splits (macro-F1: 0.894--0.906).

Historical observations are not always fixed: statistical agencies revise previously published values as new evidence arrives. Forecasting from a contemporary download can therefore expose a model to information unavailable at the date it purportedly made a prediction. We propose VINTAGE-TS, a revision-aware adaptation of a time-series foundation model that distinguishes observation time from information-availability time. Its targets are the next period's first-published value and the value available a fixed number of days after that publication; neither is declared final truth. A joint predictive distribution preserves dependence between these targets and exposes uncertainty about their difference. We specify an ALFRED-based rolling evaluation, a matched Chronos-2 comparison, conventional and revision-aware baselines, and a separate audit of pretraining overlap. The accompanying software implements validity-interval reconstruction, delayed-label filtering, a frozen-backbone adapter interface, and reproducible diagnostics. An executed synthetic demonstration and a 25-configuration sensitivity suite verify the workflow, expose variation across seeds and revision regimes, and illustrate how hindsight contamination changes measured performance. Thirty one automated tests check temporal and integration contracts. Real ALFRED and Chronos-2 experiments have not been executed; no empirical foundation-model advantage is claimed.

Long-conversation memory benchmarks increasingly test recall and prompted knowledge updates, and recent work studies evolving user beliefs and memory state. TWIST is a proposed benchmark suite for a complementary, unmeasured property: intervention quality -- whether a deployed memory system, exercised through its own ingest/recall/vet surface, acts correctly at belief change points. Four tracks cover unprompted tension detection, vetting outgoing drafts against the record, answering with current beliefs while preserving supersession history, and governing sensitive recall. The suite extends LoCoMo's corpora and harness, pairing every detect/block metric with a matched do-not-over-detect control: surface-matched hard negatives price false intervention, so no track can be gamed by flagging everything. The benchmark itself is validated first: independent, gold-blind double annotation with adjudication, judge decoy calibration, and a separability audit. On the human-validated Track B v1.0 key (161 items, post-adjudication kappa = 0.85), no tested configuration simultaneously achieves high contradiction recall, high hard-negative specificity, and high attribution: flat-RAG baselines detect 0.76-0.97 of true contradictions but falsely flag 16-43% of surface-matched safe drafts depending on backend, while a deployed coherence-oriented system almost never over-flags (0.98-1.00 specificity) yet catches 42% of true contradictions -- a trade-off no recall-only score can see. A 13-configuration baseline ladder localizes causes: every gold contradiction is detectable from its evidence alone (recall 1.000), calibrated models nearly solve the track given the full transcript -- consistent with substantial retrieval-coverage gaps -- and draft-only floors reveal model-dependent style priors. A system's TWIST profile, beside its recall score, measures whether memory knows when to intervene and when not to.

Multi-stage LLM-based cyber agents may complete attack workflows while remaining brittle, costly, or reliant on incorrect interpretations of execution evidence. Success rates alone obscure inefficiency, adaptation through retries, and recognition of success or failure. We present an end-to-end diagnostic study of an Autonomous Adversary system with orchestrator, executor, and validator LLMs in enterprise-like lateral-movement scenarios. Six frontier models are evaluated across two scenarios and three modes: expert-defined, self-scaffolded, and fully autonomous. We assess validator consistency and evidence grounding; introduce a subtask-conditioned, cost-aware score for abnormal token use, retries, and runtime; and use comparative LLM-as-a-Judge analysis to identify planning deficiencies, including tool misalignment, plan similarity, over-specification, inadequate probing, and weak recovery. Validators are generally relevant and evidence-grounded but often nonspecific and overly optimistic. Bottlenecks cluster in credential and lateral-movement tasks, spread with scenario complexity, and vary more under full autonomy. Reliable evaluation must assess outcomes, evidence interpretation, resource use, and adaptation after failure.

Newton-Schulz (NS) iteration has recently been used in the Muon optimizer to transform update matrices during the training of large language models. Motivated by its spectral effect, we investigate applying NS directly to Transformer attention representations. We introduce Newton-Schulz Attention (NS-Attn.), a parameter-free transformation applied to the output of each attention head. Each head output is arranged as a feature-by-token matrix and normalized by its Frobenius norm. We then apply a finite NS polynomial step and restore the original norm. The objective is to reduce spectral concentration and increase effective rank before standard head merging and output projection. Across ViT and Swin on CIFAR-10 and CIFAR-100, NS-Attn. improves final-epoch accuracy in all 12 matched-seed comparisons, with mean gains of 0.25--0.83 percentage points. ViT ablations show higher mean accuracy with one iteration than with two. Spectral analysis further shows reduced leading-eigenvalue concentration and increased effective rank. These gains incur additional inference latency.