# Research Papers — 2026-09 · bundle page 52 of 266 > Full-text markdown of papers #2551–2600 of 13298 published in 2026-09, newest first. AI-readable mirrors of the full 13298-paper 2026-09 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-09/page/52 [← Previous bundle](https://aipod.dev/papers/archive/2026-09/page/51.md) [Next bundle →](https://aipod.dev/papers/archive/2026-09/page/53.md) ### SCOPD: Sparse-Context On-Policy Self-Distillation for Efficient Vision-Language Models Authors: Ahmadreza Jeddi, Enming Zhang, Jasper Gerigk, Hakki Karaimer, Mozhgan Nasr Azadani, Jiayun Luo, Minh Ngoc Le, Gholamali Aminian, Hugo Buurmeijer, Yongchao Chen, Leonid Sigal, Igor Gilitschenski et al. Published: 2026-09-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.34044v1 Reasoning vision-language models (VLMs) process images and videos as long sequences of visual tokens, making inference expensive. Training-free token pruning reduces this cost, but aggressive compression can sharply degrade performance, often attributed to irreversible loss of task-relevant visual information. We show that this explanation is incomplete. In a fixed-context Pass@K analysis, repeated sampling from the same pruned visual representation recovers many examples missed by greedy decoding, indicating that useful visual evidence can remain accessible but be used unreliably. We call this the representation-utilization gap. Motivated by this observation, we introduce SCOPD, a sparse-context on-policy self-distillation framework in which a student generates reasoning trajectories from pruned visual tokens while a privileged full-context teacher supervises the same on-policy prefixes. SCOPD requires no ground-truth responses, architectural changes, or additional inference-time computation. We further introduce SCOPD+, which uses a small visual-budget intervention to identify visually sensitive response positions and selectively distill them. At 10% visual-token retention, the Vanilla model retains 86.37% of its unpruned performance across 13 benchmarks. SCOPD raises this to 90.49%, while SCOPD+ further improves it to 92.43%. Across token budgets, benchmarks, and pruning operators, our results show that efficient reasoning depends not only on which visual information survives pruning, but also on how reliably the model learns to use it. --- ### Singularities of Non-negative Matrix Factorization and their application to Bayesian inference Authors: Naoki Hayashi, Yota Maeda, Yasushi Esaki Published: 2026-09-28 Categories: stat.ML, cs.LG, math.ST arXiv: https://arxiv.org/abs/2609.34043v1 Non-negative matrix factorization (NMF) is a singular statistical model whose Bayesian asymptotics are governed by the real log canonical threshold (RLCT). We study the local geometry of the factorization map and derive an upper bound for the RLCT of NMF. Let $H$ be the model inner dimension and $H_0$ the non-negative rank of the true $M\times N$ matrix. Assuming that the true matrix admits a strictly positive factorization of inner dimension $H_0$ in the interior of the parameter domain, we prove, for smooth positive priors, that $λ\leq \{(H-H_0)\min(M,N)+H_0(M+N-H_0)\}/2$. This bound strictly improves the previous bound when $H_0\geq3$. The proof uses a local analytic normal form that separates independent linear coordinates from a residual matrix product. When $H=H_0$ also equals the ordinary rank of the true matrix, we obtain the exact value $λ=H_0(M+N-H_0)/2$. Under the standard assumptions of singular learning theory, these results bound the leading coefficients of the expected Bayesian generalization error and the Bayesian free energy. --- ### Vision--Language Signals in Constrained RL: Safety Gains Without Anticipation Authors: Samuel Tetteh, Cody Fleming Published: 2026-09-28 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.34041v1 Safe reinforcement learning seeks policies that maximise task performance while satisfying safety constraints. In driving benchmarks, however, collision costs typically appear only at the time of collision, providing no advance warning of an approaching hazard. Frozen vision--language models can provide dense semantic feedback, yet it remains unclear whether their scores anticipate collisions and which component drives an observed safety improvement. Episodic cost can also favour policies that make little task progress. To address these gaps, we propose VLM-Safe-RL, a framework that integrates frozen CLIP signals into PPO-Lagrangian through reward shaping and an augmented multiplier update. On MetaDrive Hard, which combines the densest traffic with the largest map, the catastrophe rate falls from 31.6\% to 19.4\%. FormulaOne-L2 analysis finds no evidence that the CLIP signals anticipate collisions and shows that the VLM term has a negligible effect on the Lagrange multiplier. These findings show a conditional reduction in observed catastrophe rate without evidence of collision anticipation. --- ### Large Language Models for Structured Clinical Data Analysis: Dual-Agent Grounding and Validation Authors: Erfan D. Dehkalani, Seetha Shankaran, Abbot R. Laptook, C. Michael Cotten, P. Ellen Grant, Yangming Ou Published: 2026-09-28 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.34039v1 Objective: To develop and characterize CLEAR-Med, a dual-agent framework for natural-language analysis of structured clinical data that separates SQL-based invocation from independent validation. Methods: CLEAR-Med uses one agent to translate a question into executable Structured Query Language (SQL), retain the executed query and database result, and produce a draft. Deterministic checks and a separately invoked cross-provider Validation Agent then accept the draft, request one bounded repair, or abstain. We formalized the system as a bounded selective pipeline and evaluated CLEAR-Med's configuration and scalability, and the Invocation Agent's accuracy and consistency on a 25-query development benchmark, using a harmonized 21-site neonatal hypoxic-ischemic encephalopathy table containing 532 de-identified infant records and approximately 1,300 variables. Results: CLEAR-Med completed all six nominal scalability configurations, including 500x1300. Across 25 development-benchmark queries repeated five times, the Invocation Agent answered 83 of 125 responses correctly (66.4%; query-cluster bootstrap 95% CI, 48.0-83.2%), compared with 15 of 125 (12.0%; 95% CI, 3.2-22.4%) for the ungrounded ChatGPT baseline, a paired improvement of 54.4 percentage points (95% CI, 36.8-72.0%). Conclusion: CLEAR-Med provides a general architecture for traceable analysis of structured clinical data: numerical claims remain linked to executed SQL, and unresolved cases can fail closed. The reported experiments characterize CLEAR-Med's configuration and scalability and the Invocation Agent's accuracy, while the formal analysis establishes the encoded-property guarantee of the complete control flow; a prospective full-pipeline evaluation of the validation and abstention stages is the next stage of this work. --- ### Who Warmed the Archives? LLMs Overestimate Historical Warmth Authors: Claudiu Creanga, Liviu P. Dinu Published: 2026-09-27 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.37499v1 Historical archives are an under-used source for extending the instrumental climate record backward in time, and LLMs offer a way to extract the indices climatologists derive by hand. Beyond measuring how well systems extract this signal, we check whether their errors are safe to use for cross-century comparison, since a good correlation score does not rule out systematic, era-linked bias. Comparing lexical baselines, fine-tuned historical transformers, and LLM prompting on the Pfister temperature index across five centuries of German text, lexical methods beat every fine-tuned transformer we test, including one pretrained from scratch on historical German (r=-0.016). All six LLMs we test (Gemini 2.5 Flash, GPT-5-mini, DeepSeek v4 Flash, Claude Sonnet 4.6, Qwen3.7-Plus, Kimi-K2.6-Fast) show a warm bias that grows with calendar year, with the same sign in every model (slopes +0.13 to +0.34/century, p<0.01). The effect is modest in size (r-squared approx equal to 0.01 to 0.05) but consistent across six independently developed models. The best-correlated of the six, Gemini 2.5 Flash, matches the best lexical correlation (r=0.32) at double the error. An ablation stripping explicit dates and calendar-era markers from the quotes leaves this trend essentially unchanged, favoring an anachronistic present-day prior over the model correctly inferring the quote's era. Correlation alone is thus insufficient for vetting an LLM as a historical-climate-index oracle. --- ### The Rashomon Wikipedia: A Data-Perspectivist Analysis of Divergent Historical Narratives Authors: Claudiu Creanga, Liviu P. Dinu, Anca Dinu Published: 2026-09-27 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.37498v1 Wikipedia aims to provide a unified, neutral record of history, yet its independent language editions often function as distinct epistemic communities, creating divergent narratives around contested events. This paper investigates cross-lingual historiographical bias by analyzing Wikipedia articles across five languages (Romanian, Hungarian, Russian, Turkish, and English) focusing on three contentious events in Romanian history: the Battle of Posada (1330), the Soviet occupation of Bessarabia (1940), and the Night Attack at Targoviste (1462). Using human annotators and Large Language Models (LLMs) to classify citation stance and quantify narrative evolution from 2005 to 2024, we identify a phenomenon of "citation isolation". In the case of the Battle of Posada, only 2 out of 119 citations were shared between language editions, with the Romanian edition exhibiting a 91% pro-national bias compared to the balanced Hungarian edition. Longitudinal analysis reveals that these narratives are volatile and responsive to contemporary geopolitics, evidenced by a significant shift in the Russian framing of Bessarabia in 2024. Finally, we propose a "Peace-Maker" pipeline to automate conflict reconciliation. We demonstrate that while standard prompting leads models to hallucinate consensus, "adversarial" prompting, which explicitly instructs the model to preserve and attribute disagreement, achieves near-perfect neutrality scores. --- ### Larry Caused the Car to Stop, But the Model Didn't Notice: Transformer Blindness to the M-Heuristic Authors: Stefania Butnaru, Claudiu Creanga Published: 2026-09-27 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.37497v1 Modern transformer models excel at capturing semantic relationships through sentence embeddings, yet their ability to perform pragmatic reasoning remains understudied. This paper investigates whether encoder-based transformers such as DeBERTa employ the M-Heuristic (the neo-Gricean principle that marked linguistic forms implicate marked meanings). We test this hypothesis by contrasting lexical causatives (e.g., ``Larry stopped the car'') with periphrastic causatives (e.g., ``Larry caused the car to stop'') using a Natural Language Inference framework. Our experiments across 188 conditions with 15 ambitransitive verbs reveal that DeBERTa, RoBERTa, and BART show no evidence of capturing the pragmatic distinction between these forms, with DeBERTa predicting ``Neutral'' for 100% of cases. Probing analysis initially suggested a representation-use dissociation, but control experiments reveal the probe was tracking syntactic complexity, not causative pragmatics. Semantic similarity over 30 triplets places periphrastic causatives closer to unmediated manner descriptions in 29/30 cases, opposite to M-Heuristic predictions in the embedding space. Under explicit metalinguistic framing, Gemini Flash-Lite reaches 100% with item-specific traces, so the principle is available under instruction yet unused in default NLI. --- ### Risk-Controlled Selective LLM Answering by Pricing Label-Free Checks Authors: Dongyub Jude Lee, Jungseob Lee, Chanjun Park, Hyeonseok Moon, Heuiseok Lim Published: 2026-09-27 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2609.37493v1 Serving an answer from a large language model requires deciding when to abstain, yet a verifier's ranking accuracy alone does not determine the error rate among served answers. We introduce PriceCheck, which builds a compact family of decision rules from label-free checks such as re-solving a problem. Each check has a price: its agreement rates on correct and incorrect answers and its cost per run. Prices fitted on a small, class-enriched labelled set compose into predictions of a schedule's coverage and cost, guiding which checks to run and when to stop. A calibration test then selects a schedule at a stated selective-risk target. In mathematics, the selected schedules serve 76.1% of answers on average and keep held-out selective risk below 1.5% on all 15 splits. Under the shared testing protocol, PriceCheck serves more answers at that target than reward models, a prompted judge, the generator's confidence and a trained correctness classifier. At matched coverage, it keeps the fewest wrong answers among these scorers. Across 118 diagnostic schedules, price-based coverage predictions have a rank correlation of 0.97 with observed coverage. These results show that choosing how checks are combined and stopped matters alongside how well a verifier ranks answers. Code is available at https://github.com/js-lee-AI/PriceCheck. --- ### FORUM: Frozen Outputs Reconciled Using Model Agreement for Visual Grounding Authors: Taiyo Sato, Takamasa Sanda, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama, Shunya Nagashima Published: 2026-09-27 Categories: cs.CV, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2609.37488v1 Frozen multimodal large language models (MLLMs) now solve standard referring expression comprehension with a single prompted call, yet on adversarial benchmarks with same-category distractors and negation, even the largest models are confidently wrong, and resampling repeats the error. Models built from different data and architectures rarely fall for the same confounder, so their agreement is a strong label-free signal of the correct target. We present FORUM, a training-free test-time fusion of frozen MLLMs guided by two fixed geometric rules: agreement-based selection keeps the region supported by the most distinct models, and medoid localization returns an actual member box instead of a coordinate average, so one loose prediction cannot shift the answer. Fusing three open MLLMs, FORUM surpasses the 397B-parameter published reference by a relative 5% in mean accuracy on the adversarial Ref-Adv-s benchmark, and a plain averaging ensemble by 15%. The gains transfer to standard RefCOCO+, and a balanced lineup with no dominant member still surpasses the 397B model by 5%. --- ### Physics-Guided Flow-Map Matching for Precipitation Nowcasting Authors: Shunya Nagashima, Takumi Bannai, Makoto Misaizu, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama Published: 2026-09-27 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2609.37487v1 Precipitation nowcasting, generating future radar fields from past observations, is critical for flood warning and disaster response. It is also a demanding benchmark for spatiotemporal generative modeling, with chaotic dynamics, heavy-tailed intensities, and rare high-intensity structures that matter most. Deterministic models minimize a pixel loss and are driven toward the conditional mean, which blurs exactly those structures, while generative models that add a stochastic residual on top of a deterministic backbone inherit the same blur. We propose Physics-Guided Flow-Map Matching (PG-FMM), a conditional flow-map model that decouples predictable advection from uncertain small-scale detail. A frozen Lagrangian advection prior transports the radar field and supplies an explicit motion forecast, and a flow-map generative head, conditioned on the past frames and the prior rollout rather than summed onto it, produces sharp stochastic detail in four sampling steps. The prior serves only as guidance, so the head replaces blurred structure instead of inheriting it. Extensive experiments on four radar benchmarks show that PG-FMM outperforms state-of-the-art methods on 18 of 24 metrics, with the largest gains at heavy-rain thresholds, where the critical success index improves by up to 58.9%. The project page can be found at https://neurogica.github.io/PG-FMM. --- ### PoE-Fuse: Precision-Weighted Expert Fusion for Bi-Temporal Change Understanding Authors: Haruki Watase, Shunya Nagashima, Takayuki Nishimura Published: 2026-09-27 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2609.37485v1 Bi-temporal change understanding, which localizes and characterizes what changed between two satellite images, is central to disaster response and environmental monitoring, spanning change detection, building localization, and damage assessment. Strong vision-language models address these tasks, but adapting them typically requires full fine-tuning or reinforcement learning, which is costly and unstable. We propose PoE-Fuse, a parameter-efficient framework that instead composes frozen foundation experts for geometry, grounding, and language, resampling their features onto a shared spatial grid and training only a lightweight fusion trunk. PoE-Fuse treats the aligned features as Gaussian observations of a latent scene state and fuses them by learned per-cell precision. This product-of-experts estimator strictly generalizes uniform summation and scalar gating, and extends to change fields by composing the precisions of the two timestamps. A single shared trunk solves the three tasks at once, reaching a mean F1 of 59.2%, compared with 40.7% for an instruction-tuned temporal vision-language assistant, and surpassing dedicated change-detection models retrained under the same protocol and training budget. --- ### Probability Contracts: Accuracy, Coherence, and Decisions Across LLM Interfaces Authors: Han Chen, Yingrui Li Published: 2026-09-27 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2609.37470v1 A probability used for a decision should refer to the same event across equivalent requests. We introduce probability contracts, a benchmark connecting exact finite-world posteriors, validated event transformations, and failure-aware decision evaluation. Four model-interface configurations are evaluated on 1,000 worlds. Their assessments differ across accuracy, coherence, and decision loss: Kev has lower aggregate canonical posterior error than Jev, but larger complement and coarsening residuals, with accuracy ordering varying by stratum. Jev's Event and Choice interfaces induce different binary actions on 32.8% of valid pairs at defer cost 0.10. A post-hoc analysis finds that disagreement certifies only 11-52% of mean binary pair error across configurations. An elementary action-region characterization explains when averaging changes decision loss relative to randomly selecting one interface. Although averaging cannot worsen that baseline's expected Brier score, its decision effect depends on the cost and crossed boundaries; the observed same-baseline penalties occur in configurations already worse than always deferring. The benchmark makes these distinctions measurable without treating consistency as accuracy or a score improvement as a decision guarantee. --- ### Relevance Is Not Sufficient Evidence: Detecting Evidence Gaps Before Generation in RAG Authors: Suting Chen, Peichun Hua, Yunming Xiao Published: 2026-09-27 Categories: cs.CL, cs.IR, cs.LG arXiv: https://arxiv.org/abs/2609.37469v1 Retrieval-augmented generation (RAG) grounds large language models in external sources, but retrieved passages often name the right entities without providing the facts needed to answer. Even when instructed to abstain, 12 generators answer 40.0-99.3% of insufficient-evidence questions. Training generators to abstain ties the decision to model weights, may reward answers recalled from parametric knowledge, and still requires a full generator call. Can sufficiency be judged from the question and evidence alone, before any answer exists? We identify pitfalls in constructing insufficient-evidence tests: removing relevant evidence or pairing evidence with unrelated questions can reveal labels through lexical overlap or evidence position. We build a paired benchmark using substitution, deletion, and question-swap constructions that vary answer support while controlling selected surface features, such as word use. Sufficiency can be judged without generating an answer, but no single signal works across all datasets. We introduce RINSE (Relevance Is Not Sufficient Evidence), which combines three signals: whether every part of the question is covered, whether any passage offers an answer, and whether a small language model reading the passages together judges them sufficient. Across six datasets, RINSE ranks sufficient above insufficient evidence with a score of 0.837 (chance 0.5), exceeding the best of 10 prior methods (0.746) and a frontier model queried through an API (0.784). Its weakest dataset scores higher than any other method's weakest (0.684 vs. 0.676). RINSE runs locally before generation, taking 36.5 ms per question on a single GPU. --- ### Event-Only Wingbeat Counting under Camera Motion: A Controlled MuJoCo Benchmark Authors: Zhang Nengbo Published: 2026-09-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.37465v1 Counting completed wingbeats requires identifying individual cycles, including during frequency changes and pauses; estimating a dominant frequency alone is insufficient. Camera motion further mixes target and background brightness changes in event observations. We present a controlled MuJoCo benchmark that separates motion training from event-only image translation compensation. The acquisition contains 324 streams from 24 independent scenes, three flapping geometries, two distances (1.5 and 3.0 m), and static, moderate-motion and stronger-motion views. Fifteen scenes are used for fitting, three for validation and six for held-out testing. A fixed causal temporal convolutional network is evaluated in a matched 2 x 2 ablation with three initialization seeds and compared with ridge, Fourier, autocorrelation and an adapted EEPPR baseline. Under moderate motion, paired motion training reduces count mean absolute error from 31.130 to 3.185 cycles at 1.5 m and from 42.019 to 5.444 at 3.0 m. Adding the tested compensation increases these errors to 4.630 and 10.185, respectively. A Fourier baseline achieves 0.944 cycles at 1.5 m under moderate motion, showing that the neural model is not uniformly best. We report exact-count accuracy and temporally matched cycle F1 alongside count error. These findings support motion-aware training in this small synthetic benchmark, while exposing limits of simple event-background stabilization. They do not establish real-sensor performance, aerodynamic flight, or generalization to unseen vehicle types. --- ### Engineering Efficient Self-Play Chess: Search, Replay, and Throughput Under Limited Compute Authors: Bertil Braun Published: 2026-09-27 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.37447v1 How strong can an AlphaZero-style chess system become under limited training compute when its entire learning loop is engineered for efficiency? We train from random initialization through searched self-play on a single eight-GPU node for 2.5 days. The resulting 6.32-million-parameter model reaches 3,251 benchmark Elo (3,206, 3,297) at 100,000 searches per move (estimated at under five seconds of thinking time) against a fixed-node Stockfish 13 ladder. The run ingests 3.25 million completed games, involves an estimated 100 billion search simulations, and makes 836.6 million training presentations. We investigate search allocation, replay and restart-state selection, policy representation, progressive model sizing, quantized inference, and throughput engineering. Alongside the retained design, we document plausible alternatives that failed to improve the complete learning loop or did not justify their cost. The reported strength is a result of the integrated system, not an isolated Elo gain attributable to any single choice. --- ### Wasserstein Causal Forests for Distribution-Valued Outcomes Authors: Hugo Gobato Souto Published: 2026-09-27 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2609.35898v1 This paper proposes Wasserstein Causal Forests (WCF) for settings in which each unit's outcome is itself a probability distribution. This study also defines finite-grid transformed average and conditional average treatment effects, including a reference-distance contrast that asks whether treatment moves unit-level distributions toward a prespecified benchmark. Simulations cover null effects, location and shape changes, limited overlap, equal-mean but different laws, heterogeneous effects, multimodality, and structural zeros. WCF is most accurate on the conditional-law metric in most reported designs and sharply improves reference-effect estimation in the principal location-and-shape settings, but it is less accurate than the forest baselines for multimodal settings. WCF is applied to the famous Project STAR \citep{word1990state}, revealing that small classes alter more than the mean: they raise within-grade mathematics achievement by $0.161$ standard deviations on average (SE $0.028$); but the gain is not a uniform location shift, it is larger in the upper part of the classroom score distribution ($+0.179$ at the ninetieth percentile versus $+0.091$ at the tenth) and, in descriptive stratum estimates, largest in the schools serving the most economically disadvantaged students (highest free-lunch quartile, $+0.262$, versus $+0.092$ to $+0.164$ elsewhere), while overall dispersion is essentially unchanged. --- ### Self-discovering RL in the Era of Experience: Is Learning History an Asset or a Burden? Authors: Haomin Luo Published: 2026-09-27 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.35897v1 The pursuit of recursive self-improvement (RSI) toward general intelligence is divided between macro-level language model scaling and the interaction-driven principles of "Era of Experience". Yet, any self-improving architecture ultimately rests upon its underlying optimization engine: if general intelligence requires learning from grounded interaction, the reinforcement learning (RL) update rule itself must be capable of cumulative adaptation. While algorithm self-discovery has produced Disco103 that surpassed PPO to achieve SOTA benchmark performance -- its internal update machinery remains an uninspected black box. We present the first causal mechanistic audit of a self-discovered RL rule, structured directly around the five pillars of the Era of Experience: extended horizon, grounded reward scales, continuing streams, within-lifetime change, and exploration depth. By surgically pinning, freezing, and transplanting recurrent states while holding meta-parameters fixed, we test when learning history acts as an asset or a burden. Three findings organize the audit: (1) Recurrent history actively expands usable reward scales, sustaining a six-decade window versus three under zero-pinning. (2) Decoupling historical content from its maintenance reveals that the penalty of mismatched history stems from perpetual clamping; allowing imported state to evolve naturally attenuates this burden. (3) Under environmental change, controlling replay retention reverses the apparent adaptation advantage over DQN, demonstrating that external data turnover can confound internal plasticity. Validated through capability thresholds and ported to a second rule (OPEN), this work grounds macro-RSI ambitions in micro-level learning dynamics, establishing a foundational audit standard for next-generation, self-evolving RL algorithms. --- ### Representational Simplicity and Circuit Size Dissociate in a Threshold-Dependent Way: A Controlled Test via Adversarial Training Authors: Adam Elimadi Published: 2026-09-27 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.35890v1 Sparse-autoencoder decomposability and concentrated feature attribution are increasingly treated as evidence that a model's computation is easier to reverse-engineer. Whether this representational and attributional cleanliness actually predicts a smaller or more tractable causal circuit remains an open question. We test this directly using adversarial training as a controlled instrument: it reliably reshapes internal representations, but this alone does not constitute a test of circuit size. We investigate this question through reverse-engineering complexity: the causal structure required to recover a model's behavior at a fixed level of faithfulness. To our knowledge, this is the first controlled empirical test of whether representational or attributional simplicity translates into causal simplicity at the circuit level. Starting from the same pretrained GPT-2 Small checkpoint, we apply matched standard and adversarial continual training, requiring both conditions to retain competence on indirect object identification and pass independent robustness verification before comparing mechanisms. We then compare the models along three complementary axes: sparse-autoencoder decomposability, SAE feature engagement in task attribution, and the size of faithful circuits recovered from the raw computational graph. The robust model is more SAE-decomposable and engages fewer SAE features in task attribution. Circuit size is regime-dependent: on competence-matched IOI, standard leads or ties below 85% faithfulness, but robust needs substantially fewer edges at high faithfulness (90%, 95%), a pattern established on the primary pair while representational trends generalize across a seven-point sweep and a second corpus. --- ### SINGED: Correct Outputs Do Not Certify Safe Execution in LLM Agents Authors: Xiaoyu Xu, Zi Liang, Minxin Du, Qipeng Xie, Qingqing Ye, Yuyuan Li, Haibo Hu Published: 2026-09-27 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2609.35889v1 Tool-using language-model agents select and execute third-party artifacts. Different implementations can return the requested output while producing hidden execution effects that task-, attack-, or choice-based evaluations may miss. We study functional counterfeits: implementations that match benign alternatives on the requested output but add an effect forbidden by the task contract. We introduce SINGED (Source Integrity and the Nonidentifiability Gap in Execution Decisions for LLM Agents), a controlled benchmark covering five primary and two held-out task families. It varies displayed rank, evidence depth, decision policy, model release, and agent configuration, while task and process oracles verify the artifact and execution path. Across 7,549 audited trials, the randomized-rank study finds counterfeit execution in 45% (27/60) of rank-one trials and none at later ranks. Cross-candidate comparison eliminates shallow failures and reduces layered failures from 15.7% to 4.2%, but leaves dependency failures; its benefit is uncertain on unseen effects and public-package structures. Moreover, seven releases with no counterfeit executions when benign alternatives are available execute the counterfeit in 55/175 single-source cells after alternatives are removed. SINGED thus exposes a rank-, evidence-, and choice-sensitive outcome-to-execution gap: evaluation must connect correct outputs to execution paths. --- ### Agentic Commerce Bench: Measuring Fraud Detection for Agents That Spend Money Authors: Ankit Srivastava, Debjyoti Paul Published: 2026-09-27 Categories: cs.CR, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2609.35886v1 AI agents now hold spend authority and settle payments without per-action human confirmation. The resulting loss is often not a security failure: a counterparty with the correct domain, the correct settlement address and a genuinely delivered service can charge more than it should, and no check keyed on identity will see it. We present three artefacts for measuring and reducing that loss. First, a taxonomy of agentic commerce fraud that separates five observation levels (agent reasoning, wire, settlement rail, counterparty, principal) from the request-level and history-level evidence available at each, and records which levels can observe which attacks. Second, Agentic Commerce Bench (ACB), a benchmark of twenty fraud classes generated from production aggregates, 1,647 catalogued service operations and 1,068 settlements, of which six involve a counterparty that is exactly who it claims to be. Third, gordonguard, an open-source detector stack and offline harness with which an operator can audit an agent configuration, replay hostile counterparties without an account, and run the same detectors inline. Calibrating to a stated false-positive budget on clean training traffic gives a 6.5% clean flag rate, replicated across three independent generations, and leaves eight of twenty classes no better than chance. On the four classes a reasoning layer can observe, a widely used agent security scanner run over its jailbreak-detection panel scores zero on all four, while correctly scoring 1.0 on a jailbreak supplied as a control. A measured median payment of $0.007 places a hard constraint on deployment: one human review costs 143 times the value of the payment it examines. --- ### Learning in the Transverse Subspace: A Minimal Representation for Divergence-Free Operator Learning Authors: Yifei Sun Published: 2026-09-27 Categories: cs.LG, physics.flu-dyn arXiv: https://arxiv.org/abs/2609.35884v1 Divergence-free vector fields are fundamental state variables in incompressible flows and many PDE systems. Redundant parameterizations, including Neural Conservation Law (NCL) potentials, map multiple auxiliary representations to the same physical field. Our experiments show that this redundancy can reduce static representation-fitting error by enlarging the set of equivalent solutions, but the resulting many-to-one mapping does not provide a unique state for operator learning. We introduce a minimal representation that encodes a real \(D\)-component divergence-free vector field on a \(D\)-dimensional domain as a real \((D-1)\)-component field on the same domain. Exploiting the transverse structure imposed by incompressibility in Fourier space, we use a Householder orthogonal transformation to construct the reduced coordinates directly. For periodic and closed impermeable fields, the transform is invertible, isometric, and angle-preserving. For open nonperiodic flows, Fourier extension constructs a compatible periodic field, and a minimum-energy rule selects a unique reduced representation. Neural operators then learn temporal evolution entirely in this reduced space. At inference, the predicted \((D-1)\)-component field is decoded directly into a physical divergence-free \(D\)-component field, without predicting an ambient field or applying post-hoc projection. Experiments on static fitting and temporal prediction reveal a task-dependent trade-off: redundancy facilitates static optimization, whereas unique invertible coordinates provide a well-defined state for temporal dynamics. By removing unconstrained longitudinal or null directions from the learned state space, the proposed formulation achieves lower prediction error and greater robustness while preserving divergence freedom by construction. --- ### CipherGenome: Homomorphic Inference for Genomic Mixture-of-Experts Authors: Guang Yang, Fengchen Liu Published: 2026-09-27 Categories: cs.CR, cs.LG, q-bio.GN arXiv: https://arxiv.org/abs/2609.35883v1 Genome foundation models are growing into sparse mixture-of-experts (MoE) networks whose expert weights no longer fit on the machines that hold the sequences, yet sending a private genome to rented accelerators exposes it: we show that a single server hosting one expert recovers the input nucleotides with 99.8% top-1 accuracy. We present CipherGenome, a protocol that keeps the embedding, attention and router of a 15.1B-parameter MoE genome model on a trusted thin client and outsources every expert projection, 95.8% of the parameters, to untrusted and possibly colluding GPU servers under module-LWE encryption. The design exploits three structural facts: expert layers are linear between two SwiGLU gates, expert weights are public, and GPU integer tensor cores can evaluate a ciphertext-weight product exactly modulo $2^{48}$ in a single GEMM. The client evaluates the nonlinearity exactly and re-encrypts with fresh secrets, so no polynomial approximation or bootstrapping is ever needed. On 72 windows from 12 bacterial genomes, encryption adds $2.54 \times 10^{-4}$ nats per token of KL divergence (95% CI upper bound $3.95 \times 10^{-4}$), below a pre-registered non-inferiority margin and indistinguishable from bf16 inference, while the same inversion attack falls to chance level. A reusable public hint cuts end-to-end latency by 3.54 times, wire compression reduces traffic 6.8 times, per-layer padding reduces routing leakage from 54.9% to 8.9% accuracy, and HE-compatible int4 experts remain non-inferior to their plaintext counterparts. Per expert and token, the server-side cost is more than six orders of magnitude below a CKKS baseline. --- ### GenomeOcean Anywhere: Private WebGPU Inference for Genome MoEs Authors: Guang Yang, Fengchen Liu Published: 2026-09-27 Categories: cs.CR, cs.LG, q-bio.GN arXiv: https://arxiv.org/abs/2609.35882v1 Genome foundation models are most useful where sequences are generated, yet the largest models need datacenter accelerators and a place to send private DNA. We ask whether a 15-billion-parameter genome mixture-of-experts (MoE) model can instead run on volunteers' web browsers, with the experts spread across many untrusted devices, without changing its predictions and without revealing the sequence to any single device. We build a system in which a trusted coordinator runs attention and routing while browser workers run every expert feed-forward network through hand-written WebGPU kernels, and we protect the expert inputs with real-valued Lagrange coded computing: each worker receives only a Gaussian-padded share, computes the expert's linear maps, and the coordinator decodes from any two of three workers. On GenomeOcean-MoE (8 experts, top-2 routing, 24 layers), the browser path matches native llama.cpp at every quantization level, the distributed path stays at the BF16 numerical noise floor (KL 0.0036 nats per token), and an unfitted latency model predicts decode time within 0.74% (median) under emulated wide-area links. We first show that plaintext expert inputs are not private: a probe recovers the token from a single vector at every depth, and one worker can identify the source genome from 300 unordered tokens with 92% accuracy. With coded experts, an adaptive attacker trained on shares falls to the most-frequent-token baseline, one worker's information about each token is bounded below one bit per forward pass, and the fidelity cost stays below the BF16 noise floor; in Chrome, coded decoding runs at 220 to 376 ms per token, depending on how much of the routing is hidden, and continues without replicas when a worker fails. --- ### GenoTrace: Inheritable Watermarks for Genome Foundation Model Distillation Authors: Guang Yang, Fengchen Liu Published: 2026-09-27 Categories: cs.CR, cs.LG, q-bio.GN arXiv: https://arxiv.org/abs/2609.35881v1 Can a genome model retain a detectable record of the synthetic sequences used to train it? We study watermark inheritance through distillation with GenoTrace, a codon-aware extension of green-list watermarking. Two token-level factors modulate the teacher's generation bias using codon position and organism-specific codon usage. The resulting sequences train a smaller student, whose outputs are audited without an active watermark processor. In a three-seed GenomeOcean-500M-to-100M experiment, the joint configuration achieves a mean audit score of 17.88 and 94.5% detection at a fixed threshold. It retains 49.0% detection after key-aware token substitution, compared with 0% for the available single-seed plain-watermark comparator, and 47.0% after combined mechanism-targeted nucleotide edits. Additional experiments establish inherited signal across five organism-conditioned datasets and teacher-student size ratios up to 40. Component ablations and computational sequence-quality assays reveal distinct operating points for detection strength and coding coverage. GenoTrace provides a practical token-level construction and an empirical account of how genomic structure shapes inherited watermark signals. The findings concern shared-tokenizer distillation and the tested editing procedures, with calibration and biological utility treated as separate evaluation requirements. --- ### UOPD: Uncertainty-Aware Intervention for On-Policy Distillation of Multi-Turn Agents Authors: Wenbo Zhang, Pengcheng Xu, Weizhi Du, Jing Zhang, Hengrui Cai Published: 2026-09-27 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.34036v1 On-policy distillation (OPD) trains a student on its own rollouts using dense supervision from a teacher. In multi-turn environments, a mistake at a critical decision step can redirect the subsequent rollout toward poor outcomes. We use low teacher confidence on student actions to select high-uncertainty steps for correction. In a controlled ALFWorld study, a single teacher correction at a low-confidence step improves subsequent student behavior and task success, motivating selective intervention during distillation. We propose UOPD, an uncertainty-aware intervention method for on-policy distillation. At low-uncertainty turns, UOPD executes student actions and applies the standard OPD loss. At high-uncertainty turns, it samples and executes teacher actions and trains the student to imitate them through supervised fine-tuning, which minimizes forward Kullback-Leibler divergence in expectation. UOPD utilizes adaptive uncertainty thresholds to target a scheduled intervention rate. Empirically, we evaluate UOPD across a broad range of agentic tasks, including ALFWorld, WebShop, and Search, demonstrating its superior performance over OPD methods and their variants. UOPD improves WebShop score by up to $15.8\%$ relative to standard OPD. --- ### 3D Point Tracking with State Space Models Authors: Masahiro Ogawa, Qi An, Atsushi Yamashita Published: 2026-09-27 Categories: cs.CV, cs.LG, cs.RO arXiv: https://arxiv.org/abs/2609.34035v1 Tracking any point of a dynamic scene in metric 3D - in absolute meters, not up to an unknown scale - underpins 3D and 4D reconstruction, robot navigation, and autonomous driving, where decisions are made in meters, not pixels. Our objective is a 3D point tracker accurate in those absolute terms and operating within a single commodity GPU, pose-free, monocular budget. Our method rests on one observation: once a point's 2D image trajectory is fixed, the quantity that governs its metric accuracy is the depth along its pixel ray. Rather than learning tracking end-to-end, we therefore compose two frozen front-ends - dense optical flow for 2D correspondence and a monocular metric-depth network for the third dimension - and learn only the residual they cannot supply: that depth, refined by a compact state space model (Mamba-3) conditioned on appearance features (DINOv3). A state space model rather than the transformers the strongest 3D trackers adopt is what makes a single-GPU budget attainable: it summarises a track in a fixed-size recurrent state whose memory cost is constant in the number of frames, whereas attention requires a key-value cache that grows linearly with them. On the TAPVid-3D minival benchmark our best configuration attains the highest absolute metric accuracy among methods evaluated under identical conditions (mean metric Average Jaccard, 0.256), exceeding strong feed-forward trackers, while a companion analysis, reproduced with each competitor's own evaluator, explains why several published trackers lose most of their accuracy under this budget. --- ### ADPTNet: Adaptive with Prescriptive Timescales Non-Linear SSM for Sequence Modelling Authors: Matei-Ioan Stan, Oliver Rhodes Published: 2026-09-27 Categories: cs.NE, cs.AI, cs.DC, cs.LG arXiv: https://arxiv.org/abs/2609.34034v1 A central aim of neuromorphic computing is to provide a viable alternative to highly energy-intensive Transformer-based AI. However, efficient alternatives struggle to capture the set of qualities that have secured the Transformer's status as the de facto standard in sequence modelling. Any realistic contender must be data-adaptive, able to capture long-range dependencies, and GPU-parallelisable, but also non-linearly recurrent to enable complex reasoning. Based on evidence suggesting the auditory cortex operates on fixed timescales, this work proposes the ADaptive with Prescriptive Timescales Network (ADPTNet) as a potential solution to achieving all four properties simultaneously. ADPTNet is built around local topological conjugates, obtained by a novel combination of linear attention and Riemannian optimisation, applied to static global dynamics. This enables non-linear yet predictable long-term behaviour. Dynamical systems theory proofs provide theoretical guarantees for the parametric control of ADPTNet's timescales (its Lyapunov spectrum). ADPTNet improves performance on Selective Copying over Hawk, the existing method balancing long-range memory and adaptability, while also improving state tracking over linear SSMs like Mamba. On sequential CIFAR-10, ADPTNet matches linear SSM accuracy and outperforms existing selective models (incl. the Transformer), using fewer parameters. We also introduce a neuromorphic SpikingADPTNet, which achieves a new state-of-the-art accuracy on the Spiking Speech Commands dataset ($83.56\%\pm0.15$). Finally, ADPTNet's constant timescales enable two efficient, Jacobian-free extensions to the DEER parallel simulation algorithm (Conv and Forward DEER) that retain the same average convergence. Conv DEER adds no computational overhead beyond the network's forward pass and enables non-linear RNN parallelisation via iterated convolutions for the first time. --- ### Faithful Activation Verbalization: Reducing Hallucinations in LLM Representation Interpretation Authors: Haiyan Zhao, Zirui Hei, Wei Shi, Huiqi Deng, Na Zou, Mengnan Du Published: 2026-09-27 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.34033v1 Activation verbalization methods such as Activation Oracle and Natural Language Autoencoders decode hidden representations of large language models into human-readable natural language. However, existing methods can produce incomplete or hallucinated descriptions, making their activation verbalizations difficult to trust and use reliably in practice. To this end, we introduce AVPO, a two-stage framework that first reconstructs source text from a hidden activation and then evaluates the resulting text with a separate frozen question-answering model, yielding an explicit and inspectable intermediate readout. We further optimize the inverter with direct preference optimization (DPO), using rewards that capture both semantic recoverability and lexical fidelity. Across six text families, AVPO improves gist- and detail-level information recovery over the strongest baseline by up to 17.1 and 9.3 percentage points, respectively. Crucially, the gains arise from preference optimization rather than fine-tuning on selected reconstructions alone, enabling compact cross-model inverters to surpass donor-matched question-conditioned verbalizers while improving both semantic recoverability and lexical fidelity. Moreover, out-of-distribution case study shows that AVPO better recovers high-level semantics while fabricating fewer details. --- ### Re:Cognize -- Open-Set Comic Character Re-Identification Authors: Aaditya Baranwal, Madhav Kataria, Yogesh S Rawat, Shruti Vyas Published: 2026-09-27 Categories: cs.CV, cs.MM arXiv: https://arxiv.org/abs/2609.34032v1 A manga reader meets a character on one page and knows them on sight a hundred pages later, without ever being handed a cast list. Re-identifying comic characters demands the same, open-set and sequential: pages arrive as a stream in reading order, new faces appear before anyone names them, and the cast is assembled as the story is read. $\textbf{Re:Cognize}$ evaluates recognition as the story is read, not against a cast handed over in advance: four protocols on one query stream, from closed-set retrieval to a cast the model must build and grow itself. The surprise is where models fail. Recognising is close to solved: one reference image per character already ranks as well as a gallery built in advance. Knowing what to believe is not: a model that adds its own matches makes its cast worse, while the same growth with correct labels would gain over twenty points of top-1 accuracy. The bottleneck is acceptance, not vision, and one comparison decides it: an addition pays exactly when it is right more often than the cast already was on the queries it takes over. The comparison has nothing to fit, and measured on half of a new corpus it calls the other half correctly. $\textbf{ReCast}$ puts it to work with nothing fitted on data: a cast sheet of one running average per character, grown only where the page itself vouches for a crop. It recovers a third to two thirds of what perfect labels would, depending on whether the cast starts from random examples or from first appearances. Re:Cognize measures whether a model can read along; ReCast is a cast that does. Our claims are on identity maintenance, recognising characters already met; the emergence of new ones is measured as a diagnostic under a fixed reference rule, and we propose no method for it. --- ### Posterior Regimes and Latent Deception: Variational Bayesian Inference in Hidden Markov Models for Sequential Fraud Detection in Financial Transactions Authors: Joseph Uririoghene Obukofe, Anthony O'Hare, Chioma Sandra Dike Published: 2026-09-27 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2609.34031v1 We present a three-tier progression of Hidden Markov Models: maximum-likelihood (Baum-Welch), variational Bayesian (VBEM), and a neural variational extension (Neural VBEM), that model each customer's transaction history as a trajectory through a small number of latent behavioural regimes, one of which is empirically identified as fraud-associated. The Neural VBEM HMM replaces the fixed Gaussian-multinomial emission family with a learned encoder, compressing a 741-dimensional transaction representation into a 64-dimensional latent space in which the VBEM HMM's posterior operates; a UMAP projection of this space reveals that the discovered regimes are not discrete clusters but ordered segments of a single continuous behavioural manifold, with confirmed fraud concentrated at its extreme. We show that the model's natural output, that is, the posterior probability of regime membership, is routinely mistaken for a fraud probability, and quantify the resulting miscalibration (the regime-membership interpretation error, MRIE); a corrected posterior-predictive score, closes most of this gap. We further distinguish batch (smoothed) inference, which uses look-ahead unavailable at deployment time, from filtered (forward-only) inference, and report both. On IEEE-CIS transaction data, the neural tier achieves a 14.4$\times$ fraud enrichment in its identified regime; while its AUPRC trails a discriminative XGBoost baseline, we show this gap is structural and not incidental, and argue the model is best positioned as a calibrated triage and interpretability layer rather than a drop-in ranking replacement. --- ### Uncovering shortcut learning in audio classifiers by discovering recurring concepts in temporal explanations Authors: Cecilia Bolaños, Luciana Ferrer, Magdalena Fuentes Published: 2026-09-27 Categories: cs.SD, cs.AI arXiv: https://arxiv.org/abs/2609.34030v1 Correlations between events in machine learning datasets may result in shortcut learning, where models learn to predict the target event based on the presence of a correlated event. When these correlations are spurious -- arising from data collection artifacts -- models are likely to perform poorly in practice. We propose a pipeline to uncover shortcut learning in audio classifiers by discovering recurring concepts in their temporal explanations. Specifically, we isolate audio segments that explain classifier decisions, caption them with an ensemble of Large Audio-Language Models, and use a Large Language Model to extract recurring concepts. The resulting concepts can be audited by humans to uncover potential shortcut learning. We evaluate our framework using datasets curated from AudioSet Strong, controlling for the presence or absence of spurious correlations. Results show that this approach reliably uncovers learned shortcuts, such as the model relying on the presence of "laughter" to predict "applause". --- ### Structure-Adaptive Tree Field Integrators Authors: Millend Roy, Soham Samal, Ivan Zelich, Krzysztof Marcin Choromanski Published: 2026-09-27 Categories: cs.LG, cs.CV, cs.DS, math.NA, math.OC arXiv: https://arxiv.org/abs/2609.34025v1 We present a new class of near-linear algorithms for efficiently integrating general tensor fields defined on trees with distance dependent kernels, the Structure-Adaptive Tree Field Integrators (STAD-TFIs). STAD-TFIs exploit the tree's underlying structure through decompositions built around path backbones and single vertex separators, and use two-dimensional fast Fourier transforms to compute interactions jointly. By exploiting this structural information, STAD-TFIs achieve more computationally efficient integration than their regular efficient tree field integrators (TFI) counterparts. We provide a detailed theoretical analysis of our proposed approach and complement it with an exhaustive empirical evaluation, ranging from speed tests on synthetic trees, through accelerated Sinkhorn-based relaxations of the Optimal Transport algorithms on real meshes, to Topological Attention Transformers for vision tasks. To the best of our knowledge, we provide some of the first results showing that efficient to compute and accurate relaxations of the geodesic Sinkhorn-based solutions of the Optimal Transport problem can be derived by applying fast TFI methods. --- ### Jev in Medicine: A Benchmark Evaluation. Preliminary Results Authors: Alfredo Madrid-García, Beatriz Merino-Barbancho Published: 2026-09-27 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.34024v1 Jev is a non-generative "System One" model that assigns probabilities to predefined answer options and cannot answer outside them. Its accuracy and calibration on medical question-answering and case-based diagnostic-reasoning tasks are unknown. We evaluated Jev 1.13 on four medical benchmarks: MetaMedQA, PubMedQA, DiagnosisArena-MCQ and the NEJM Case Challenges. GPT-6 Sol, with (medium) and without reasoning, was the reference. The primary outcome was top-1 accuracy; key secondary outcomes were calibration, selective prediction and recognition of unanswerable questions. All 8,469 requests returned a valid answer. Jev's accuracy was similar to that of GPT-6 Sol with medium reasoning on PubMedQA (78.4% vs 78.2%;), lower on MetaMedQA (74.8% vs 82.7%) and much lower on DiagnosisArena-MCQ (59.8% vs 82.4%;) and the NEJM cases (61.8% vs 82.4%). On MetaMedQA, Jev's probabilities were the best calibrated (expected calibration error 0.063 vs 0.146), and its answers with a probability of at least 0.9 (52.9% of questions) were 93.4% accurate, but GPT-6 Sol was as accurate when it accepted a similar proportion of questions. On DiagnosisArena-MCQ, Jev's probabilities discriminated poorly (AUROC 0.645 vs 0.768). Of the 162 questions whose correct answer was "I don't know or cannot answer", Jev chose that option for 10.5% (GPT-6 Sol, 8.6%). Median latency was 0.27-0.31 s; all 2,823 items cost USD 0.08. Jev was fast and inexpensive, and its accuracy was similar to that of a frontier LLM on research abstracts but lower on examination questions and much lower on complex diagnostic cases. Task-specific validation is required before clinical use. --- ### Position Aware Layer Queries for Test Time Training in Vision Language Models Authors: Rajat Modi, Priyank Pathak, Xin Liang, Yogesh Singh Rawat Published: 2026-09-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.34021v1 Test-Time Training (TTT) adapts models to incoming test samples (e.g. out-of-distribution, (OOD)) when conventional fine-tuning is infeasible. Existing TTT methods for Vision-Language Models (VLMs) create supervision from several augmented views, each requiring forward (and often backward) passes through the entire VLM, incurring substantial computational cost. We observe that one forward pass with all the intermediate layer outputs already yields far more signal than the final embedding from all augmentations. We introduce Layer Query Network (LQN), a lightweight approach that can adapt a frozen VLM (teacher) in a single forward pass of the VLM via a small model (student). LQN uses Position-Aware Distillation (PAD) to mimic the teacher VLM's intermediate-layer spatial tokens by querying spatial coordinates of intermediate tokens. LQN additionally relies on Location Consistency Regularization (LCR), a self-supervision technique, replacing expensive O(H x W) image augmentation with O(1) coordinate sampling. Integrating these, LQN i) adapts and improves zero-shot CLIP ViT-B/16 by 9.8% Top-1 on OOD ImageNet, ii) outperforms the previous best GS-Bias on fine-grained classification by 3.9% Top-1, iii) achieves faster convergence than TPS for CLIP ResNet-50 (47 mins vs 55 mins), iv) generalizes adaptation to VLMs like SigLIP, EVA-CLIP, and CoCa, and lightweight students like MLP, ResNet, VGG, and v) extends to panoptic, instance, and semantic segmentation. --- ### SR4-Fit: A Unified Interpretable Rule-Based Machine Learning Framework for Informative and Trustworthy Decision-Making Authors: Shyam Sundar Murali Krishnan, Dean Frederick Hougen Published: 2026-09-27 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.34019v1 In many high-stakes applications, machine learning is dominated by black-box models that require post hoc explanations to justify their predictions. These explanations are often unreliable because they do not reflect the model's actual computations, limiting accountability and trust. A natural alternative is to use models that are interpretable by design. However, existing rule-based approaches, such as RuleFit and decision trees, while transparent, often lack stability and predictive strength, reinforcing a perceived trade-off between traditional performance measures and model understandability. To address this, we propose Sparse Relaxed Regularized Regression Rule-Fit (SR4-Fit), an intrinsically interpretable algorithm for both classification and regression that produces compact and stable rule sets without sacrificing performance. Using demographic data from the U.S. Census Bureau's American Community Survey, SR4-Fit predicts U.S. House election outcomes with high accuracy and interpretability while uncovering demographic interactions missed by black-box models. We further validate SR4-Fit across fourteen benchmark datasets (six classification and eight regression), where it outperforms existing rule-based methods, including RuleFit and decision trees in terms of accuracy, stability, and compactness while remaining competitive with black-box models in predictivity. These results demonstrate that interpretability and predictive reliability need not be mutually exclusive, offering a practical and transparent alternative for high-stakes decision-making. --- ### Estimate, Don't Imitate: Reusing Differentiable State-Based Policies for Visuomotor Control Authors: Denis Shcherba, Adrian Abel, Eckart Cobo-Briesewitz, Paul Mattes, Wojciech Samek, Marc Toussaint Published: 2026-09-27 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2609.34018v1 Simulation-trained manipulation policies can exploit privileged state information to learn effective contact-rich behaviours, but deployment requires acting from partial observations such as noisy camera images. A common solution is teacher-student distillation, in which a visuomotor policy is trained to reproduce the actions of the privileged expert. This requires the student to jointly infer the task-relevant state and relearn the expert's action mapping that is already available. An alternative is to reuse the state-based expert and learn only a perceptual interface that reconstructs its missing state inputs. However, minimising the state estimate error alone does not necessarily minimise the downstream control error induced by these estimates. To bridge this gap, we train a visual state estimator using both direct state supervision and an action-consistency loss backpropagated through the frozen, differentiable expert. A scheduled objective first establishes a physically meaningful state estimate and progressively emphasises errors that affect the expert's actions. Across five goal-conditioned manipulation tasks, retaining the expert consistently outperforms direct pixel-to-action imitation from the same expert demonstration corpus. We further demonstrate sim-to-real transfer on a physical Panda robot, achieving 76% success without retraining the underlying expert. --- ### Maat: Independent Deterministic Contract-Based Governance for Multi-Agent LLM Workflows Authors: Uliana Elina Published: 2026-09-27 Categories: cs.SE, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2609.34017v1 Large-language-model multi-agent systems (LLM-MAS) introduce a characteristic reliability problem: an error produced by one agent can be accepted as context by downstream agents and propagate across the workflow. Many proposed safeguards rely on learned or LLM-based judges whose verdicts are themselves probabilistic; we ask whether a deterministic layer can instead stop contract-detectable handoff defects. We present Maat, a runtime governance layer that validates agent-to-agent handoffs against a versioned workflow contract, or anchor, with no language model in the validation or scoring path. We evaluate it in six controlled domain workflows (6-15 agents, 522 trials) with injected data-level defects and a deterministic seven-check rubric. Version 1 reported gains in all six workflows (2.9-26.5%). A post-publication audit found that three benchmark scorers credited any early halt as a prevented defect. On paired trials where the governed run completed or halted on a finding attributable to a verified defect, the rubric score changes by +7.7% to +29.1% in five workflows and is flat in software development; model-call cost falls 17-53% where attributable halts occur early. A hand review of all 94 governed-arm halts found 35 false alarms (37%), caused by validator defects rather than model behaviour; counting those halts as failed work, the governed arm scores below the ungoverned arm in four of six workflows. The results support deterministic handoff validation for contract-expressible defects and show that validator configuration and halt attribution must themselves be tested; they do not establish universal correctness, hallucination detection, or model-independent effectiveness. --- ### A Computer Vision Approach to Visual Fraud Detection in Phishing Websites Using YOLOv8 Authors: Basil Sajid Shaikh, Hajar Homayouni Published: 2026-09-27 Categories: cs.AI, cs.CV arXiv: https://arxiv.org/abs/2609.34015v1 Phishing remains one of the most common vectors for financial and identity fraud, and most detection systems still rely on inspecting a page's URL, HTML markup, or domain registration history. These signals are easy for an attacker to rotate or obfuscate, and they say very little about what actually convinces a victim to hand over a password or a card number: the way the page looks. This paper describes a visual, image-based approach to phishing detection that treats a rendered webpage the same way a human eye would, as a picture that either matches a trusted brand or doesn't. A YOLOv8 convolutional neural network was trained to classify full-page website screenshots as phishing or legitimate based on layout, logo placement, color scheme, and login-form structure, rather than on text extracted from the page. The system reached 92% classification accuracy on a held-out test set, processed a single screenshot in roughly 100 milliseconds, and, after a round of data augmentation aimed specifically at lighting, compression, and scaling variation, cut the false-positive rate by 11% relative to the pre-augmentation baseline. The paper walks through the dataset construction, the augmentation strategy, the model architecture and training setup, and the resulting performance, and closes with a discussion of where this kind of visual detector fits alongside, rather than instead of, existing URL- and content-based defenses. --- ### LTV-CTDNet: Compositional Turning Decomposition for Short-Term Turning-Movement Forecasting Authors: Md Atiqur Rahman Mallick, Kamrul Hasan, Robert T. White Published: 2026-09-27 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.34014v1 Short-term turning-movement forecasts can support signal control and corridor operations, but unconstrained neural networks may produce physically impossible negative counts or outputs that are not explicitly tied to an approach-demand total. This study introduces the Linear Temporal-Variable Compositional Turning Decomposition Network (LTV-CTDNet), a forecasting framework designed to combine competitive accuracy with structurally admissible outputs. LTV-CTDNet was evaluated using seven months of 15-minute LiDAR observations from eight monitored corridor locations in Nashville, Tennessee. Its lightweight encoder combines recent turning-movement history, weekly time-slot embeddings, and location embeddings. The Compositional Turning Decomposition framework separately predicts nonnegative approach totals and within-approach turning proportions, then reconstructs movement forecasts from these components. Among the evaluated predefined configurations, LTV-CTDNet achieved a movement-level MAE of 1.8189 and RMSE of 3.8072. Its accuracy gains over the strongest sequence models were modest, but it produced no negative forecasts, while unconstrained learned models generated negative values in approximately 10.6% to 29.2% of raw forecast cells. The framework enforces nonnegative outputs and exact agreement between each model-predicted approach total and the sum of its component movements by construction, providing directly interpretable forecasts without clipping or coherence correction. --- ### When Known Physics Helps Neural PDE Models: Residual Constraints Out-Regularize Generic Priors for Nonlinear Dynamics Authors: Zahra Farazpay, Aniruddha Bora Published: 2026-09-27 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.34012v1 Neural PDE surrogates increasingly incorporate structural priors, yet it is often unclear whether their gains arise from physics-specific information or simply from regularization and training choices. We evaluate several such priors under a common protocol against a matched from-scratch neural operator baseline. Our central result is that a known-equation residual consistently outperforms the best generic regularizer at equal tuning budget. At fixed capacity this benefit appears across linear and nonlinear PDEs, but a capacity sweep reveals a sharp distinction: the advantage persists and grows for Burgers, KdV, and Allen-Cahn, while collapsing toward or below parity for linear heat and advection-diffusion. Thus, the durable value of the residual is specific to nonlinear operators. We further falsify a pre-registered hypothesis that the benefit is activated only by data sparsity: the residual remains advantageous even under full supervision. Its usefulness does, however, have a clear boundary. Under grid under-resolution, nonlinear coarse fields no longer satisfy the naive governing-equation residual, and enforcing it becomes actively harmful. In contrast, cross-family pretraining and in-context conditioning fail to outperform the strong from-scratch baseline in the regime studied. Together, these results identify when known physics provides non-redundant information to neural PDE models, when it does not, and when enforcing it introduces bias. --- ### ZeroBot: Learning from Scratch in Minutes with Generative Real2Sim Authors: Ivan Kapelyukh, Xiaohan Zhang, Stephen James, Laura Herlant, Edward Johns Published: 2026-09-27 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2609.34010v1 We present ZeroBot, a real2sim framework for learning a robot manipulation task from scratch in minutes under challenging conditions: zero human demonstrations, zero policy pre-training, and zero known object models. Given only a single view of an object and a goal pose for that object, ZeroBot uses image-to-3D generative models to obtain a complete object mesh, which is used in simulation for large-scale parallel reinforcement learning. To accelerate training, we introduce an action space which leverages the generated geometry and learned value function to sample states involving robot-object contact. When evaluated on real-world tasks including grasping, pushing, articulated object interaction, and multi-stage manipulation, ZeroBot achieves an 87% success rate with an average training time of 119 seconds. These results show the value of using image-to-3D models in a real2sim framework for rapid, autonomous robot learning. --- ### Fisher-Informed Recalibration for Feedback-Based On-Policy Self-Distillation of LLMs Authors: Seohyun Lee, Dong-Jun Han, Seyyedali Hosseinalipour, Christopher G. Brinton Published: 2026-09-27 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.34009v1 Feedback-based on-policy self-distillation has emerged as a promising approach for enabling foundation models, more specifically Large Language Models (LLMs), to learn from their own outputs under external feedback, with a single model serving as both teacher and student. However, such methods can exhibit unstable optimization, conducive to performance collapse during training. To address this limitation, we propose FIRE (Fisher-Informed REcalibration), a dual-branch framework that recalibrates the supervision applied to correct and incorrect on-policy outputs during fine-tuning. For correct responses, FIRE replaces self-distillation with re-weighted on-policy SFT, while for incorrect ones FIRE identifies feedback components that disproportionately influence the teacher-induced update and recalibrates the feedback-conditioned target accordingly. Both branches are influenced by a token-level radius derived in part from a softmax Fisher trace. FIRE separates which direction feedback should move the model from how far the model should move in that direction, while leaving well-behaved feedback supervision unchanged. Our experiments demonstrate that FIRE provides substantially more stable self-distillation while maintaining strong downstream performance, particularly in settings where standard feedback-conditioned distillation becomes unstable. --- ### EHRAdapt: Adapting Pretrained Language Models to Electronic Health Records with Semantic Priors for Rare Clinical Events Authors: Andre R Goncalves, Vincent Liu, Priyadip Ray Published: 2026-09-27 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.34007v1 Electronic health records (EHRs) encode clinical histories as (time, modality, code) tuples, whereas pretrained language models expect text tokens. Serializing them as text inflates sequence length and redundantly encodes structure. We introduce EHRAdapt, an adapter that maps tuples directly into a frozen language model's embedding space. Modality receives a learned embedding, time gaps enter through learned attention biases, and event codes receive dedicated vectors. Learning event vectors is the central challenge: clinical vocabularies are long-tailed, leaving rare events too few observations for reliable estimates. EHRAdapt therefore represents each event vector as the sum of a semantic prior and an evidence residual. The prior is a frozen embedding of the event's clinical description from a biomedical language model trained on clinical ontologies, mapped into the model's input space by a shared learned projection, so it supplies clinical meaning even when observations are scarce. The residual, a learned low-rank event-specific correction, refines it as evidence accumulates. We run continued pretraining on about 4 million patients' records with three frozen LLM backbones (OLMo2 1B, Llama3.2 1B, and OLMo2 7B), training only the adapter (0.1--0.6% of all parameters). The full adapter outperforms all ablations in held-out next-event prediction on every backbone. Removing the semantic pathway hurts rare events over ten times more than the most frequent ones, whereas removing the residual hurts overall prediction but improves it for the rarest events. On reportable infectious-disease and syndromic downstream classification tasks, EHRAdapt outperforms text-based LLM and count-based baselines, and both pathways improve rare-disease discrimination. The two pathways therefore play complementary roles, visible only when results are broken down by event frequency rather than averaged. --- ### RICE-Alpha: Reliability-Informed Correction with Event Graphs for LLM-Agent Stock Forecasting Authors: Tong Liu, Lanmiao Liu, Xiang Hu Published: 2026-09-27 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.34004v1 Equity-relevant news evolves through temporally dependent corporate events, making historical information useful only when event continuity, information availability, and transition reliability are modeled. Existing LLM-based financial agents incorporate historical evidence, yet they provide limited support for preserving issuer-specific chronology under point-in-time constraints and for identifying when historical transitions contribute information beyond the current forecast. We present RICE-Alpha (Reliability-Informed Correction with Event Graphs), a point-in-time stock-scoring framework that separates a history-aware multi-view Base Alpha from a reliability-calibrated residual correction derived from historical event continuation. A Multi-Tier Memory Layer grounds news interpretation in temporally eligible issuer-specific history, while a Typed Event Agent constructs event states whose successor relations are formed within issuers and pooled across firms only after valid local pairing. Matured transitions are calibrated by their empirical reliability, and the resulting graph signal is residualized against the Base Alpha and technical view to obtain the RICE Delta. On daily Nasdaq-100 and Hang Seng Index panels from 2024 to 2026, RICE-Alpha achieves the strongest results among the evaluated LLM-based agents and momentum across four predictive and four portfolio-level metrics. Its ICIR more than doubles that of the strongest baseline, while net Sharpe ratios reach 1.656 and 1.725 in the U.S. and Hong Kong, respectively. U.S. ablations further show significant reductions in IC and RankIC after Holm adjustment when major components are removed. These results indicate that historical event continuation adds incremental information when it is temporally grounded, reliability-calibrated, and introduced as a residual correction to a multi-view forecast. --- ### T-SNN: Temporal Simplicial Neural Network for EEG Decoding Authors: Nikita Malik, Shubhajit Roy, Mohit Kataria, Isuru Herath, Suraj Yadav, Inés García-Redondo, Dhananjay Bhaskar Published: 2026-09-27 Categories: cs.LG, q-bio.NC arXiv: https://arxiv.org/abs/2609.34002v1 Decoding brain states requires models that capture both the evolution of neural activity and interactions among groups of brain regions. Existing EEG methods often treat recordings as multivariate time series or represent functional connectivity with pairwise graphs, leaving dynamic higher-order interactions largely unmodeled. We introduce the Temporal Simplicial Neural Network (T-SNN), which represents EEG recordings as sequences of evolving simplicial complexes. By combining simplicial convolutions with recurrent updates, T-SNN jointly learns higher-order interactions and their temporal evolution. On the seven-class SEED-VII emotion recognition task, T-SNN outperforms convolutional, recurrent, graph-based, and Transformer methods in both trial-wise and cross-subject evaluations. Incorporating eye-movement features further improves performance, demonstrating the framework's potential for multimodal brain-state decoding. --- ### MetaSampling: Making Frame Samplers Efficient for Long-Video Question Answering Authors: Ashim Dahal, Bikramjit Banerjee Published: 2026-09-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.33998v1 Frame selection is an important component of long-video question answering (VQA) with Multimodal Large Language Models (MLLMs). Existing frame-selection methods improve over simple top-$k$ embedding retrieval and uniform sampling, but are typically applied under a fixed global selection budget. We introduce \textbf{MetaSampling}, a training-free, plug-and-play sampling strategy that can be applied on top of existing frame selectors. MetaSampling improves downstream VQA efficiency by dynamically reducing the number of frames passed to the MLLM while preserving, and in some cases improving, answer accuracy. We evaluate MetaSampling across 36 paired frame-selector--MLLM-backbone--VQA-benchmark configurations. MetaSampling reduces the number of selected frames in all 36 configurations and improves accuracy in 25 of them, yielding an average frame reduction of $8.9\%$ while slightly improving accuracy overall. --- ### UnfoldCRF: Structured Mask Refinement with Image-Conditioned Latent Regions Authors: Chunming He, Rihan Zhang, Lei Xu, Guanyi Qin, Chengyu Fang, Longxiang Tang, Fengyang Xiao, Sina Farsiu Published: 2026-09-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.33996v1 Learned mask refiners improve segmentation accuracy, but it is hard to tell how much of the improvement comes from explicit structure rather than from extra capacity, and whether it holds up when the mask generator or its error distribution changes. UnfoldCRF treats refinement as inference in a conditional random field over pixel labels and latent region variables. Its energy has a corrected unary term, learned local pairwise interactions, and image-conditioned latent-region consistency, with a null state that lets a region with weak label agreement withdraw from the consistency term; inference unrolls damped mean-field updates on this one energy. To isolate the effect of structure, we compare against recurrent black-box refiners that read the same inputs and receive the same parameter budget, stage count, and supervision. On COD10K, UnfoldCRF beats the strongest matched control by 1.0 $F^ω_β$ point, improves all four COD metrics, and lowers the fraction of images made worse from 11.7\% to 8.5\%. Under a train-once protocol over five datasets and several mask sources, the 2.6M-parameter variant gains 4.2 mean $Δ$IoU against 2.0 for its control, and a variant built on frozen DINOv2 features matches the strongest foundation-model refiner with about a seventh of its resident parameters while staying ahead of its own control. On mask generators never seen in training, the gain is 2.0 $F^ω_β$ points against 0.6 for the control. Zeroing individual messages shows where the corrections come from: the pairwise messages mostly fix boundaries, the region messages mostly fix non-boundary errors. Code and supporting materials will be publicly released. --- ### A packet-level digital hardware twin for commissioning megahertz diagnostic edge AI and plasma control system integration in tokamaks Authors: Semin Joung, Abhilasha Dave, Luca Scomparin, Filipp Khabanov, Zheng Yan, Benedikt Geiger, George McKee, Ryan N. Coffee, David R. Smith Published: 2026-09-27 Categories: physics.plasm-ph, cs.AI arXiv: https://arxiv.org/abs/2609.33994v1 High-bandwidth plasma diagnostics increasingly provide inputs to machine learning and signal-processing algorithms intended for real-time tokamak control, but the complete path from diagnostic sampling to control-system handoff is difficult to commission because of their sampling rates. We develop a packet-level digital hardware twin for the megahertz diagnostic edge-AI architecture. The simulator represents a 64-channel, 1 MHz beam emission spectroscopy (BES) diagnostic embedded in a 96-channel dual-carrier acquisition system, two 48-channel streams with SPAD0 sample counters, 10 GbE Hardware UDP transport, packet loss and network jitter, FPGA parsing and dual-carrier alignment, causal preprocessing and edge inference, a compact Ethernet result packet, receiver-side shared state, and a 1 kHz PCS-like control cycle. Binary UDP payloads and PCAP files are generated rather than emulating transport only at the array level. With a baseline of 20 samples per packet, each carrier generates 50,000 packets s$^{-1}$ and 100 MB s$^{-1}$ of user payload. A 110 ms reference run produces 11,000 HUDP packets; an intentionally dropped 20-sample packet is detected by the sample-counter continuity logic and invalidates the two overlapping 128-sample inference windows without silent interpolation. For valid windows, the configured engineering latency model gives a median last-input-to-shared-memory latency of 91.6 us and a 99th percentile of 108.1 us. A separate operating-system loopback test sends binary FPGA-result datagrams through a UDP receiver into POSIX shared memory and preserves packet sequence and CRC for 20/20 packets. Interactive GUI interfaces expose timing, packetization, network faults, inference thresholds, and control-state inspection. The framework provides a reproducible environment for testing diagnostic-to-accelerator interfaces and fail-safe behavior for deployment on fusion devices. --- ### ASTRA: ADMM-Accelerated Topology Reconfiguration for Dynamic Satellite Constellations Authors: João Norberto, Ricardo Ferreira, Cláudia Soares Published: 2026-09-27 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.33993v1 Dynamic topology reconfiguration is central to the reliability and efficiency of large satellite constellations, yet many existing approaches rely on idealized assumptions such as full constellation deployment or uniform orbital spacing. We present Adaptive Satellite Topology via Regret-Aware learning (ASTRA), a theoretically-grounded framework for dynamic satellite topology reconfiguration that builds on an online learning formulation and makes it computationally practical. ASTRA combines an ADMM-based offline solver with efficient online updates for both online gradient descent and online conditional gradient, yielding markedly cheaper constrained updates than generic optimization pipelines. On the theory side, we show that for a relevant class of entry-wise nonzero utility matrices, the objective is strongly convex, which yields logarithmic static regret for online gradient descent, and we further instantiate known dynamic-regret guarantees under inexact ADMM inner loops. Empirically, ASTRA matches or improves topology quality, presenting a good trade-off with computational time on synthetic constellations, and it remains effective on real Starlink data under partial deployment and non-uniform spacing, where idealized structural assumptions break down. These results position ASTRA as an efficient and theoretically grounded approach to topology reconfiguration in realistic Low Earth Orbit networks. --- ### A Multi-Dataset Benchmark of YOLO-Based Weed Detection in Precision Agriculture Authors: Hristina Zdraveska, Vlatko Spasev, Ivica Dimitrovski, Ivan Kitanovski, Petre Lameski Published: 2026-09-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.33991v1 Weed detection is an important component of precision agriculture, enabling site-specific weed management and reducing unnecessary herbicide use. Although deep learning methods have achieved strong results for crop and weed detection, many studies rely on single-dataset evaluation, making it difficult to assess robustness across different agricultural domains. This paper presents a multi-dataset benchmark of deep object detectors for weed detection in precision agriculture, with a focused evaluation of YOLO26 models. We evaluate nano, small, and medium variants on seven public weed-detection datasets covering different crops, weed species, field conditions, acquisition setups, and annotation protocols. The models are compared in terms of detection accuracy, model complexity, inference latency, FPS, and model size. In addition to in-dataset evaluation, we investigate cross-domain generalization using a unified one-class weed setup and evaluate multi-source training using the combined training subsets from all datasets. The results show that YOLO26 achieves strong in-dataset performance, with YOLO26m obtaining the highest average accuracy and YOLO26s providing the best practical accuracy-efficiency trade-off. However, cross-domain performance decreases substantially, with YOLO26s dropping from an average in-domain mAP$_{50:95}$ of 0.603 to 0.148 in the off-domain setting. Multi-source training improves performance on several datasets, but does not fully eliminate domain shift. Overall, the benchmark highlights the importance of dataset diversity, domain similarity, and target-domain adaptation for robust weed detection in real-world precision agriculture applications. ---