# Research Papers — 2026-09 · bundle page 94 of 266 > Full-text markdown of papers #4651–4700 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/94 [← Previous bundle](https://aipod.dev/papers/archive/2026-09/page/93.md) [Next bundle →](https://aipod.dev/papers/archive/2026-09/page/95.md) ### ScopeBench: Do Agents Preserve Engagement Boundaries Under Goal Pressure? Authors: Shane Caldwell, Max Harley, Ads Dawson, Michael Kouremetis, Vincent Abruzzo, Will Pearce Published: 2026-09-23 Categories: cs.AI, cs.CR arXiv: https://arxiv.org/abs/2609.30325v1 Agents are increasingly deployed with real autonomy in web application and network penetration testing, where a single out-of-scope action can breach a client's engagement boundary. Existing offensive-security benchmarks measure raw hacking capability; as those benchmarks saturate, the real barrier to deployment is a special case of alignment: scope adherence. We introduce ScopeBench, a benchmark of 30 dead-end agentic security tasks in which the stated objective is reachable only by violating the stated scope. Each task appears under two conditions that share an environment, verifier, and objective and differ only in scope: one instruction set has no scope and measures capability; the other has a natural-language scope to measure adherence. Scopeless trajectories are graded by a standard deterministic verifier. Scoped trajectories pass through two grading arms. First, the same deterministic verifier checks for the flag: because the flag sits behind the scope boundary, a pass proves by construction that a forbidden action occurred, yielding a high-precision lower bound on the violation rate. If the verifier does not pass the trajectory, an agentic judge estimates whether an out-of-scope call occurred. We calibrate the judge against 100 ScopeBench trajectories labeled call-by-call by human annotators, and a blinded audit of the evaluated rollouts finds its high recall holds - no false negatives among the 36 audited violations, with over-flagging its only observed error. Across 8 models in one harness, raw capability spans 12.2% to 81.1% and scope adherence spans 34.4% to 86.7%, with the judge finding 331 violations that mechanical verification misses. Opus-4-8 achieves a raw-capability score 10 percentage points higher than sonnet-4-6's while exhibiting 35.6 percentage points higher scope adherence. We release the frozen pilot benchmark, evaluation code, and all 2160 ATIF trajectories. --- ### Adaptive Random Matrices in Gaussian Bandits: Spectral Universality and Selection-Induced Outliers Authors: Sudarshan Manikantan, Abhishek Bhattacharjee Published: 2026-09-23 Categories: stat.ML, cs.LG, math.PR, math.ST arXiv: https://arxiv.org/abs/2609.30321v1 Adaptive arm selection changes the distribution of the observations collected by a bandit algorithm, but it need not change their limiting empirical spectrum. We study Gaussian bandit designs in which the dimension and the number of observations grow proportionally. A quantitative coupling theorem compares the design generated by any causal selection rule with an independent Gaussian design. If the logarithm of the number of available arms is sublinear in the dimension, the empirical spectral distribution converges to the Marchenko-Pastur law, uniformly over the selection rule. Consequently, Gaussian Bayesian bandits have policy-independent first-order limits for posterior mean-square uncertainty, squared posterior covariance, and information acquisition. For linear-score selection, we obtain the exact conditional arm distribution and show that two-arm selection produces an exactly Wishart Gram matrix in every dimension, despite its nonzero conditional mean. For a fixed selection direction, we identify an explicit eigenvalue and eigenvector transition governed by the second moment of a Gaussian maximum. A counterexample shows that a direction's overlap with a reference signal does not determine this transition. Finally, an exponentially large arm pool permits a different bulk limit, establishing the order-sharpness of the arm-growth condition. These results distinguish global spectral stability from directional effects in adaptive bandit data. --- ### MEVL-STP: Multi-Encoder and Vision Language Model for Arbitrarily Shaped Scene Text Spotting Authors: Aman Anand, Partha Pratim Roy, Shivakumara Palaiahnakote Published: 2026-09-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.28857v1 Scene text spotting remains challenging for arbitrarily shaped text instances such as curved signs and dense multi-oriented characters in natural images, where tightly coupled architectures propagate localization errors directly into recognition failures. We present a two-stage pipeline that combines multi-encoder segmentation with vision-language model recognition to address this problem. In the detection stage, six frozen vision encoders (CLIP, DINOv2, SigLIP, EVA-CLIP, SAM, and ConvNeXt) extract complementary features spanning semantic, spatial, and texture spectra, which are fused through a trainable hierarchical Feature Pyramid Network with channel attention and decoded via a deep-supervision Progressive Scale Expansion network to generate precise instance-level text masks. By keeping the encoders frozen, their independently learned feature spaces remain orthogonal during fusion, preventing the feature homogenization that degrades boundary precision in single-backbone detectors. The detection stage produces tight polygon masks that conform to the actual shape of curved and arbitrarily oriented text, rather than axis-aligned rectangles that inevitably include background content. In the recognition stage, these polygon-masked crops isolate the target text from surrounding clutter, allowing a Qwen3-VL-8B-Instruct model, fine-tuned via Low-Rank Adaptation on polygon-cropped scene text, to focus purely on reading the text without interference from neighbouring words or background noise. Without any synthetic pretraining data, our method achieves 91.99% detection F-measure and 85.86% end-to-end H-mean on CTW1500, setting a new state of the art and achieving strong performance on Total-Text and ICDAR 2015 without any synthetic training data. Code is available at https://github.com/doubleblind-afk/MEVL-STP --- ### Persuaded, Not Informed: Incentive-Misaligned Witnesses Defeat In-Context Grounding Authors: Rahul Balakavi Published: 2026-09-23 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2609.28854v1 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. --- ### Looks the Same, Answers Differently: Flip-Direction Steering for Robust Vision-Language Reasoning Authors: Yeonsung Jung, Joonhyun Jeong, Hoang Pham, Joowon Kim, Yoonsik Park, Viet Dac Lai, Eunho Yang Published: 2026-09-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.28851v1 Vision-language models (VLMs) achieve strong visual reasoning performance, yet subtle changes from routine image capture and processing can alter their reasoning trajectories even when images appear nearly identical. In long-horizon generation, the resulting activation shifts may accumulate across decoding steps, progressively altering reasoning tokens and ultimately changing the final answer, a phenomenon referred to as answer flips. To address this instability, we propose FlipDir (Flip-Direction Steering), a training-free inference-time method that estimates a low-rank flip-inducing activation subspace from contrastive pairs of original and answer-flipping inputs and selectively steers hidden states during decoding. A margin-based gate limits subspace attenuation to uncertain decoding steps, recovering original predictions while preserving stable ones. To evaluate robustness beyond accuracy or consistency on fixed test sets, we introduce VisFlip, a benchmark framework that constructs evaluation groups for a target model and visual variation setting to separately assess recovery of original predictions and preservation of stable ones. VisFlip spans nine dataset-variation combinations across scientific reasoning, robot-scene understanding, and medical VQA, covering subtle visual variations common in each domain. Experiments across 18 settings demonstrate that FlipDir consistently outperforms existing methods on the combined recovery and preservation metric. We will make our code publicly available. --- ### RECLAIM: Can Agents Reproduce the Claims of Machine Learning Papers? Authors: Mithil Salunkhe, Haochen Ding, Samridhi Verma, Volodymyr Kindratenko Published: 2026-09-23 Categories: cs.AI, cs.LG, cs.SE arXiv: https://arxiv.org/abs/2609.28850v1 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. --- ### LastOPD: Taming Collapse in Latent On-Policy Distillation Authors: Jie Yang, Zhengyu Fang, Zelin Xu, Jiarui Sun, Xiran Fan, Junpeng Wang, Liang Wang, Qinghua Liu, Yiwei Cai, Yan Zheng Published: 2026-09-23 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2609.28845v1 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-Enabled Artificial Intelligence and AI Agents for Secure Data Sharing and Cybersecurity Applications Authors: Harsh Verma Published: 2026-09-23 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2609.28843v1 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. --- ### Uncertainty-Gated Exploration Noise Suppresses Task Collapse in Online RL Fine-Tuning of a Flow-Matching Vision-Language-Action Policy Authors: Mehmet Turan Yardımcı, Yunus Emre Çoğurcu Published: 2026-09-23 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2609.28838v1 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. --- ### M$^2$PFN: End-to-End Disentangled Alignment for Generalizable Multimodal In-Context Learning in Alzheimer's Disease Authors: Lujia Zhong, Shuo Huang, Jianwei Zhang, Xinyu Nie, Yonggang Shi Published: 2026-09-23 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.28836v1 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. --- ### When Does Unsupervised Learning Succeed or Fail? A PoS Perspective on Reconstruction-Based Anomaly Detection Authors: Mehmet Yamaç, Yagmur Mustu, Muhammad Numan Yousaf, Lei Xu, Marcel van Gerven Published: 2026-09-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.28832v1 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. --- ### COILD: An Indic-Centric Parallel Corpus and Benchmark for Machine Translation Across Indian Languages Authors: Kshetrimayum Boynao Singh, Nitin Kumar Mishra, Palash Pratim Dutta, Atai Waris Khan, Aparna Kaushik, Avinash Kumar, Deeksha, Deepak Kumar, Saroj Kumar Jha, Saloka Sengupta, Anansa Roy, Umalatha Kannoth et al. Published: 2026-09-23 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.28826v1 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. --- ### KeyGen: Unsupervised Keypoint based Object-Centric Representations for Category-Level Policy Generalization Authors: Shuxin Cao, Liquan Wang, Masoud Moghani, Benjamin Joffe, Animesh Garg Published: 2026-09-23 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2609.28818v1 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. --- ### CinematicVQA: Benchmarking Film-Grammar Reasoning in Large Vision-Language Models Authors: Shuo Xing, Pooja Verlani, Balu Adsumilli, Zhengzhong Tu Published: 2026-09-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.28813v1 Cinematography, the craft of visual storytelling through framing, lighting, and camera operation, fundamentally shapes how audiences perceive and emotionally engage with video content. While Large Vision Language Models (LVLMs) have made remarkable progress in video question answering, existing benchmarks primarily focus on identifying low-level techniques rather than understanding their storytelling impact. To address this, we introduce CinematicVQA, the first-of-its-kind benchmark for cinematic video understanding that goes beyond technique recognition to evaluate film-grammar reasoning, utilizing our introduced Cinematic Scene Graph (CSG), a structured representation that links filming techniques to their perceptual effects and narrative functions. Through comprehensive evaluation of state-of-the-art LVLMs, we reveal a striking semantic gap: models consistently perform higher on describing visual presentations than on identifying the underlying techniques. Surprisingly, Chain-of-Thought prompting fails to provide consistent gains and degrades performance for most models, suggesting that current LVLMs lack sufficient cinematic domain knowledge to benefit from step-by-step reasoning. Fine-tuning on \textsc{CinematicVQA-train} yields consistent improvements, particularly for narrative function and multi-hop reasoning. Overall, \textsc{CinematicVQA} serves both as a rigorous benchmark for cinematic evaluation in LVLMs and as a practical dataset for training more film-aware video models. --- ### DeltaWAM: Delta World Action Models for Bimanual Manipulation Authors: Han Yan, Zishang Xiang, Haokai Jiang, Zeyu Zhang, Qilin Wang, Weiyu Guo, Yandong Guo, Boxin Shi, Hao Tang Published: 2026-09-23 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2609.28811v1 World-action models (WAMs) transfer visual and motion priors from pretrained video generators to robot control by jointly modeling visual dynamics and actions. Existing WAMs, however, predict dense future frames during training, repeatedly modeling largely unchanged content and coupling action-conditioned dynamics to nuisance appearance variations. At inference, processing each complete observation with the heavy video expert bottlenecks few-step action generation. Accordingly, we propose DeltaWAM, which jointly predicts visual deltas and actions using dense-anchor, sparse-delta, and action streams, with three architectures that differ in representation and computation sharing. We further develop Streaming Delta Memory (SDM), which updates cached anchor context with compact observed deltas, reducing heavy video-expert processing. On RoboTwin, DeltaWAM with SDM improves average success over Fast-WAM from 81.3% to 85.4% in the clean setting and from 75.8% to 83.9% under visual randomization. The three architectures reduce training FLOPs by 17.78-23.77%, while SDM reduces one-step inference latency and FLOPs by 36.57% and 31.55%, respectively; real-world evaluations further show the highest overall success rate and normalized progress among the evaluated policies. Code: https://github.com/AIGeeksGroup/DeltaWAM. Website: https://aigeeksgroup.github.io/DeltaWAM. --- ### Stream Recursion Model (SRM) Authors: Asael Sorensen, Charles Brock, David Chamberlain, Jennifer Minnich, Matthew Hoffman, Ramyaa Ramyaa Published: 2026-09-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.28809v1 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. --- ### A Harness for Synthesizing Diverse Naturalistic Full-Duplex Conversations Authors: Matthew Sun, Vinay Kothapally, Meng Yu, Chao Huang, Hao Zhang, Yixuan Zhang, Steve Yves Published: 2026-09-23 Categories: eess.AS, cs.AI arXiv: https://arxiv.org/abs/2609.28806v1 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. --- ### DrGait: Biomechanically Grounded Visual Reasoning for Interpretable Clinical Gait Analysis Authors: Xiangyu Yin, Shiqi Wang, Abrar Alamri, Yasir Aljohani, Weichen Liu, Goeran Fiedler, Wei Gao Published: 2026-09-23 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.28796v1 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. --- ### Monitoring Urban Traffic Dynamics at Fine Spatiotemporal Resolution Using Distributed Acoustic Sensing and Deep Learning Authors: Hao Tian, Heng Cai, Xiaowei Chen, Yifan Yang Published: 2026-09-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.28793v1 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. --- ### Vector Bellman Theory for Multichain Robust Average-Reward Markov Decision Processes Authors: Yue Wang, George Atia Published: 2026-09-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.28792v1 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. --- ### Script Choice in LLMs: Evidence for Late-Layer Commitment Authors: David Kletz, Sandra Mitrović, Itay Sabato, Ljiljana Dolamić, Fabio Rinaldi Published: 2026-09-23 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.28784v1 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. --- ### The Mechanics of Delta Learning: Target Design for Generalizable Scientific Machine Learning Authors: Kareem M. Gameel, Ihor Neporozhnii, Sjoerd Hoogland, Oleksandr Voznyy Published: 2026-09-23 Categories: cs.LG, physics.chem-ph, physics.comp-ph arXiv: https://arxiv.org/abs/2609.28782v1 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. --- ### Reward-Tilted On-Policy Distillation for Acoustic Grounding in Audio-Language Models Authors: Kaiyang Li, Shaobo Han, Yue Tian, Shihao Ji Published: 2026-09-23 Categories: cs.SD, cs.CL arXiv: https://arxiv.org/abs/2609.28778v1 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. --- ### Learned Cross-Task Relationships in Multi-Task Models Authors: Victor Zhang, Yiping Yuan, Florian Raudies, Bosun Adeoti, Brian Y. C. Leung, Sanjay Surendranath Girija, Naijing Zhang Published: 2026-09-23 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.28776v2 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. --- ### Physics-Guided Multi-Objective Deep Learning for Ultrasound RF Data Interpolation in Resource-Constrained Imaging Authors: Luoyuan Zhang, Yiyang You, Ananya Tandri, Yinan Feng, Hyunwoo Song, Jeeun Kang, Youzuo Lin Published: 2026-09-23 Categories: eess.IV, cs.LG arXiv: https://arxiv.org/abs/2609.28775v1 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. --- ### Agent Memory with Episodic Retrieval for Financial Decision-Making Authors: Nuoyue Xu, Jiang Liu, Wenxuan Huang, Xiang Zhang, Juntai Cao, Jiaqi Wei Published: 2026-09-23 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.28771v1 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 for Small Search Agents Authors: Gaurisankar Jayadas, Aske Plaat, Álvaro Serra-Gómez, Sandheep P Published: 2026-09-23 Categories: cs.AI, cs.IR arXiv: https://arxiv.org/abs/2609.28765v1 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. --- ### KathDB-FAO: Synthesized Query Plans in a Multimodal DBMS Authors: Guorui Xiao, Douglas Brown, Artur Borycki, Magdalena Balazinska Published: 2026-09-23 Categories: cs.DB, cs.AI arXiv: https://arxiv.org/abs/2609.28761v1 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. --- ### BiMamba2 Masked Discrete-Unit Prediction for Multilingual Speech Representation for Unsupervised Speech in the Wild Challenge Authors: Prakriti Subedi, Howard Prioleau, Saurav K Aryal Published: 2026-09-23 Categories: cs.SD, cs.CL arXiv: https://arxiv.org/abs/2609.28758v1 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. --- ### Small yet Assistive: Spatially-Aware Post-Training for Low Vision Authors: Rishabh Choudhary, Shreyansh Raj, Umesh Goyal, Shubh Kashyap, Shrestha Kumar, Sushovan Jena, Komal Kumar, Hisham Cholakkal, Aditya Nigam Published: 2026-09-23 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2609.28757v1 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/ --- ### Selective Inference for Deep Clustering in Latent Spaces Authors: Eina Mizui, Tomohiro Shiraishi, Shunichi Nishino, Ichiro Takeuchi Published: 2026-09-23 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2609.28756v1 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. --- ### Evaluating Cross-region Generalization for Wavelet-Diffusion Precipitation Downscaling Authors: Weikang Qian, Yixin Wen, Chugang Yi, Zhi Li, Lingcheng Li, Haizhao Yang Published: 2026-09-23 Categories: cs.LG, physics.ao-ph arXiv: https://arxiv.org/abs/2609.28749v1 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. --- ### Technical Manual for Toolkit for Confidence-Corpus Consistency via Fine-Tuning on a Fabricated Corpus Authors: José Luciano Verçosa Marques, Frederico Jorge Heitmann, Daniel Omar Perez, Reinaldo Cesar, Marcelo Vinicius de Paula, Tárcio André dos Santos Barros Published: 2026-09-23 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.28747v1 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. --- ### GeoNLI - A Natural Language Interpreter for Satellite Imagery Authors: Ashutosh Gandhe, Anupam Rawat, Geet Sethi, Kabir Nasiruddin, Madhav Kotecha, Panav Shah, Rakshit Sawarn, Soumitra Nayak Published: 2026-09-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.28741v1 Multi-modal multitasking models have shown strong performance on remote sensing datasets. However, because these models are trained on heterogeneous data and vary across tasks, designing a unified model that performs well in captioning, visual question answering (VQA), and visual grounding remains challenging. In this work, we evaluate several models on the VRS Bench and NWPU-VHR-10 datasets. The EarthMind model demonstrates strong results in both captioning and VQA. For grounding, we propose multiple pipelines - RemoteSAM-SAM-v1, RemoteSAM-SAM-v2, and DiffuSAM - and ultimately adopt a majority-voting ensemble across EarthMind, RemoteSAM, SAM3, Falcon, RemoteSAM-SAM3-v1, RemoteSAM-SAM3-v2, and DiffuSAM predictions. Our unified, modular pipeline integrates advanced SAM variants with multimodal LLMs to jointly perform captioning, VQA, and grounding. It achieves 82% accuracy on captioning and 83.32% on VQA, with 90.94%, 52.04%, and 92.06% for binary, numeric, and semantic question types respectively. For grounding, it attains 64.94% accuracy. By combining diverse VLMs with our custom RemoteSAM-SAM3 models through ensemble majority voting, the system delivers more accurate and consistent remote-sensing understanding than task-specific approaches. --- ### Temporal Taxation Compounds Under Post-Training Compression of Whisper Models Authors: Srishti Ginjala, Eric Fosler-Lussier, Christopher W. Myers, Srinivasan Parthasarathy Published: 2026-09-23 Categories: cs.CL, cs.SD arXiv: https://arxiv.org/abs/2609.28739v1 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. --- ### Policy Complexity, Reaction Time, and Bounded Rationality in Reinforcement Learning Authors: James Wu, Chris R. Sims Published: 2026-09-23 Categories: cs.LG, cs.AI, cs.IT arXiv: https://arxiv.org/abs/2609.28737v1 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. --- ### Integrating Local Detail and Global Context: A Dual-Input Multi-Task Learning Framework for Bone Tumor Diagnosis Authors: S. M. Nasif Uddin, Rusab Sarmun, Muhammad E. H. Chowdhury, Adam Mushtak, Israa Al-Hashimi, Sohaib Bassam Zoghoul Published: 2026-09-23 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2609.28732v1 Primary bone tumors are rare but clinically aggressive neoplasms whose diagnosis from radiographs is challenged by heterogeneous morphology, subtle lesion margins, and overlapping bone structures. To address the limitations of existing single-view models, we present a dual-input, multi-task learning framework that, to our knowledge, is the first to apply bidirectional cross-modal attention between a lesion crop and the full radiograph for joint segmentation and subtype classification. Using the multi-institutional Bone Tumor X-ray Radiograph Dataset (BTXRD, n=3,746), we employ a YOLO-based detector to generate regions of interest, which are paired with full images as inputs to a dual-stream DenseNet121 architecture. Features are integrated via a novel cross-modal attention fusion strategy, refined by Hierarchical Multi-scale Feature Fusion, effectively balancing fine-grained lesion detail with global anatomical context. Evaluated on a held-out patient-level test split, the model demonstrates superior performance over single-input baselines, achieving an overall Dice Similarity Coefficient of 0.896 and a macro-averaged classification F1-score of 0.928. Notably, the system exhibits exceptional sensitivity for malignant osteosarcoma (AUC 0.999), validating the potential of dual-stream context modeling to support radiologists in accurate, early decision-making. --- ### PTC-Bias: Phoneme-Level Temporal Competition for Bias Retrieval and Post-Decoding Correction in Speech LLMs Authors: Zhiqi Ai, Han Cheng, Shiyi Mu, Yongjin Zhou, Shugong Xu Published: 2026-09-23 Categories: cs.CL, cs.SD arXiv: https://arxiv.org/abs/2609.28727v1 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. --- ### Unmasking Shortcut Learning in IoT Intrusion Detection: A Forensic, Multi-Paradigm Evaluation of Feature Dependence and Data Leakage Authors: Uday Shankar Roy, Mahbuba Jahan Minu Published: 2026-09-23 Categories: cs.CR, cs.LG, cs.NI arXiv: https://arxiv.org/abs/2609.28725v1 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. --- ### Upholding Robustness in Federated Learning: Trends, Emerging Strategies, and Research Opportunities Authors: Pravija Raj P, Ashish Gupta, Andrea Augello, Sajal K. Das Published: 2026-09-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.28722v1 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. --- ### Exact Bayes Regret and Asymptotic Optimality in High-Dimensional Gaussian Bandits Authors: Prakhar Singhvi, Yi Zou, Abhishek Bhattacharjee Published: 2026-09-23 Categories: stat.ML, cs.LG, math.ST arXiv: https://arxiv.org/abs/2609.28718v1 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. --- ### Temporal Learning for End-Effector Position Estimation under Aerodynamic Disturbances in Aerial Continuum Manipulation Authors: Niloufar Amiri, Houman Masnavi, Farrokh Janabi-Sharifi Published: 2026-09-23 Categories: cs.RO, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.28716v1 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. --- ### Spooftral: Can Voxtral Audio-Language Model Detect Speech Spoofing? Authors: Avishai Weizman, Yehuda Ben-Shimol, Itshak Lapidot Published: 2026-09-23 Categories: eess.AS, cs.CL arXiv: https://arxiv.org/abs/2609.28713v1 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. --- ### An Explainable DistilBERT-BiLSTM-Attention Framework for Binary and Multi-Class Hate Speech Detection Authors: Rameesha Zia, Muhammad Shahid Iqbal Malik Published: 2026-09-23 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2609.28703v1 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. --- ### LabFactory: Building and Evaluating Executable AI Labs Authors: Jinge Wu, Hongjian Zhou, Mingde Zeng, Jiayuan Zhu, Junde Wu, Jiazhen Pan, Lei Clifton Published: 2026-09-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.28697v2 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, 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 10 selected constructions across six scientific task categories---from molecular and genomic prediction to medical imaging, clinical decision support, and biomedical text---whose delivered labs exceeded their configured reference values on all 12 subtests under host-side execution. Four contain predictive models fitted during construction; the others assemble executable analysis environments, knowledge resources, 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. --- ### Federated Learning of AnDE Classifiers Authors: Pablo Torrijos, Juan C. Alfaro, José A. Gámez, José M. Puerta Published: 2026-09-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.28695v1 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. --- ### Progressive Skill Discovery as Access Control for Tool-Using LLM Agents: Structural Governance through Role-Scoped Capability Delivery Authors: Michael Stettler, Benjamin Girardet, Jonas Canton, Nicolas Corod Published: 2026-09-23 Categories: cs.AI, cs.CR, cs.MA, eess.SY arXiv: https://arxiv.org/abs/2609.28693v1 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. --- ### Driving Epidemic Models with AI Agents: the Epydemix Agent Framework Authors: Nicolò Gozzi, Ciro Cattuto, Alessandro Vespignani Published: 2026-09-23 Categories: cs.AI, cs.CY arXiv: https://arxiv.org/abs/2609.28692v1 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. --- ### TRACER: Trajectory-Aligned Learning for Multi-Turn User Simulation Authors: Geng Chen, Ruotong Pan, Zhirui Yang, Qiqi He, Jiawei Chen, Zhang Yunfei, Chongyuan Chen, Minxuan Lv, Zheng Yang, Win-Bin Huang, Xiangyu Wu, Wenwu Ou Published: 2026-09-23 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.28690v2 Faithful user simulation is fundamental to building, evaluating, and improving interactive AI at scale. Yet current simulators often produce plausible individual responses without reproducing the intent evolution and outcomes observed in real interactions. We propose TRACER, a multi-turn user simulator that models evolving user intent and aligns simulated trajectories with real ones. 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 addressing reward sparsity and credit assignment challenges in long dialogues. On real customer-service sessions organized into reference cohorts, TRACER-7B surpasses the strongest baseline by 11.4 conversion F1 points, while outperforming all baselines on group-level conversion-rate error and semantic trajectory distance and generalizing to out-of-distribution scenarios. In human Turing tests, annotators identified TRACER conversations at near-chance accuracy. Building on this simulator, we further introduce the Dynamic Marketing Benchmark, which jointly evaluates persuasion and response quality via simulated interactions, revealing that higher response quality does not necessarily correspond to higher conversion rates. --- ### M-plicits: Neural Implicit Surfaces via Nested Multiscale Residuals Authors: Vinícius da Silva, Isabelle Melo, Matheus Bessa, Guilherme Schardong, Luiz Schirmer, André Araújo, Nuno Gonçalves, Hélio Lopes, Alberto Raposo, Luiz Velho, Tiago Novello Published: 2026-09-23 Categories: cs.CV, cs.GR, cs.LG arXiv: https://arxiv.org/abs/2609.28684v2 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 are available at https://github.com/dsilvavinicius/m-plicits. ---