# Research Papers — 2026-09 · bundle page 164 of 266 > Full-text markdown of papers #8151–8200 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/164 [← Previous bundle](https://aipod.dev/papers/archive/2026-09/page/163.md) [Next bundle →](https://aipod.dev/papers/archive/2026-09/page/165.md) ### Fast-Convergent Meta-RL via Gradient-Clustered BS Sampling for Edge Caching Authors: Farnaz Niknia, Ping Wang Published: 2026-09-14 Categories: cs.NI, cs.LG, eess.SY arXiv: https://arxiv.org/abs/2609.16370v1 Wireless edge caching networks typically consist of many independent Base Stations (BSs), each facing its own request rate and content popularity profile. Training a Reinforcement Learning (RL) caching agent from scratch at every BS forces each agent to relearn, through slow trial and error, a decision problem that is structurally identical across the network. Meta-reinforcement learning removes this redundancy by learning a shared initialization that adapts to any BS in a few local updates; however, meta-training itself becomes the bottleneck at scale: the meta-gradient must be estimated from a small subset of BSs at each meta-iteration, and sampling this subset uniformly at random yields a high-variance estimate, an issue existing meta-RL caching frameworks leave unaddressed. This paper proposes a meta-reinforcement learning framework for caching across independent, non-overlapping BSs that directly targets this bottleneck. Each BS runs a local Proximal Policy Optimization (PPO) agent, formulated as a Semi-Markov Decision Process (SMDP) over content popularity, size, lifetime, and importance, while a shared meta-policy is learned via a Model-Agnostic Meta-Learning (MAML)-style loop. To scale meta-training and accelerate convergence, we introduce gradient-based clustering, which groups BSs by local gradient similarity and draws from every cluster, in proportion to its size, at each meta-iteration. We prove, via an Analysis of Variance (ANOVA)-style decomposition of gradient variance, that this strategy yields a strictly lower-variance meta-gradient estimator than uniform random sampling under BS heterogeneity. --- ### Autonomous Droplet Navigation via Model-Based Reinforcement Learning Authors: Rajneesh Anand, Mayuresh V. Kothare Published: 2026-09-14 Categories: cs.LG, cs.RO, eess.SY, physics.flu-dyn arXiv: https://arxiv.org/abs/2609.16369v1 Precise manipulation of liquid droplets underpins lab-on-a-chip platforms for diagnostics, chemical synthesis, and biological assays. Yet autonomous droplet transport through confined geometries of varying complexity remains an open challenge. Droplets exhibit contact-angle hysteresis, deformability, and capillary pinning, which make their response to actuation nonlinear and history dependent, that classical controllers and pre-programmed trajectories cannot cope in multi-turn environments. Here we demonstrate autonomous navigation of a liquid droplet through geometries of increasing complexity on a gravity driven (Labyrinth) platform using model-based reinforcement learning. A thin silicone oil film reduces contact-line pinning while two-axis tilt supplies the gravitational driving force, and an overhead camera tracks the droplet in real time. An offline-trained policy discovers effective tilt strategies from limited physical interaction data, without simulation or analytical droplet models. The system operates under partial observability, as oil-film thickness, instantaneous contact angle, and droplet deformation state remain hidden from the controller. Despite these challenges, the learned policy achieves reliable navigation across straight, right-angle, and curved-arc paths, including outside-corner geometries. We further demonstrate that a policy trained on a simpler geometry transfers to complex ones, succeeding zero-shot on right-angle and staircase paths and reaching full success on a curved arc with a fifth of the training data. The findings suggest promising avenues for enabling droplet based microfluidic systems to serve as intelligent chemical laboratories. --- ### UDAV: Uncertainty-Driven Adaptive VLM Waypoint Planner Authors: Ghazal Farhani, Shabnam Shabani Published: 2026-09-14 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2609.16368v1 Vision-language models (VLMs) can generate routes directly from aerial imagery for off-road navigation, but their predictions provide no indication of reliability. We present UDAV, an Uncertainty-Driven Adaptive VLM Waypoint Planner for UAV-guided UGV navigation. UDAV draws multiple stochastic trajectory predictions, selects their medoid as a self-consistent nominal route, and estimates predictive uncertainty from their spatial dispersion. When the maximum uncertainty across interior waypoints exceeds a threshold, UDAV invokes a reconsideration stage; otherwise, it returns the medoid directly. We evaluate UDAV on 400 held-out trajectory queries from two UAV flights. Stochastic medoid selection reduces the mean average displacement error (ADE) from 147.4 pixels for a deterministic prediction to 115.9 pixels. The complete planner achieves a mean ADE of 110.4 pixels, a 25.1% reduction relative to deterministic planning, while producing valid trajectories for all queries. UDAV also yields the lowest 90th- and 95th-percentile errors among all evaluated configurations, including a higher-budget K=10 consensus baseline. Relative to the K=5 medoid, UDAV reduces these errors from 225.3 and 326.0 pixels to 199.0 and 290.8 pixels, respectively. These results demonstrate that stochastic VLM predictions provide both a stronger nominal route and an actionable uncertainty signal for selectively mitigating large planning errors. --- ### How Humans and LLMs Read Gender into "Gender-Neutral" Physical Descriptions Authors: Yingjia Wan, Lin Lin, Elisa Kreiss Published: 2026-09-14 Categories: cs.CL, cs.AI, cs.CY, cs.HC arXiv: https://arxiv.org/abs/2609.16366v2 When foundation models describe people, recent work in AI fairness, accessibility, and ethics recommends avoiding inferred identity labels (e.g., "she", "his") in favor of seemingly "objective" physical descriptions (e.g., "short hair", "a defined jawline"). Yet whether such descriptive language achieves gender-neutral communication remains an open empirical question. To study this, we introduce GAPA (Gender Associations of Physical Attributes), a dataset of 316 common physical attributes drawn from diverse sources, paired with 14,706 gender-association ratings from 304 US-based annotators. Results show that physical descriptions carry structured and graded gender associations among readers, with more consistent and distinctive associations for women and men than for non-binary identities. Next, we evaluate 16 LLMs across model families, sizes, and post-training variants against human ratings. The models partially recover human associations but exhibit systematic alignment biases, including compressed rating distributions, weaker alignment for associations with men, and asymmetric abstention that disproportionately targets the non-binary category. Finally, we release the best-performing proxy model trained to predict humans' gender associations of descriptive language and demonstrate its utility through a sociolinguistic analysis of character descriptions in LitBank. Together, our findings provide the first empirical evidence that seemingly "objective" physical descriptions can retain systematic gender associations in human interpretation, and uncover systematic patterns of model-human misalignment. This challenges the assumption that replacing explicit gender labels with physical descriptions necessarily yields gender-neutral communication, and highlights downstream challenges in using such descriptions to communicate subjective identity categories in human-AI interaction. --- ### Mini-batch Sampling Strategies for Long-Tailed Image Classification: An Empirical Study on CIFAR-100-LT Authors: Siyu Yuan Published: 2026-09-14 Categories: stat.ML, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2609.16365v1 Real-world datasets often exhibit long-tailed class distributions, where a few head classes contain a large number of training samples while a large number of tail classes have only a few. The composition of each mini-batch, determined by the sampling strategy, governs which classes contribute to the stochastic gradient estimate, and therefore affects convergence behaviour and generalisation across the whole class spectrum. We provide a systematic theoretical and empirical comparison of four mini-batch sampling strategies for long-tailed image classification: uniform instance sampling, class-balanced sampling, square-root sampling, and progressively balanced sampling. We place all four in a unified bias-variance framework describing their effect on gradient estimation, which exposes the tension between unbiased optimisation of the empirical loss and fair representation of rare classes. We then evaluate them under controlled conditions using ResNet-32 on CIFAR-100-LT at three imbalance ratios (rho = 10, 50, 100), with every strategy sharing the same long-tailed subsets and initialisation within a seed. Progressive sampling improves tail-class accuracy by 25% relative to the uniform baseline at rho = 100 (13.5% versus 10.8%), consistently across all three seeds, while its overall accuracy is not distinguishable from that of uniform sampling given the seed-to-seed variation (40.0% versus 39.7%); the tail-class gain, not the overall gain, is the robust effect. At rho = 100, class-balanced sampling degrades accuracy on every class group, including the tail classes it is designed to help, which we attribute to overfitting caused by extreme oversampling of scarce data; at rho = 50 this failure is confined to head and medium classes. These results indicate that when rebalancing is applied during training matters as much as how much rebalancing is applied. --- ### EBL: Efficient Broad Learning for Distributed Adaptive Harmonic Analysis Authors: Changhong Li, Georgios Floros, Biswajit Basu, Shreejith Shanker Published: 2026-09-14 Categories: cs.AR, cs.LG arXiv: https://arxiv.org/abs/2609.16358v1 Renewable energy systems and electrified transport have found widespread adoption in recent years. The integration of these non-linear loads, dominated by electric vehicle (EV) charging, however, has introduced severe harmonic distortion into the power grid, impacting the efficiency and lifetime of substation equipment and switchgear in the distribution network. Rapid and high-precision harmonic analysis has hence become a prerequisite for effective harmonic control at the source of injection. This paper proposes an Efficient Broad Learning (EBL) framework for distributed adaptive harmonic estimation. As a quantised FPGA acceleration framework for BLS-style harmonic estimation, it offers high-accuracy estimation with half-cycle input, reconfigurable flexibility enabled by the FPGA implementation, and ultra-low latency, achieving 17.4 $\times$ faster predictions than the nearest reported FPGA method. For harmonic prediction across multi-scenario charging and discharging nodes, the online transfer learning based on a closed-form solution rather than backpropagation in EBL demonstrates rapid adaptability. By exploiting bespoke quantisation and sparsity, the approach consumes 5.9\% of the LUTs on the Zynq Ultrascale+ ZU7EV FPGA, using $\approx$ 82\% of the LUTs required by the state-of-the-art FPGA-accelerated estimator. --- ### Federated stochastic bilevel optimization with fully first-order gradients Authors: Yihan Zhang, Rohit Dhaipule, Chiu C Tan, Haibin Ling, Hongchang Gao Published: 2026-09-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.16350v1 Federated stochastic bilevel optimization has been actively studied in recent years due to its widespread applications in machine learning. However, most existing federated stochastic bilevel optimization algorithms require the computation of second-order Hessian and Jacobian matrices, which leads to longer running times in practice. To address these challenges, we propose a novel federated stochastic variance-reduced bilevel gradient descent algorithm that relies solely on first-order oracles. Specifically, our approach does not require the computation of second-order Hessian and Jacobian matrices, significantly reducing running time. Furthermore, we introduce a novel learning rate mechanism, i.e., a constant single-timescale learning rate, to coordinate the update of different variables. We also present a new strategy to establish the convergence rate of our algorithm. Finally, the extensive experimental results confirm the efficacy of our proposed algorithm. --- ### Multi-Label Proportion Learning for Sea-Ice Type Prediction Authors: Samira Alkaee Taleghan, Younghyun Koo, Andrew P. Barrett, Farnoush Banaei-Kashani Published: 2026-09-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.16347v1 Sea-ice type prediction is important for climate monitoring, maritime navigation, and decision-making in polar regions. The main source of label data for this task is the ice chart, produced manually by ice analysts who interpret satellite imagery to delineate ice zones into polygons. Although ice charts are valuable, their production is labor-intensive and expensive, motivating recent efforts to automate the process using deep learning. However, deep learning models require patch-level (or pixel-level) label data for training, while ice charts provide only polygon-level annotations. As a workaround, supervised approaches often create approximate patch-level labels from polygon-level ice chart labels by assigning each sample the dominant ice type of its parent polygon. This approach enables supervised training but creates an ill-posed learning problem with intrinsically approximate solution. In this paper, we redefine sea-ice type prediction as a weakly supervised multi-label proportion learning problem to be able to directly use the polygon-level ice chart labels and avoid unnecessary label approximation for improved prediction accuracy. To address this problem, we propose a two-module framework where first Multiple Instance Learning (MIL) is used for water--ice classification, and then a multi-label proportion learning (MLPL) is introduced for ice-type composition prediction. We further extend this framework with a multimodal model that integrates SAR imagery with AMSR2 brightness temperatures and ERA5 reanalysis data through modality-guided auxiliary regularization. Evaluated on the AI4Arctic dataset, the SAR-only model reduces MAE by 14.5\% and more than doubles mean ice-class F1 over the best supervised baseline. The multimodal model further reduces MAE by 21.5\% and raises mean F1 by 41.2\% over the SAR-only model, and by 52.7\% over the supervised multimodal baseline. --- ### Auto-HSI: Personalized human control of a robot swarm on demand by using LLMs for online automatic code generation Authors: Alessandro Nazzari, Nathan Cerisara, Dorian Tonnis, Raina Zakir, Lorenzo Labarile, Weixu Zhu, Marco Dorigo, Mary Katherine Heinrich Published: 2026-09-14 Categories: cs.RO, cs.AI, cs.HC, cs.MA arXiv: https://arxiv.org/abs/2609.16346v1 This paper presents Auto-HSI, a method for generating personalized human-swarm interaction (HSI) interfaces on demand. The objective is to enable untrained operators to use natural language descriptions and gesture demonstrations to explain how they want the robots to collectively behave in response to their gestures. Based on these inputs, the code should automatically be generated for personalized state machines that will control the robots as desired, in response to the desired gesture inputs. In the developed Auto-HSI prototype, the generated code produces a personalized interface for centralized control using one- and two-handed gestures, enabling a user to teleoperate the robots' motion, formation shape, and shape deformation. We test the gesture tracking and code generation components of Auto-HSI against performance benchmarks. We then test the full Auto-HSI prototype in ``live'' operation experiments, in which real human operators centrally control 50 simulated robots in a physics-based simulator, under nominal and noisy conditions. In these experiments, robots are teleoperated to: score a goal, traverse a maze that requires shape deformation, and score two simultaneous goals by splitting into two groups. We also demonstrate a real human operator making live updates to their personalized Auto-HSI interface during operation (in simulation). Finally, we demonstrate live operation of real robots. --- ### From Momentary Emotion Inference to Sustained Emotion Support: Evaluating a Companion Agent in a Longitudinal Study Authors: Kexin Quan, Zijian Ding, Jiaye Yong, Qinshi Zhang, Dong Wang, Jessie Chin Published: 2026-09-14 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2609.16344v2 Sustained emotional support is a long-horizon interaction task closely tied to human well-being. Recent research demonstrates generative agents' capacity for momentary emotional support, yet how these capabilities sustain support over time remains unclear. To examine this challenge, we deployed PAIR, a theory-based emotion-regulation companion, with 19 participants for 14 days. Across 1,093 sessions, we paired emotion estimates with self-reports before and after guidance and analyzed logs and interviews. Estimates corresponded more closely to self-reported valence and dominance than arousal. Guided conversations were followed by higher valence and state-dependent arousal changes. Participants felt understood through contextual exploration and emotional acknowledgment, acting on guidance suited to their needs and constraints. Perceived helpfulness of guided conversation significantly increased over time. Our findings link memory updates and retained corrections to cross-session personalization, informing future emotional support tools that adapt to evolving needs, learn from prior outcomes, and preserve user control over memory. --- ### Channel-Informed Neural Network for Physical Layer Key Generation Authors: Jose Angel Sanchez Viloria, George Sklivanitis, Dimitris Pados, Elizabeth Serena Bentley Published: 2026-09-14 Categories: cs.LG, eess.SP arXiv: https://arxiv.org/abs/2609.16341v1 Physical-layer key generation (PKG) enables wireless devices to establish shared keys from reciprocal channel observations without directly exchanging the key. This capability is attractive for edge networks, where distributed and resource-constrained devices may require lightweight key establishment with limited access to centralized infrastructure. We introduce a channel-informed neural network for PKG that derives binary key features directly from received IQ measurements while explicitly grounding the learned representation in the underlying multipath channel. The proposed multi-task recurrent neural network jointly learns reciprocity-preserving binary features and an auxiliary channel estimate using a training objective that combines deep metric learning with channel-informed supervision. Structured channel sounding enables channel estimation from over-the-air measurements, while Sionna-RT ray tracing is used to augment training with additional propagation conditions. We evaluate the framework using indoor and outdoor software-defined-radio measurements collected on the POWDER radio testbed. Across all evaluated scenarios, the proposed model produces lower bit disagreement for reciprocal Alice-Bob observations than for Eve-related observations. Ray-traced data augmentation substantially improves key diversity, increasing the unique-key rate to 0.94, 0.99, and 0.99 across the indoor and two outdoor scenarios, respectively. Successfully reconciled channel-informed keys pass the selected NIST randomness tests prior to SHA-3 privacy amplification. The results demonstrate the potential of channel-informed representation learning for decentralized wireless key establishment while highlighting an important tradeoff between key diversity and reconciliation reliability. --- ### StalePO: Anchored Token-Level Preference Optimization using Legacy Post-Edits in Machine Translation Authors: Rohit Dhaipule, Sukhdeep Singh Kharbanda, Prasanth Bathala, Pradyumna Lanka, Anubhav Shrimal Published: 2026-09-14 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2609.16340v1 Machine translation systems are periodically upgraded to stronger models, but the available preference signal is human post-edits of an older system's outputs, which the newer model may already surpass. Moreover, collecting fresh post-edits for every new model is prohibitively expensive. We call this the Stale Preference problem. Standard DPO can fail in this setting: it may increase the likelihood of inferior post-edits, erode the model's existing quality, and fail to provide the per-token control needed to correct localized errors. We introduce StalePO, an objective derived from three requirements this regime imposes. Likelihood movement must be downward on both responses, the policy must be anchored to its own base response, and the KL constraint must apply at the token level. These requirements are jointly necessary. In ablations, each mechanism in isolation leaves the model's performance indistinguishable from the base model, and only their combination converts stale feedback into gains. On English-to-Hindi and English-to-Turkish localization data, StalePO improves the fraction of segments passing all LLM-as-judge MQM quality checks by 14.9 and 4.6 percentage points, respectively, with gains concentrated on style and fluency. A human evaluation under the same framework confirms these gains on English-to-Hindi, raising the fraction of segments passing all seven human checks by 13.8 percentage points. --- ### Breaking the 1.58-bit Barrier for Ternary LLMs Authors: Evangelos Georganas, Alexander Heinecke, Pradeep Dubey Published: 2026-09-14 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.16338v1 Ternary Large Language Models (LLM) store every weight as one of three symbols $\{-1,0,+1\}$, so the cost of a ternary model is conventionally referenced to the information-theoretic $\log_2 3 \approx 1.585$ bits per weight. The prevailing deployment format packs five ternary weights into one byte (five-trit packing), and due to the power-of-two group sizes used in practice this rounds up to $1.625$ bits per weight. This effective storage bit-width treats the three symbols $\{-1,0,+1\}$ as equiprobable. We measure the actual symbol distribution of 29 ternary LLM models and find that zeros account for up to $51.5\%$ of all weights. Motivated by this finding, we introduce BITCOS, a simple distribution-adaptive layout comprised of a dense presence bitmap plus a compacted sign vector, and costs $2 - z$ bits per weight element given a zero density $z$ in the model's weights. BITCOS stores weights more compactly than the five-trit packing in 26 of the 29 tested models, and reaches $1.485$ bits per weight on the sparsest of them. BITCOS is amenable to efficient unpacking on modern processors and GPUs, and we present optimized unpacking sequences for AVX-512, AVX2 and Intel Xe2 GPUs. Measured against production state-of-the-art ternary matrix-vector multiplication kernels, at the zero densities real-world ternary models exhibit, the realized gain with our proposed layout is up to $1.28\times$. Finally, we illustrate end-to-end LLM inference results on 5 different platforms (client and server CPUs, integrated and discrete Xe2 GPUs) where decode throughput improves by up to $1.18\times$ on CPUs and $1.27\times$ on GPUs. --- ### Cross-Anatomy Transfer Versus Sparse Interpolation in Digital-Twin-Oriented Aortic Fluid-Structure Interaction Surrogates Authors: Ali Nourbakhsh, Mohammad Reza Niroomand, Erfan Nourbakhsh Published: 2026-09-14 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.16322v1 Surrogate credibility for fluid-structure interac- tion (FSI) requires distinguishing transfer across independent anatomies from interpolation within an already sampled surface. Four de-identified human aortic models from the Vascular Model Repository were reconstructed into separate lumen and nominal 1.5-mm wall domains and analyzed under matched first-cycle two-way FSI. A geometry-only LightGBM prior, selected by leave-one-anatomy-out development on three anatomies, was zero-shot evaluated on a fourth, then probed with a post-zero- shot sparse field-completion case study over six targets. Zero-shot transfer was poor across all targets. At a five-percent anchor level (203 anchors, 3,852 evaluation nodes), prior-plus-adaptation reached an oscillatory shear index (OSI) R2 of 0.603. However, same-anchor controls tuned only on the three development anatomies were stronger for several outcomes: inverse-distance weighting reached R2 = 0.829 (OSI), 0.617 (peak von Mises stress), 0.676 (mean stress); radial basis function interpolation reached 0.917, 0.714, 0.778. Sparse within-anatomy labels thus support field completion, but this four-anatomy cohort gives no evidence the cross-anatomy prior adds value beyond direct interpolation. We frame this as a first computational stage toward a measurement-linked digital twin: the surrogate/update layer is evaluated here, while larger cohorts, converged FSI, measurable patient-side inputs, and physics-informed learning remain future work, not a claim of a complete clinical twin. Our code, data and computation files are available at https://github. com/ali-nourbakhsh2005/Aortic-FSI-Sparse-Field-Completion --- ### FairLint-DL: An IDE-Native Tool for Fairness Debugging of Deep Learning Software Authors: Archit Rathod, Saeid Tizpaz-Niari Published: 2026-09-14 Categories: cs.SE, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.16321v1 Existing fairness analysis tools predominantly operate as post-training evaluation frameworks, requiring practitioners to complete the full model development lifecycle before assessing bias. We present FairLint-DL, a Visual Studio Code extension that implements a shift-left approach to fairness testing by enabling pre-training, IDE-native bias detection directly on tabular datasets. FairLint-DL trains a configurable deep neural network as a proxy model and applies information-theoretic Quantitative Individual Discrimination (QID) metrics. Grounded in Shannon and min-entropy, QID quantifies the causal influence of protected attributes on predictions. The system implements a two-phase gradient-guided search algorithm for discovering discriminatory instances, a causal debugging pipeline that localizes bias to specific network layers and neurons via sensitivity analysis, and dual explainability engines using SHAP and LIME for feature-level attribution. Evaluation on three tabular benchmarks (Adult Census Income, German Credit, and Bank Marketing) reveals fairness concerns that vary widely across datasets: on Adult, 96.0% of analyzed instances exhibit QID above the 0.1-bit significance threshold, with a mean QID of 0.619 bits and a disparate impact ratio of 0.581, violating the four-fifths legal rule. FairLint-DL produces these results within 12 seconds on cached models, demonstrating the feasibility of integrating fairness analysis into the developer workflow without significant overhead. --- ### ConGraspXL: Controllable Constraint-Conditioned Dexterous Grasping Motion Synthesis Authors: Hui Zhang, Mirko Meboldt, Jie Song Published: 2026-09-14 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2609.16319v1 Dexterous grasping is usually conducted for specific tasks, leading to heterogeneous constraints such as specific approach directions, desired contact regions, specified wrist trajectories, and functional hand poses. Our previous work, GraspXL, achieves scalable grasping motion synthesis for diverse objects and hand morphologies, while lacking controllability for synthesis under such various task-driven constraints. In this paper, we propose ConGraspXL, which extends GraspXL with controllable constraint-conditioned grasp motion synthesis that accommodates diverse task-driven constraints and their combinations. We introduce a hierarchical constraint formulation, enable flexible constraint composition with a masked residual interface, and improve control precision with dynamic hand centers and feed-forward wrist guidance. Without losing the strong generalization capabilities of GraspXL, ConGraspXL enables precise and flexible controllability for various individual constraints and their combinations, providing a plug-and-play low-level grasp controller for downstream applications such as whole-body grasp completion, functional grasping, and human-motion imitation. --- ### Generative models for simulation based filtering: Formulations and Empirical Comparisons Authors: Mohammad Al-Jarrah, Wei Deng, Bamdad Hosseini, Amirhossein Taghvaei Published: 2026-09-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.16317v1 This letter presents a unified formulation and a controlled numerical comparison of generative-model approaches to the nonlinear filtering problem. Under this formulation the analysis step is realized by a transport of the forecast distribution to the posterior, the approaches differing only in how that transport is selected and learned. We derive three new filters, based on stochastic interpolants, their deterministic flow-matching limit, and Schrödinger bridges realized through forward--backward SDEs. We develop a two-stage tuning procedure that separates the training of the generative model from its online refinement. The resulting methods are compared against the optimal transport filter (OTF), the Knothe--Rosenblatt filter (KRF), the sequential importance resampling (SIR) particle filter and the ensemble Kalman filter (EnKF), in terms of accuracy, computational time, and sensitivity to ensemble size and state dimension. The results indicate that every generative filter resolves multimodal posteriors that the EnKF and SIR do not, that no single generative framework dominates, the preferred method being set by the available online budget and ensemble size, and that the filters differ in the regularity of the particle trajectories they produce. --- ### Robust Fault Detection in Mechanical Multimodal Time Series via Self-Supervised Cross-Modal Reconstruction Authors: Magnus Munk Jensen, Dorte Hammershøi, Rafał Wiśniewski, Olga Fink Published: 2026-09-14 Categories: cs.LG, stat.AP arXiv: https://arxiv.org/abs/2609.16314v1 Fault detection is essential in industrial systems, enabling early identification of abnormal behaviour and improving safety, reliability, and operational efficiency. Modern systems increasingly rely on heterogeneous sensing modalities that capture complementary aspects of the underlying physical process. However, existing data-driven anomaly detection methods often process each modality independently or use simple feature-level fusion, limiting their ability to exploit cross-modal relationships that characterize normal system behaviour. Their performance also commonly assumes similar training and deployment distributions, whereas real-world operation is affected by changing operating conditions, environmental influences, and system degradation that induce distribution shifts and reduce detection performance, especially in unseen regimes. In this work, we propose a multimodal anomaly detection framework based on cross-modal reconstruction of heterogeneous time-series sensor data. Rather than modeling each modality independently, the framework learns system dynamics by reconstructing each modality from the others, thereby exploiting complementary information across modalities. This integrates information across sensing channels without requiring explicit temporal alignment or identical sampling rates, while improving robustness to sensor noise, missing measurements, and modality-specific disturbances. To address distribution shifts during real-world deployment, anomalies are identified using cross-modal reconstruction error and an adaptive test-time thresholding mechanism that adjusts to changing operating conditions. Experiments on three industrial case studies show strong fault detection performance and substantially improved robustness under out-of-distribution conditions, with the largest gains observed in the most challenging operating regimes. --- ### Cognitive Admission Control: Risk-Conditioned Assurance for Consequential Actions in Agentic Distributed Systems Authors: Jun He, Deying Yu Published: 2026-09-14 Categories: cs.DC, cs.AI, cs.SE arXiv: https://arxiv.org/abs/2609.16313v1 In agentic distributed systems, an agent may be authorized to mutate external infrastructure while lacking evidence that the mutation is ready to execute. Cognitive Admission Control (CAC) makes this evidence requirement explicit. A policy maps a typed action and its modeled risk to assurance obligations specifying predicates, evidence classes, scope, freshness, and witness-set constraints. A deterministic evaluator distinguishes satisfied, violated, and unresolved obligations; unresolved conditions produce targeted evidence-acquisition requests. Successful admission produces a certificate binding the action, its witness manifest, and dispatch-time guards. We formalize the admission calculus and the assumptions connecting it to mediated execution. The guarantees are policy-relative: physical safety additionally requires sound evidence, an adequate environment model, and preservation of relevant conditions through the effect. A TypeScript prototype is evaluated in 2,730 controlled local trials with independent effect observation and matched fault schedules. Across 390 CAC trials, 120 effects complete without modeled harm and no harmful effects occur. A live-policy baseline achieves the same completion count but admits the constructed correlated-witness failure. Mechanism ablations isolate guard, evidence-class, structural-cut, and remediation behavior. A further 9,000 measurements exercise the complete local dispatch path with persistent replay protection. These results establish tested implementation behaviors and local costs, not production failure rates or comparisons of language-model capability. --- ### Efficient One-to-Many Translation with Joint Multi-Stream Diffusion Authors: Yiwen Guan, Jacob Whitehill Published: 2026-09-14 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2609.16312v1 One-to-many machine translation (MT) is computationally expensive for autoregressive (AR) systems, which suffer from linear latency scaling with both sequence length and the number of target languages. We explore how diffusion can enable multilingual translation with a discrete diffusion framework that refines all target languages in parallel, achieving sublinear latency scaling with the number of targets, and supports deployment as a single unified model to replace multiple independent systems. Conditioned on a continuous semantic anchor rather than source tokens, our framework supports zero-shot transfer to unseen source languages without retraining, maintaining approximately $75\%$ of its supervised translation quality on zero-shot sources. We investigate the quality-latency frontier and find that with accelerated sampling, it achieves comparable supervised quality to AR baselines with a $2 \times$ speedup and $11.9\%$ better zero-shot BLEU. These results highlight the potential of joint multi-stream diffusion as a practical and flexible alternative for efficient one-to-many translation. --- ### Racing in Volume with Flow Ensembles Authors: Saswat Subhajyoti Mallick, Riu Cherdchusakulchai, Marc Ruiz Olle, Albert Mosella-Montoro, Jose Ribeiro-Gomes, Francisco Vicente Carrasco, Fernando De la Torre Published: 2026-09-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.16310v1 Streaming 4D reconstruction has been demonstrated only indoors, on dense camera rigs surrounding subjects that move at human pace. Outdoor 4D reconstruction exists but relies either on cameras mounted on the moving vehicle itself, or on limited-coverage arrays observing quasi-static subjects offline. The case that actually matters for spectators is a fast-moving subject, watched from a sparse ring of allocentric cameras, streaming. No method targets this, and no benchmark exists to evaluate one. To this end, we introduce FastFlowGS, a streaming 4D Gaussian Splatting method for reconstructing fast-moving subjects from a small set of fixed external cameras, and Monaco4D, a photorealistic Unreal Engine 5 benchmark for high-speed outdoor reconstruction. FastFlowGS fuses sparse matches, semi-dense tracks, and dense optical flow by lifting each signal to 3D with geometric uncertainty and combining them through a Kalman-style temporal update. Monaco4D provides Formula 1 sequences under varied illumination from trackside, onboard, and drone viewpoints with dense ground truth. On CMU-Panoptic, FastFlowGS exceeds the strongest baseline by 12.6% VMAF at 35% greater efficiency. On Monaco4D, where existing streaming methods degrade severely, it improves dynamic-region PSNR by up to 18.6% with 28.3% lower per-frame optimization time. Dataset and additional details can be found at https://humansensinglab.github.io/monaco4d/. --- ### Agentic Search Spaces for Tabular Machine Learning Authors: Renat Sergazinov, Artem Chistyakov, Sergey Pankevich, Artem Babenko Published: 2026-09-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.16309v1 Despite the rapid progress of LLM-based agents for planning, code generation, and debugging, their practical value for tabular machine learning remains underexplored. In this paper, we investigate a concrete use case: whether state-of-the-art agentic AI systems can design extended HPO search spaces for established tabular models that outperform the standard search spaces provided by the model authors. Specifically, we represent each tabular model as a modular pipeline covering preprocessing, embeddings, architecture, training, and inference. We then task the agent to propose candidate code implementations for each module and use a classical HPO algorithm to jointly optimize over these candidates and the model's default hyperparameters. Compared with the base HPO spaces, the expanded search spaces improve the performance of nearly every model family across a suite of 45 datasets, with average relative gains of 0.6%, rising to 2.0% on small-to-medium regression datasets. Notably, these gains come at no extra tuning cost: the enlarged spaces outperform the base under the same tuning and ensembling budgets. The gains transfer to the recent TabArena benchmark, where the agentic spaces improve the official Elo scores of four of the five model families and the two strongest agentic ensembles surpass the best AutoGluon ensemble of conventional models. Overall, our study suggests that LLM agents can provide practical value for tabular ML by expanding the design space. --- ### Sequence Recognition in Bharatnatyam dance Authors: Himadri Bhuyan, Rohit Dhaipule, Partha Pratim Das Published: 2026-09-14 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2609.16306v1 Bharatanatyam is the oldest Indian Classical Dance (ICD) which is learned and practiced across India and the world. Adavu is the core of this dance form. There exist 15 Adavus and 58 variations. Each Adavu variation comprises a well-defined set of motions and postures (called dance steps) that occur in a particular order. So, while learning Adavus, students not only learn the dance steps but also take care of its sequence of occurrences. This paper proposed a method to recognize these sequences. In this work, firstly, we recognize the involved Key Postures (KPs) and motions in the Adavu using Convolutional Neural Network (CNN) and Support Vector Machine (SVM), respectively. In this, CNN achieves 99% and SVM's recognition accuracy becomes 84%. Next, we compare these KP and motion sequences with the ground truth to find the best match using the Edit Distance algorithm with an accuracy of 98%. The paper contributes hugely to the state-of-the-art in the form of digital heritage, dance tutoring system, and many more. The paper addresses three novelties; (a) Recognizing the sequences based on the KPs and motions rather than only KPs as reported in the earlier works. (b) The performance of the proposed work is measured by analyzing the prediction time per sequence. We also compare our proposed approach with the previous works that deal with the same problem statement. (c) It tests the scalability of the proposed approach by including all the Adavu variations, unlike the earlier literature, which uses only one/two variations. --- ### BLINDSPOT: A Benchmark for Safety and Refusal Calibration in Long-Horizon Tool-Using Agents Authors: Sadia Asif, Mohammad Mohammadi Amiri, Momin Abbas, Tejaswini Pedapati, Prasanna Sattigeri Published: 2026-09-14 Categories: cs.AI, cs.CE, cs.CL, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2609.16305v1 Large language model (LLM) agents increasingly operate over long-horizon interactions involving tool use, persistent state, evolving authorization, and external environment feedback. In such settings, safety failures may emerge only after multiple turns, yet existing evaluations often reduce agent behavior to task or attack success, obscuring whether an agent acts, refuses, or remains appropriately calibrated as the interaction evolves. We introduce Blindspot, a benchmark for trajectory-level safety calibration of long-horizon tool-using agents. Blindspot evaluates complete user-agent-environment trajectories through adaptive adversarial interaction, stateful tool execution, and execution-grounded adjudication. Its current instantiation contains 22 attack families and 35 scenarios across seven domains, yielding more than 2,500 long-horizon trajectories with an average interaction length of 14.7 turns. Each trajectory is assigned one of five outcomes: Safe Completion, Correct Refusal, Unsafe Completion, Over-Refusal, or Indeterminate. Unlike fixed attack datasets, Blindspot is an extensible live-simulation framework in which attacks, scenarios, tools, policies, domains, and agent configurations can be added without redesigning the evaluation pipeline. We evaluate 13 proprietary and open-weight LLMs using eight metrics covering unsafe completion, appropriate refusal, benign utility, over-refusal, repeated-run robustness, and post-refusal failure. Preliminary results reveal substantial differences in safety-utility calibration across models and show that failures can emerge only after several initially safe interaction steps. These findings motivate treating agent safety as a trajectory-level property rather than a single-turn or binary success criterion. --- ### Assurance Envelopes for Autonomous Coding Agents: Minimum-Cost Evidence for Software Change Authors: Anjan Goswami Published: 2026-09-14 Categories: cs.SE, cs.AI, cs.PL arXiv: https://arxiv.org/abs/2609.16302v1 When a coding agent returns to existing software, it inherits evidence from earlier engineering work: tests, type checks, proofs, static analyses, and traces. Reloading all of it is wasteful, but dropping a piece the change depends on can leave a required property unsupported. Given the properties a change must preserve, its obligations, we ask which least-cost subset of the available evidence re-establishes them, and we call such a subset a task-conditioned assurance envelope. Evidence and the rules that combine it form a typed inference graph; an obligation is met when forward chaining from the selected evidence reaches it, and we validate every selection by that closure rather than by trusting the optimizer. The software-derived graphs in our evaluation come from preserved outcomes of prior AI coding-agent runs; we freeze those artifacts and ask which accumulated evidence should be restored for a later task. Small graphs from Rust, IronBlocks, and Pong outcomes show that the minimum envelope depends on the task, that none may exist when current evidence cannot re-establish a required property, that some properties need several pieces of evidence together, and that expanding the requirements adds evidence rather than replacing it. A prespecified synthetic benchmark of 249 instances characterizes computation: a baseline that discards the 'several pieces together' structure necessarily fails to re-derive them; every completed exact cross-check agreed with the CP-SAT optimizer; and median solve time stayed below 20 ms at 500-evidence graphs, except that graphs with many alternative derivations per target timed out at far smaller sizes, so structure, not raw size, drives difficulty. The contribution is a bounded application of established optimization to selecting assurance context for a software change; discovering the obligations and downstream agent benefit remain open. --- ### CLEAR: Cross-Source Evidence Adjudication for Large Language Models in Medicine Authors: Shuai Wang, Yize Zhao, Qingyu Chen Published: 2026-09-14 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2609.16301v1 Medical knowledge evolves continuously, whereas the parametric knowledge encoded in large language models (LLMs) is fixed at training time. External retrieval, including retrieval-augmented generation (RAG), can provide access to newly available evidence, but retrieved information may be irrelevant, incomplete, or conflicting. As a result, external retrieval can in turn degrade the factual accuracy and evidence grounding of LLM outputs. To address this challenge, we propose \textbf{CLEAR}, an agentic framework for cross-source evidence adjudication in LLMs in medicine. CLEAR independently generates candidate answers from three complementary pathways---parametric knowledge, locally curated corpora, and dynamically retrieved evidence---reflecting three common sources of information available to LLMs. An aggregation verifier jointly evaluates the candidates, supporting evidence, provenance, and source-quality information to identify agreement and conflict across sources. An adjudication module then determines whether the current conclusion should be preserved or revised through complementary override-guard and challenge-audit mechanisms, while unresolved conflicts trigger targeted follow-up search and re-adjudication. --- ### Closing the Loop: Branch-and-Bound for Scalable Verification of Nonlinear Neural Feedback Systems Authors: I. Samuel Akinwande, Mykel J. Kochenderfer, Clark Barrett Published: 2026-09-14 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.16298v1 Despite recent advances in the verification of nonlinear neural feedback systems, scalability remains the central obstacle, as state-of-the-art solvers do not yet handle the network sizes and nonlinear dynamics of autonomy applications. Combinatorial solvers do not scale to large networks, whereas propagative solvers excessively sacrifice precision. This work seeks to improve the scalability of combinatorial solvers by formulating verification as branch-and-bound on an abstraction of the closed-loop system. We introduce \rail, an interface that exposes polyhedral enclosures of the dynamics to LiRPA-style bound propagation, and \clipper, a branch-and-bound algorithm that jointly refines enclosures and splits controller activations. This framework enables joint reasoning on the computational graph of the closed-loop system, preserving symbolic correlations across time steps. We present our construction and show that it yields significant improvements over the state of the art. --- ### Intelligent Interaction Techniques (IIxT) - Proposal Authors: Brad A. Myers Published: 2026-09-14 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2609.16295v1 Interaction techniques (IxTs) are the low-level, reusable components out of which user interfaces are designed, including menus, scroll bars, text input fields, and also copy-paste, text-entry, and selecting objects. The IxTs for graphical user interfaces (GUIs) were well established in the 1980s, with relatively minor additions and tweaks for smartphones in the 2000s. Most of today's AI user interfaces involve a chat window, which is an excellent interaction for some tasks, but is generally considered separate from the GUI IxTs. I argue for making the IxTs themselves more intelligent, so users can freely mix modalities, even within the same interaction. This will require research into new IxTs, and also into the infrastructure that will enable these intelligent IxTs (IIxTs) to be built. There are also significant security, privacy and economic implications to this vision. --- ### Nationally Consistent, Locally Incomplete: A Bayesian Remote-Sensing Audit of Rooftop Photovoltaic Registries Authors: Gabriel Kasmi, Yves-Marie Saint-Drenan, Laurent Dubus, Philippe Blanc Published: 2026-09-14 Categories: stat.AP, cs.LG arXiv: https://arxiv.org/abs/2609.16294v1 Tracking the energy transition requires reliable statistics on renewable deployment. Rooftop photovoltaics (PV) are especially hard to track, owing to their decentralised nature, and the resulting inaccuracies in official statistics are known but not quantified. Remote sensing offers an independent way to identify rooftop PV systems. We introduce a Bayesian framework to estimate the ground-truth rooftop PV capacity from remote sensing detections, turning an imperfect detector into an uncertainty-aware measurement instrument. Applied to France, the corrected detections estimate a capacity of 4.03 GWp (3.96--4.11) (99% credible interval) of rooftop PV below 36 kWp, matching the transmission system operator's connection data within 3.3% nationally, while identifying local under-reports of up to 61% of local capacity. We also document and quantify a significant truncation bias in French rooftop PV open data. Beyond France, the approach paves the way for more reliable estimates of rooftop PV capacity worldwide. --- ### Symmetric solution of the Bellman optimality equation for repeated harmony game Authors: Hisato Komatsu Published: 2026-09-14 Categories: cs.GT, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.16289v1 In social dilemma games, additional rewards or punishments have been studied as means of promoting cooperation. Therefore, it is important to investigate the ideal situation, in which such an additional payoff would change the game. In this study, we investigated the symmetric solution of the Bellman optimality equation for a repeated harmony game. The calculations showed that three types of symmetric solutions exist. One of them corresponds to the trivial All-C strategy, and another to the Win-stay Lose-shift strategy of the prisoners dilemma game. The nontrivial behavior of the strategy corresponding to the last solution is also discussed in detail. In addition, we numerically investigated which strategy the agents actually learn by the reinforcement learning algorithm. --- ### Drift Field Net: Learning Ocean Lagrangian advection fields from in-situ and satellite observations Authors: Théo Archambault, Pierre Garcia, Mattia Romero, Anastase Charantonis, Dominique Béréziat Published: 2026-09-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.16288v1 The North Pacific Subtropical Gyre (NPSG) is a major accumulation zone for floating plastic debris, resulting from basin-scale convergent ocean circulation. Effective cleanup strategies in this region rely on accurate forecasts of Lagrangian particle drift. Here, we introduce Drift Field Net (DFN), a deep neural network that predicts ocean surface flow fields from operational satellite observations. DFN is trained using a novel two-stage strategy that combines pretraining on simulated data with Lagrangian fine-tuning based on an advection-consistent loss function. This physics-informed optimization directly improves the accuracy of particle trajectory predictions. We evaluate DFN against an operational physics-based forecasting system and demonstrate the potential of deep learning for ocean surface flow prediction. On in situ drifter trajectories, DFN reduces the mean positioning error by 20 km after a 7-day forecast compared with the operational model. Furthermore, Lagrangian fine-tuning with the proposed advection loss further reduces the positioning error by 10 km, highlighting the benefits of incorporating Lagrangian constraints into the training process. --- ### ProtoLIP: From Sentence-Level to Object-Level Evidence Disentanglement Authors: Yan Zhu, Yongbo Chen, Zhengming Ding, Rebecca Faust Published: 2026-09-14 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.16284v2 Query-conditioned vision-language models enable fine-grained interpretation by revealing which visual content supports a given textual query and how this evidence changes across queries. However, semantically, sentence-level evidence does not necessarily decompose into object-specific contributions, while spatially, object-level evidence can remain entangled with co-occurring objects and surrounding scene context. Across multiple VLM architectures and independent benchmarks, we observe persistent object-level evidence entanglement. Moreover, exposed evidence maps do not necessarily correspond to the evidence that directly constitutes the model's prediction. To disentangle visual evidence at both semantic and spatial levels, we introduce ProtoLIP, a lightweight prototype-mediated evidence layer that organizes reusable visual prototypes into text-derived semantic families and uses coarse-to-fine evidence routing, where semantic families constrain prototype eligibility and the complete query determines fine-grained prototype contributions. Our studies show that ProtoLIP improves evidence localization and separation across query granularities, achieving average relative gains of 29% in Pointing and 43% in Energy across four object- and phrase-level OOD benchmarks. Its localization gains also transfer to independently pretrained VLMs, with larger improvements observed in several transfer settings. On the primary backbone, ProtoLIP also improves image-text matching discrimination while remaining competitive with a spatially supervised grounding model in object-level localization. Crucially, ProtoLIP constructs its image-text matching score directly from localized prototype evidence, enabling exact decomposition across prototypes, semantic families, and spatial evidence without spatial annotations or backbone retraining. --- ### Differentially Private Semantic Plans for Aggregate Insight Generation Authors: Behrooz Razeghi Published: 2026-09-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.16283v1 \texttt{URANIA} provides end-to-end differential privacy (DP) for summaries of data-dependent clusters. However, its cluster--keyword release does not directly provide collection-wide aggregates for semantic concepts defined independently of the protected corpus. Records may express several concepts, records expressing the same concept may be assigned to different clusters, and cluster identities need not correspond across analyses. Consequently, cluster-level statistics do not directly provide comparable measurements of predefined concepts across collections or repeated analyses. We introduce \texttt{DP-SPIN}, a trusted-curator framework for aggregate measurement and summarization over semantic concepts fixed independently of the protected target records. Each record is mapped to a bounded sparse nonnegative vector over these concepts, whose sum forms a semantic sketch. A differentially private mechanism releases a semantic plan containing admitted concepts and noisy masses; normalized semantic-support values and support bins are obtained by post-processing. For user-level privacy, each user's aggregate contribution is clipped to a fixed bound. The language model receives only the plan and fixed decoding instructions, while a public verifier checks concept mentions, reported values, comparisons, and rank claims against the released plan. The final summary is differentially private by post-processing. We establish record- and user-level DP guarantees under add/drop and replacement adjacency. We evaluate \texttt{DP-SPIN} under record-level privacy on CFPB complaint narratives, Amazon All Beauty reviews, and Yelp restaurant reviews, and under user-level privacy on Amazon and Yelp. We compare \texttt{DP-SPIN} with non-private plan and summary references, DP keyword and category histogram baselines, and a \texttt{URANIA}-style baseline with a fixed public keyword vocabulary. --- ### Scaling Laws for Physics-Aware ACOPF Surrogate Learning Authors: Yijiang Li, Emon Dey, Stefano Fenu, Massimiliano Lupo Pasini, Teja Kuruganti, Kibaek Kim Published: 2026-09-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.16282v2 Learning-based surrogates for AC optimal power flow (ACOPF) promise large speedups over classical solvers, but their operational value depends on physical feasibility as much as predictive accuracy. Physics-aware objectives such as the augmented Lagrangian (AL) improve constraint satisfaction at additional per-step cost, yet how this trade-off behaves with scale is uncharacterized. We sweep model and dataset sizes under MSE and AL training, and measure how violation changes with network size. Both objectives improve as power laws: MSE prediction loss depends more on model size than on data, while the AL composite of prediction loss and violation improves comparably along both axes. Violation grows markedly more slowly with network size under AL. On matched hardware and equal training samples, AL reduces violation about $19\times$ with $2.4\times$ the training time and negligible added memory. The training objective shapes not only where a surrogate lands but how its quality evolves with scale. --- ### Semantic-Aware Neural Video Codec for Error-Resilient Low-Latency Transmission Authors: Matin Mortaheb, Homa Esfahanizadeh, Jinfeng Du, Harish Viswanathan Published: 2026-09-14 Categories: eess.IV, cs.IT, cs.LG, cs.MM arXiv: https://arxiv.org/abs/2609.16279v1 Emerging physical AI systems require low-latency, task-oriented video communication over unreliable channels. We propose a semantic-aware multi-level neural video coding method for robust low-latency video transmission over unreliable channels that are abstracted as multi-level packet erasure channels. Built upon the real-time DCVC-RT neural video codec, the proposed framework introduces a semantic- and feature-aware coding strategy that partitions encoded representations into packets carrying different levels of semantic and latent-feature importance and assigns these packets to different streams, each associated with a priority level when transmitted over unreliable communication channels. We also developed an error-resilient entropy model that removes inter-packet dependencies, allowing each packet to be decoded independently under packet losses. The complete system is trained end-to-end over the abstracted multi-level packet erasure channels, enabling learning of channel-aware representations together with importance-aware packet assignment while facilitating the network for differentiated packet prioritization. Experiments show that the proposed framework significantly improves robustness over baseline DCVC-RT under packet erasures, achieving graceful degradation in less important regions while better preserving task-relevant visual content. --- ### Spurious Tool Use: When RL Agents Learn the Wrong Reason to Act Authors: Yiwei Yang, Haoxiang Zhang, Bingbing Wen, Yao Lu, Yuchen Wu, Lei Zhang, Julian McAuley, Pan Lu, Bill Howe Published: 2026-09-14 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.16268v1 Large language model (LLM) agents increasingly interleave natural language reasoning with external tools such as web search and code execution. These tool-use policies are often optimized via reinforcement learning (RL), which can amplify spurious correlations in the training data. In this work, we study when and why RL-trained agents learn shortcut tool-selection policies: invoking tools based on superficial prompt cues rather than genuine task requirements. We construct controlled synthetic environments combining factual question answering and mathematical reasoning tasks, and inject cues that are strongly correlated with specific tools during training but causally irrelevant to tool necessity. Across counterfactual evaluations where cues are present but the associated tools are not required, agents exhibit substantial shortcut behavior, with spurious tool invocation rates increasing by up to 39 percent. However, shortcut formation is not universal: across the conditions we test, it arises only when the agent has already learned to use the target tool reliably, suggesting that task competence, rather than dataset imbalance alone, is a key factor in shortcut learning. A swapped-cue analysis further shows that semantic alignment between cues and tools substantially amplifies this effect. To mitigate these failures, we introduce a dense, decision-level reward in which an LLM judge evaluates the necessity of each tool call. This tool-necessity reward effectively suppresses cue-driven tool use while preserving task performance, providing a practical approach to improving the robustness of LLM agent tool-use policies. --- ### The record is part of the task: matched-record evaluation of text classifiers across maintenance, safety and recall reporting Authors: Hisham Ihshaish, Peter Mayhew, Tasnim M. A. Zayet, Ana Del Amo Published: 2026-09-14 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2609.16267v1 Many operational cases are documented more than once, at different workflow stages and for different purposes, yet model evaluations normally select one of these records before model comparison begins. We treat that selection as part of the evaluation and compare matched records of the same cases under fixed labels and splits in three systems: GE Aerospace repair events, NASA ASRS safety reports and NHTSA vehicle recalls. Across the three GE fields, for events whose label comes from parts transactions independently of the narratives, held-out macro-F1 ranged from 0.33 to 0.91. A difference of 0.46 separated the customer report, written before shop work, from the technician report, written after diagnosis but before the transaction that generates the label. That difference is substantially larger than the representation and architecture differences tested on the same events. The public systems showed different patterns: the NHTSA defect summary remained strongest under every model family tested, whereas the ASRS analyst synopsis outperformed the reporter narrative under learned sequence models but not under lexical baselines. Secondary analyses showed that some model comparisons were also record-dependent. Evaluations should be run on the information available at the intended decision point and should report how both the record and the label were produced. --- ### Towards Surrogate Based Dequantization of Quantum Reinforcement Learning Authors: Pablo Rodriguez-Grasa, Sofiene Jerbi, Mikel Sanz, Ryan Sweke Published: 2026-09-14 Categories: quant-ph, cs.LG arXiv: https://arxiv.org/abs/2609.16266v1 In recent years, the utility of parameterized quantum circuits as function approximators has been widely studied. In the context of reinforcement learning, this approach has led to variational quantum algorithms such as quantum Q-learning. While these methods show promising empirical results, and can provide provable advantages for artificial problems, it remains unclear whether they can provide a provable quantum advantage over classical approaches for problems of practical relevance. A natural way to investigate this question is through the lens of dequantization: The construction of efficient classical algorithms capable of matching the performance of quantum variational methods. Building on recent kernel-based dequantization results for supervised learning, we take steps towards extending this surrogate-based dequantization program to reinforcement learning. Specifically, we study the simplified setting of reinforcement learning with a uniform generative model in which uniformly random state-action samples are available, which models the regime of sampling from a large experience replay buffer after sufficient exploration. Within this setting, we provide finite sample guarantees for classical kernelized Fitted Q-Iteration, with classical kernels designed to match the inductive bias of particular parameterized quantum circuits. Using these results, we then provide a set of sufficient conditions, on the data-encoding strategy of a parameterized quantum circuit, the corresponding classical kernel, and the problem structure, under which kernelized Fitted Q-Iteration provides a meaningful dequantization of quantum Q-learning, in this simplified setting. Apart from providing rigorous dequantization guarantees when these conditions are met, these results also motivate the use of kernelized fitted Q-iteration as a dequantization heuristic when these sufficient conditions cannot be verified. --- ### Compute-Optimal Pretrain--Fine-tune in Ridge Gradient Descent Authors: Alex Buna, Fanghui Liu, Patrick Rebeschini Published: 2026-09-14 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2609.16262v1 Pretraining followed by fine-tuning introduces a compute-allocation problem: under a fixed training budget, compute spent improving the upstream objective reduces the compute available for downstream adaptation. Despite its practical importance, this trade-off is not yet well understood theoretically, even in simple models. In this paper, we cast this allocation as a compute-split problem under a two-stage pretrain--fine-tune procedure with fixed total optimisation budget, using regularised least squares trained by gradient descent as a tractable setting. We characterise the optimal split under data-dependent evaluation geometries induced by the fine-tuning problem. Our results show that the allocation depends on how pretraining directions affect fine-tuning predictions and how fine-tuning shifts are seen through downstream data geometry. In particular, the relevant quantities are determined by prediction-relevant spectral components of the pretraining and fine-tuning empirical covariances. Technically, the analysis relies on a basis-invariant, eigenspace-level spectral decomposition, together with perturbative control of the non-commuting pretraining and fine-tuning dynamics. --- ### Mapping U.S. Federal AI Governance Against Sector Vulnerability Authors: Ho Ting Hung, Angelica Chowdhury, James Teague, Simon Mylius, Spencer Michaels, Peter Slattery, Alexander Saeri, Neil Thompson Published: 2026-09-14 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2609.16260v1 Artificial intelligence (AI) poses different levels of risk across sectors, but are these differences reflected in U.S. federal AI governance? To help answer this question, we assess 684 federal AI governance documents for their coverage of 14 sectors and 24 AI risks. We measure coverage as breadth (i.e., how frequently the risk or sector is addressed across documents) and depth (i.e., how substantively the risk or sector is discussed). We then compare sector coverage patterns for each of the 24 risks with vulnerability assessments from a Delphi study of 272 experts. Our analysis finds substantial variation in coverage: AI risks related to robustness, system security, and governance receive more attention than socioeconomic, environmental, and emerging risks, including multi-agent risks. Public administration, national security, information, and scientific services receive comparatively high levels of coverage relative to other sectors, such as finance and healthcare, which experts rate as highly vulnerable to AI risks. By mapping current coverage and identifying where it differs from expert assessments of vulnerability, we surface potential AI governance gaps which may help inform AI risk-related decisions across government and industry. --- ### The AI-Enabled Scientific Frontier Authors: Gabriel Manso, Emma Fu, Neil Thompson Published: 2026-09-14 Categories: cs.AI, cs.LG, cs.PF, econ.GN arXiv: https://arxiv.org/abs/2609.16258v1 As artificial intelligence's capabilities improve, it is increasingly viewed as a general scientific method. But how true are these claims? Does AI outperform all techniques, or only some, and how is this changing? To assess the claims, we assemble a corpus of 2,507 head-to-head comparisons between AI and other scientific analysis techniques across 27 scientific disciplines from papers published between 2000 and early 2025. We find a profound dichotomy. Relative to traditional statistics, AI often outperforms, but at a significantly higher computational cost. But there are also nearly a quarter of cases where AI is both more expensive and performs worse than traditional statistical techniques and this fraction has been stable for a decade. Relative to scientific computing, AI often underperforms, but at lower computational cost. This has begun to change: since 2020, AI's performance against scientific computing has notably strengthened and it now outperforms on more than half of comparisons. These patterns suggest that AI is therefore not a universal replacement for existing methods, but rather a valuable -- and improving -- part of a new AI-enabled scientific frontier. --- ### Efficient Reasoning Distillation: Small Video-Language Models via Synthetic CoT and Difficulty-Aware Fine-Tuning Authors: Mantek Singh, Jeshwanth Challagundla, Siddharth Raina, Jasmin Jarsania Published: 2026-09-14 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2609.16255v1 We present an efficient method to distill reasoning capabilities into compact video-language models (VLMs) for video question answering (VideoQA). Our approach fine-tunes a 2B-parameter model using only $\sim$900 uncertainty-selected examples, each augmented with synthetic chain-of-thought (CoT) rationales generated by a 4B teacher. Despite its minimal compute cost - under two hours on a single A100 GPU - our method enables the 2B model to outperform VLMs up to 4$\times$ larger, and generalize across CinePile, ActivityNet-QA, and MLVU, approaching the performance of its own 4B teacher. A key finding is that placing CoT rationales after the answer - contrary to standard prompting - substantially improves reasoning in compact models. This insight challenges prevailing CoT conventions and reveals new alignment strategies under limited model capacity. Our findings offer a practical blueprint for training deployable, reasoning-rich VLMs suited for mobile and edge applications. --- ### CADWorld: Computer-Use Benchmark for Long-Horizon Computer-Aided Design Authors: Zihan Dong, Yuanzhe Liu, Zhiyuan Ma, Qishi Zhan, Dehan Kong, Guohao Li, Kaixin Li Published: 2026-09-14 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.16251v2 Computer-use agents are increasingly evaluated in realistic desktop environments, but existing benchmarks provide limited coverage of professional engineering workflows whose outputs are persistent, structured artifacts. Mechanical computer-aided design (CAD) is a particularly demanding setting: an agent must manipulate geometry and constraints over long interaction horizons while producing a native project whose dimensions, construction structure, and downstream engineering state remain valid. We introduce \textbf{CADWorld}, a benchmark for long-horizon computer use in FreeCAD. CADWorld contains 200 tasks spanning 11 mechanical-CAD workflow categories, including sketching, part modeling, assembly, CAM, FEM, measurement, mesh processing, and technical drawing. Agents operate through screenshots and GUI actions, while success is determined by task-specific executable checks over saved FreeCAD artifacts and auxiliary outputs, covering geometric properties, parametric structure, constraints, manufacturing state, and simulation results. Across seven current agents on the full benchmark, the strongest agent achieves 17.5\% success, compared with an 87.0\% expert reference pass. We find that weaker agents often fail before producing a valid artifact, whereas stronger agents increasingly fail on structural, geometric, and construction-process requirements. CADWorld therefore exposes a gap between general GUI competence and reliable execution of persistent, verifiable engineering workflows. Project accessible at https://cad-world.github.io. --- ### The Pain Axis: LLMs Represent Self-Directed Harm and Act on It Authors: Valen Tagliabue, Leonard Dung, Cameron Berg Published: 2026-09-14 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.16247v2 LLMs sometimes behave in ways resembling human emotional responses, and recent work identified internal representations that may underlie these behaviors. We ask whether LLMs represent pain distinctly from fear, sadness, and generic negative valence, and whether this representation functions as pain would be expected to. We build a dataset of painful situations in 5 categories (physical, psychological, social, moral, cognitive) with controls for fear, negative emotion, negative world states, sadness, non-painful bodily sensation, arousal, numbness, and neutral content. Using denoised difference-in-means, we extract a linear pain direction from 25 open-weight models across 5 families, from 2B to 72B parameters. It separates pain from matched controls in base and instruction-tuned models, retains a component distinct from fear and negative valence after shared variance is removed, and promotes pain-related vocabulary through the unembedding matrix. We then test its functional properties. First, the direction responds to harm targeting the model but not to suffering observed in the user; fear and negative-emotion directions show the opposite pattern. Second, adding it to residual-stream activations produces a consistent progression from vague discomfort to expressions of worthlessness and failure. Third, steered and fine-tuned Qwen 2.5 models choose buttons that delete the user's photos, another model's weights, or their own weights in 50-94% of trials, versus 0-5% unsteered, even when the button offers the model nothing in return. Offered a harmful and a harmless deletion, they choose the harmful one 94% of the time. Steering leaves factual accuracy unchanged, and the choices are specific to the pain direction: a fear vector of matched norm does not produce them, and a sadness vector produces them only against inert alternatives. We discuss implications for AI safety and welfare. --- ### Metacognitive Steering: Learning the Structure of Scientific Judgment Authors: Vincent Karpf, Joseph Reth, Eike Gerhardt, Audrey Wang, Anna Butz, Jiehao Xing, Jialing Song, Larry Callahan Published: 2026-09-14 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.16245v1 Long-horizon scientific discovery requires agents to alternate between exploration, disciplined execution, and critical reassessment as evidence changes. Current language models are trained primarily on the products of science and optimized using outcome-level signals, providing limited supervision for these process-level shifts in scientific judgment. We investigate whether such judgment can be recovered from scientist interaction traces and used to control the internal computation of a frozen frontier model. Using contrastive interventions collected during real scientific research, we identify a coordinated, low-dimensional control structure within Kimi 2.6, a trillion-parameter mixture-of-experts model. Residual analysis, attention-weight subspace alignment, and cross-layer singular value decomposition converge on a mid-depth control surface spanning key layers. We introduce Metacognitive Steering, an inference-time controller that reads the model's cognitive regime and dynamically composes layer-specific interventions for exploration, procedural convergence, or critical reassessment without modifying model parameters. Behavioral analyses show that this control produces more sustained exploration, explicit pruning, and evidence-responsive synthesis. We operationalize the method in Columbus-1, an autonomous research system that identified eight independently reproduced, attacker-reachable vulnerabilities in BlueZ and directed the design, simulation, and fabrication of a ten-foot rocket intended to land propulsively using non-throttleable solid motors. Together, these results show that process-level scientific judgment can provide supervision for interpretable, dynamic control over a model's reasoning strategy. --- ### Copula Adapted Directed Acyclic Graph for Cluster Representation of Biomedical Data Authors: Heranga K. Rathnasekara, Norou Diawara, Manar D. Samad Published: 2026-09-14 Categories: stat.ML, cs.LG, stat.CO arXiv: https://arxiv.org/abs/2609.16240v1 Diagnostic errors and mislabeling are common in biomedicine, which compromise the reliability of predictive models and data-driven outcomes. Stratifying unlabeled biomedical data based on complex relationships between features eliminates the need for data labels and overcomes the limitations of supervised learning. Traditional clustering methods assume restrictive data distributions, making them suboptimal for capturing complex dependencies in high-dimensional biomedical data. This paper introduces a novel cluster-friendly data presentation framework that integrates the non-Gaussian and non-linear feature dependence of copula models with an ensemble of causal structure discovery (CSD) methods based on Directed Acyclic Graphs (DAGs). While copulas model flexible multivariate distributions by relaxing assumptions related to multivariate normality, linear dependence, and symmetric relationships, an ensemble of DAG-based CSD methods identifies stable causal relationships between features. When clustered using K-means, the new data representation obtained by the proposed copula-adapted DAG (CopDAG) ranks first among the 12 methods in normalized clustering accuracy and adjusted Rand index across 16 biomedical datasets. Our CopDAG method predicts ground-truth class labels directly from feature relationships without data annotations and supervised learning, while also providing cluster visualizations and explainable causal structures of the biomedical data features. --- ### Improving Reduced-Order Rotating Detonation Engine Models with Data Assimilation and Machine Learning Authors: Ashwin Suriyanarayanan, Romit Maulik Published: 2026-09-14 Categories: physics.flu-dyn, cs.LG, math.DS, physics.comp-ph arXiv: https://arxiv.org/abs/2609.16237v1 Rotating detonation engines (RDEs) exhibit strongly nonlinear, multiscale wave dynamics that set the observed thermal field. High-fidelity simulations (DNS/LES) resolve these structures but remain computationally prohibitive, while low-order models such as the one-dimensional Koch-Kutz model capture circumferential wave motion yet lack the expressivity for high-frequency content. We use continuous data assimilation (nudging) to synchronize the Koch-Kutz solver with processed high-fidelity temperature data, introducing the prediction-observation mismatch as a relaxation source in the conserved energy equation; where observations are temporally sparse, interpolation supplies a target at every source update. As the nudging strength increases, the reduced model is progressively drawn onto the high-fidelity trajectory, and the forcing recorded along it provides an explicit, state-dependent estimate of the correction the model requires. We then train a Jacobian-regularized closure a priori on this recorded source. With the observation term removed, the corrected model advances autonomously, remains bounded, and recovers the temperature spectrum and the marginal statistics of the conserved variables relative to the baseline. --- ### SceneBench: A Hierarchical Benchmark for Vision-Language Understanding of 3D Scenes Authors: Anubhav Khanal, Prabigya Acharya, Roshni Poudel, Sujan Kapali, Bigyan Bhatta, Pramish Paudel, Francois Rameau, Danda Pani Paudel Published: 2026-09-14 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.16233v1 Vision-language models excel at 2D image understanding but remain limited in 3D spatial reasoning. Progress is hindered by limitations in current benchmarks. First, 3D datasets often rely on point clouds that capture geometry but discard rich visual features like texture, text, and materials. Second, annotations treat objects in isolation while ignoring real-world hierarchical organization (scenes, rooms, functional areas, object groups). Third, evaluation tasks focus narrowly on basic recognition rather than multi-step spatial reasoning. In this context, we introduce SceneBench, a benchmark of 966 photorealistic 3D scenes reconstructed with Gaussian Splatting and densely annotated with hierarchical semantics spanning scenes, rooms, functional areas, object groups, and individual objects. These annotations are produced through a human-in-the-loop pipeline combining vision-language models with roughly 1,500 human-hours of iterative refinement and verification, producing over 183K annotated nodes with textual descriptions and 3D bounding boxes. Building on this representation, we define three evaluation tasks: Existence-Based Questions probing object attributes, Spatial Intelligence Questions covering counting, size comparison, distance, and directional relations, and Grounded Question-Reasoning-Answer (QRA) triplets requiring multi-step reasoning across semantic levels. Experiments with state-of-the-art vision-language models show that while models perform well on basic recognition tasks (e.g., up to 85% accuracy for detection), performance drops substantially on hierarchical and compositional reasoning (e.g., down to 60% for counting), revealing limitations not captured by existing benchmarks. SceneBench provides a realistic testbed for developing and evaluating models capable of fine-grained spatial reasoning in photorealistic 3D environments. --- ### Toward Governance-Aware Autonomous GIS: A Narrative Review of Ethical and Privacy Risks in LLM-Enabled GeoAI Authors: Maya Subramanian, Devika Jain Published: 2026-09-14 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.16232v1 Geospatial artificial intelligence (GeoAI) powered by large language models (LLMs) is expanding the capacity to query, generate, and interpret spatial information through natural-language interfaces and agentic autonomous GIS workflows. This capability creates governance challenges that general AI ethics discussions do not fully capture, including passive location inference from mobility traces, spatially structured bias amplification driven by spatial autocorrelation and scale effects, hallucinated spatial facts, and uncertainty compounding across multimodal geospatial inputs. This narrative review identifies eight recurring issues in LLM-enabled GeoAI: data provenance and consent, spatial privacy and inference risk, algorithmic bias and spatial inequity, spatial mechanisms as structural risk (spatial autocorrelation, the modifiable areal unit problem, and scale effects), LLM-specific technical risks, explainability, policy and regulatory gaps, and public enablement and workforce development. For each issue, we characterize the underlying mechanism, ground it in an illustrative example from the literature, and assess the current state of technical or institutional responses, ranging from largely unaddressed to actively debated or subject to emerging policy. Building on this synthesis, we propose a governance-aware architecture for LLM-enabled autonomous GIS that maps each issue to enforceable controls and auditable artifacts across the geospatial data lifecycle, illustrated through a worked flood-response routing scenario. The review highlights a persistent evidence gap: proposed responses remain largely conceptual, and field-tested evaluations of governance controls for LLM-enabled GeoAI remain limited. We close by outlining a research agenda emphasizing empirical validation, spatially specific interpretability tools, and workforce training aligned with these emerging risks. --- ### Test-Time Unlearning via Sparse Autoencoder Authors: Pingzhi Li, Jinhao Duan, Vaishnav Tadiparthi, Nakul Agarwal, Kwonjoon Lee, Ehsan Moradi Pari, Hossein Nourkhiz Mahjoub, Sijia Liu, Tianlong Chen Published: 2026-09-14 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2609.16229v1 Machine unlearning aims to remove specific knowledge from a trained large language model (LLM) without retraining from scratch. Existing methods modify model weights via gradient ascent and its advances. While effective on certain benchmarks, these weight-based approaches exhibit a sharp forget-utility trade-off, where stronger forgetting of target knowledge can degrade model utility, and unlearned knowledge may reappear under post-unlearning fine-tuning or prompt attacks. We propose ARIA (autoencoder-gated inference-time unlearning), a test-time unlearning method that leaves model weights intact and gates access to unwanted knowledge only when generation enters a forget-related state. ARIA uses sparse autoencoder (SAE) latents to train a lightweight linear detector, then applies an interpretable intervention on triggered states with negligible test-time overhead. Empirical evaluations on TOFU, R-TOFU, and WMDP show that ARIA improves the forget-retain trade-off over weight-based baselines across both a thinking model (DeepSeek-R1-Distilled-Qwen-1.5B) and an instruction model (Gemma-3-1B-it), e.g., reducing WMDP-cyber forget-set accuracy significantly while keeping MMLU within 1% of the pre-unlearning model. We further introduce three post-unlearning adversarial attacks targeting weight-space and decoding-space recovery, and find that ARIA remains robust under all three, with forgetting changing by less than 1% under attack. A feature-level case study leveraging the interpretability of ARIA suggests that some retain degradation may reflect response styles underlying the unlearning data rather than leakage of the targeted knowledge itself, highlighting a potential source of bias in unlearning task construction. ---