# Research Papers — 2026-10 · bundle page 42 of 156 > Full-text markdown of papers #2051–2100 of 7799 published in 2026-10, newest first. AI-readable mirrors of the full 7799-paper 2026-10 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-10/page/42 [← Previous bundle](https://aipod.dev/papers/archive/2026-10/page/41.md) [Next bundle →](https://aipod.dev/papers/archive/2026-10/page/43.md) ### COMPASS: Membership Inference Attack Against Vision Large Language Models via Adaptive Noise Calibration Authors: Damien Lo, Hong Kyu Lee, Ruixuan Liu, Li Xiong Published: 2026-10-12 Categories: cs.LG, cs.CR arXiv: https://arxiv.org/abs/2610.17332v1 Vision large language models (VLLMs) are deployed in privacy-sensitive domains, raising training-data exposure concerns. Existing gray-box membership inference attacks (MIAs) commonly rely on entropy statistics or generated descriptions, requiring costly generation with limited membership separation. Perturbation-based methods instead measure response changes but focus on large perturbations, leaving VLLM membership behavior under smaller perturbations poorly understood. We systematically characterize VLLM membership behavior under controlled Gaussian perturbations across noise levels at fine resolution. We find that optimal perturbation magnitude and membership-signal direction vary across model-dataset pairs. In many settings, a previously unstudied low-noise regime yields stronger separation than large perturbations, with members exhibiting lower divergence than non-members, reversing the conventional score direction. Other settings retain the conventional direction, demonstrating that neither a fixed perturbation magnitude nor a predetermined score orientation is universally reliable. We propose COMPASS, an adaptive gray-box MIA that calibrates both the perturbation magnitude and membership-score direction using a loosely distribution-matched, known non-member reference set. We instantiate COMPASS using Renyi-normalized KL divergence and Renyi divergence, with max-k aggregation over the most informative image-logit positions. Across LLaVA v1.5-7B, MiniGPT-4, and HuluMed-32B, spanning pretraining, instruction-tuning, and medical-image datasets, COMPASS outperforms baselines. On general-domain data, COMPASS achieves AUCs up to 0.88. On the distribution-matched medical evaluation, it reaches 0.64 AUC, while the strongest baseline remains at chance level. These results establish full-range adaptive perturbation analysis as an effective approach to VLLM membership inference. --- ### Do Theorem Provers Need Theorem-Proving Agents? mini-Lean-agent: A Coding-Agent Baseline for Lean Authors: Tomas Ortega, Simon Park, Ayush Khaitan, Liam Fowl, Alex Kontorovich, Sanjeev Arora Published: 2026-10-12 Categories: cs.AI, cs.LO arXiv: https://arxiv.org/abs/2610.17331v1 General-purpose coding agents use standard shell and file interactions, yet formal theorem-proving agents often rely on specialized, ad-hoc tooling. This makes it difficult to determine which components of theorem-proving agents provide benchmark gains: an improved base model, a specialized harness, a specific tool, or a combination of any of them. We introduce mini-Lean-agent, a deliberately minimal agent for Lean tasks whose only model-visible tool is bash. The model must use bash to inspect and edit the repository, search local libraries, invoke Lean, and manage its own intermediate work, while a separate trusted evaluator verifies the final artifact. We compare mini-Lean-agent against AxProverBase and Numina-Lean-Agent on the Putnam 2025 benchmark. Experiments with Gemini 3.8 Flash as the base model show that mini-Lean-agent solves 7/12 problems at \$2 per problem limit, compared with AxProverBase's 4/12. With Astra as the base model, mini-Lean-agent solves 12/12 problems at an average cost of \$1.28 per problem. This suggests that a generic coding agent with a minimal harness can already achieve strong performance on Lean benchmarks. Our results motivate using mini-Lean-agent as a standard baseline when evaluating theorem-proving infrastructure. --- ### The Curse of Knowledge in Role-Playing Language Models Authors: Xiao Zhang Published: 2026-10-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.17327v1 Role-playing language models speak as characters in games and agent simulations, where the system records what each character can hear, see and understand. We test whether characters respect these boundaries in 480 scenes, each with a counterfactual twin that changes only the hidden fact, so mentions of the twin's fact measure guessing. Across 11 open-weight models, characters use content from speech they cannot understand or hear at 67 and 72 percentage points (pp) above this baseline, although most models correctly state what the character perceives. This is a curse of knowledge. The leak extends to hidden actions and private messages and changes where characters search. Five of six proprietary models rarely leak, but compliance in strong models depends on input format. Changing only the scene layout or character description raises the rate in two otherwise compliant open-weight models from under 10 to over 60 pp, and combined changes raise two proprietary models from near zero to 13 and 21~pp. Writing the line as the scene's author leaks nearly as much as role-play, and thinking rarely helps. Giving models only what the character observes stops the leak without hiding what it may report. --- ### Thinking Outside the Bots: Human Ideas in AI's Semantic Blind Spots Are Not Inferior Authors: Kibum Moon, Dan R. Johnson, Kostadin Kushlev, Benjamin Lira, Indre Viskontas, James C. Kaufman, Roger E. Beaty, Angela L. Duckworth, Adam E. Green Published: 2026-10-12 Categories: cs.CL, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2610.17324v1 AI-generated outputs are frequently perceived as highly creative, but also tend to be more similar to each other (homogenized) than human ideas. Does the human heterogeneity that extends beyond AI reflect valuable thinking that AI misses? Alternatively, is greater human heterogeneity driven by lower-quality ideas and less effective thinking that AI avoids? We developed Expansion of Divergent Generative Expression (EDGE) to map AI's semantic "blind spots" by assessing how strongly/weakly individual human ideas were represented in a task-matched AI semantic comparison set. Specifically, we compared human-generated vs. AI-generated ideas across three open-ended tasks: college admissions essays, alternative uses for everyday objects, and interpersonal advice. Across all three tasks, human responses extended into semantic regions sparsely covered by AI outputs. These distinctively human responses showed no meaningful deficits in creativity, quality, or effectiveness, were associated with equal-or-better academic performance, and with credibly superior ratings and achievement for some outcomes. These ideas were thus not merely poor-performing variation; they performed as well as or better than ideas that overlapped more strongly with AI ideas. More distinctive human ideas tended to receive higher creativity ratings, but this relationship was weak or reversed for AI ideas. Taken together, these results suggest that differentiation among human-generated ideas does not reflect poor thinking that AI can safely omit, and instead may afford both individual and population-level advantages. --- ### SSM-Attack: Learning Where to Perturb for Black-Box Face Privacy Authors: Tunahan Parlayıcı, Erchan Aptoula, Yücel Saygın Published: 2026-10-12 Categories: cs.CV, cs.CR, cs.LG arXiv: https://arxiv.org/abs/2610.17323v1 Face recognition systems are deployed widely enough that a photograph shared online can be matched without its subject's consent. Generator-based protection methods rely on heavy pretrained backbones, multi-stage inference or visible semantic edits. We introduce SSM-Attack, a black-box face privacy framework built on Selective State Space Models. Rather than synthesizing the perturbation, the state-space model predicts in one linear-time pass a spatial allocation of the perturbation budget, marking which facial locations carry identity evidence; a short projected refinement then sets the values within this per-pixel budget. Against published benchmark results, SSM-Attack attains the highest average black-box attack success rate on all three evaluation sets: 87.10 percent on CelebA-HQ, 86.90 on LADN and 81.15 on FFHQ, the last from a network that never saw that dataset. The allocation network holds 5.73 million parameters, or 16.13 million with the frozen networks used by its quality terms. Under the same cap of 0.10 on the maximum per-pixel change, allocation improves structural similarity by 0.044, peak signal-to-noise ratio by 1.62 decibels and Frechet Inception Distance by 11.2 points over a uniform map while spending 37 percent of its capacity. Strong facial privacy protection therefore does not require a large generative prior; it requires knowing where to spend a small one. --- ### GPU Goldmines: Tunable WebGPU Kernels for Edge LLM Inference Authors: Rithik Sharma, Reese Levine, Zheyuan Chen, Ananthajit Srikanth, Yanwen Xu, Tyler Sorensen Published: 2026-10-12 Categories: cs.DC, cs.LG, cs.PF arXiv: https://arxiv.org/abs/2610.17321v1 As demand for LLM inference grows and consumer GPUs grow more capable, edge deployment is becoming increasingly attractive. WebGPU is compelling in this setting because it offers cross-platform portability and browser accessibility. However, these same strengths also make high performance difficult to achieve, as an implementation that performs well in one context may not perform well in another. To address this, we present GPU Goldmines, a framework for specifying, executing, and tuning WebGPU kernels. We instantiate GPU Goldmines with kernels for key LLM building blocks: matrix multiplication, matrix-vector multiplication, and flash attention. We characterize performance across diverse devices, shapes, and browsers, and use the resulting database to accelerate subsequent autotuning and configuration selection. On shapes drawn from Llama and Qwen models, our matrix multiplication kernels outperform ONNX Runtime and llama.cpp WebGPU kernels by 7.0x and 1.41x geometric mean, respectively, and deliver end-to-end improvements of 1.48x in the prefill stage of llama.cpp for chat workloads. --- ### Near-Optimal Regret Bounds for Monotone Stochastic Optimization under Semi-Bandit Feedback Authors: Tao Hu, Rohan Ghuge Published: 2026-10-12 Categories: cs.LG, cs.DS, stat.ML arXiv: https://arxiv.org/abs/2610.17320v1 Stochastic optimization models sequential decision-making under uncertainty, typically assuming known input distributions. When these distributions are unknown, \citet{agarwal2026semibandit} give an online-to-offline reduction for monotone stochastic optimization under semi-bandit feedback, where only probed variables are observed. Its expected regret relative to the offline guarantee is $\widetilde O(n\sqrt T)$, where $n$ is the number of variables and $T$ the horizon. For optimal stopping and Pandora's box, \citet{liu2025improved} achieve $\widetilde O(\sqrt{nT})$ using problem-specific algorithms. \emph{Can a general online-to-offline reduction achieve this improved rate?} We give such a reduction for strongly monotone stochastic optimization, answering the corresponding open question. Strong monotonicity is defined relative to the chosen offline algorithm. Our oracle-efficient reduction achieves $\widetilde O(\sqrt{nT})$ expected regret while preserving approximation guarantees for oracles satisfying the same condition. It combines Bernstein-type optimistic distribution estimates with a Hellinger stability bound for adaptive policy transcripts, aggregating squared marginal errors weighted by the executed policy's probing probabilities. The rate is optimal up to logarithmic factors for $T\ge n$, even under full feedback. Under monotonicity and uniformly bounded coordinate-wise variation, the same algorithm achieves $\widetilde O(n^{3/4}\sqrt T)$ expected approximation regret, improving the previous linear dependence on $n$. The exponent $3/4$ is sharp for its ordinary regret over instances and exact oracle choices. Our framework applies to prophet inequality, Pandora's box, best-of-$K$ selection, stochastic knapsack, stochastic orienteering, and stochastic submodular maximization. --- ### From Sampled Evidence to Radiology Reports: Objectives, Constraints, and Realization Authors: Kun Zhao, Haoteng Tang, Chenghua Lin, Liang Zhan Published: 2026-10-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.17318v1 Sampling multiple reports creates an inference problem: how should sampled evidence be converted into a final decision, and does a better structured decision yield a better report? We study these questions through a framework that separates the decision signal, scoring objective, and feasible decision set, followed by text realization. On MIMIC-CXR and IU-Xray, controlled comparisons across 13 generator configurations per benchmark under grouped development/test evaluation reveal three findings. First, changing the objective under fixed evidence and rule capacity changes predictions and their held-out metric trade-offs. Second, relaxing candidate constraints has objective-dependent effects under shared signals and frozen scores. Diagnostics connect the IU macro-oriented assertion increase to near-zero label thresholds and show that limited candidate coverage coexists with selection headroom. Third, a controlled realization study with SFT-Qwen3-VL-8B shows that decision-level gains can be attenuated, amplified, or reversed. Change decomposition reveals that realization can remove incorrect assertions while losing correct findings, so target fidelity and reference accuracy need not improve together. Finding gains also do not consistently improve reference-based report quality. These results motivate separate evaluation of decision rules, candidate constraints, and realized reports. --- ### Deeply unrolled alternating projections for phase retrieval Authors: Jiayi Yao, Vasileios Charisopoulos, Rebecca Willett Published: 2026-10-12 Categories: stat.ML, cs.LG, eess.SP arXiv: https://arxiv.org/abs/2610.17316v1 Deep unrolling methods for inverse problems augment traditional reconstruction algorithms with learned priors to improve their performance. These methods have been developed under the implicit assumption that the geometry of the measurement operator does not change between training and deployment; when this is no longer the case, the quality of obtained reconstructions can degrade significantly. In this paper, we argue that this is not an inherent limitation of the deep unrolling paradigm and can be mitigated by a careful choice of the underlying iterative algorithm. We propose a deep unrolling framework for the phase retrieval problem that augments the alternating projections method with a learned denoising step. Our method obtains high-quality reconstructions without the need for retraining in settings where conventional model-based alternatives struggle, such as when the dynamic range of the measurement operator changes significantly at test time. --- ### Joint Embedding with Dynamic Integration network (JEDI-net) Authors: Rishav Mukherjee, Jeffrey Ahearn Thompson Published: 2026-10-12 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.17314v1 Deep learning has become the dominant form of machine learning due in part, to its ability to automatically engineer complex meta features from data. However, even deep learning features can perform erratically because of unobserved latent factors. incorporating latent factor information explicitly, can improve performance by letting the model alter its behavior based on such inferred factors. Because neural networks often capture such complexity inherently, external clustering of the original feature space offers limited benefit. clustering observations by feature importance profiles, rather than raw features, offers a principled way to uncover latent structure, since observations with similar importance patterns may share predictive dynamics. In a prior work, Feature Oriented Representation with Clustering and Explanation (FORCE) we showed that this approach measurably improved neural network performance. In this article, we present JEDI-net(Joint Embedding with Dynamic Integration Network) a unified architecture that periodically clusters SHAP values during optimization to identify latent subgroups with similar feature importance patterns, embed their identities directly into the network, allowing predictions to adapt to each observations predictive structure. --- ### A Geometrical Approach to Constructing Neural Networks for Perfect Training-set Classification Authors: Akos Hajnal Published: 2026-10-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.17312v1 This paper proposes a method for constructing a neural network that achieves perfect classification of all samples in a given training set, without taking regularization into account. The network is constructed on-demand, with its layer sizes and neuron parameters determined through a geometrical analysis of the input data, in which separating hyperplanes are created and mapped to neurons with step activation functions. The proposed architecture consists of two hidden layers with distinct roles: inter-class separation and transformation of the data into a linearly separable representation. Inter-class separation requires every bi-chromatic pair of samples belonging to different classes to be separated by at least one hyperplane. We show that when this separation is achieved through a hierarchical partitioning of the data, the leaf nodes of the oblique decision tree, obtained as a byproduct, directly define the neurons of the linear separability layer, whose size is only one neuron greater than that of the inter-class separation layer. Experiments on the MNIST dataset demonstrate that the proposed method achieves perfect training-set classification, and compact models. The direct correspondence between the decision tree and network neurons enhances interpretability and explainability, while the construction procedure offers opportunities for parallel implementation and improved scalability. --- ### Beyond Successful Play: Diagnosing Opponent Modeling in Large Language Models Authors: Hanbo Xie, Yue Zhao, Robert C. Wilson Published: 2026-10-12 Categories: cs.AI, q-bio.NC arXiv: https://arxiv.org/abs/2610.17310v1 Language-model agents are expected to adapt to others whose behavior changes through interaction. Yet adaptation may rely on learned behavioral patterns rather than theory of mind (ToM): the ability to infer others' mental states, including beliefs and intentions. We introduce a benchmark and diagnostic framework for repeated hide-and-seek against algorithmic opponents with explicitly defined recursive belief updates. Their ground-truth beliefs and action probabilities let us distinguish adaptive play, action prediction, and belief tracking through live interaction, fixed-history evaluation, and controlled information interventions. With structured elicitation and behavioral supervised fine-tuning (SFT), we find improved play in several tested settings, but diagnostics reveal limitations in opponent prediction and belief tracking. We test whether supervising opponent action probabilities can address this predictive deficit in Qwen2.5-7B-Instruct. Predictions improve when the model is told the opponent's type and parameter settings, but become less accurate when it must infer the opponent from history without this information. Training on examples that also omit these details reduces the gap, although improvements vary across opponents. Is this limitation specific to smaller open-weight models, or does it also appear in a frontier model? GPT-5.4 also benefits from correct opponent beliefs: supplying them improves its predictions and choices, whereas deeper explicit belief reports and self-generated memory do not consistently improve forecasting from interaction history. This contrast suggests that using useful belief information is easier than inferring it autonomously, even for a frontier model. Together, our findings distinguish improved play and action prediction from reliable belief tracking, providing a framework for evaluating mentalizing and testing targeted improvements. --- ### StartLux-Decision: AutoThink Decision Models with Reinforcement Learning for Calibrated Deliberative Decisions Authors: Xialie Zhuang, Zunhai Su, Jia Pan, Ngai Wong, Guanhua Chen, Chuan-Wei Kuo Published: 2026-10-12 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2610.17309v1 We introduce StartLux-Decision, decision models from 0.8B to 27B parameters that combine efficient single-pass prediction with adaptive, confidence-guided reasoning. The Instant models use bidirectional attention in full-attention layers to improve decision accuracy while keeping single-pass inference. The AutoThink models invoke explicit reasoning for uncertain decisions and answer confident cases directly. A three-stage training pipeline establishes shared decision capabilities, specializes the two variants, and equips AutoThink with reasoning through reasoning supervision and reinforcement learning. We introduce Reinforcement Learning for Calibrated Deliberative Decisions (RLCD$^2$), which uses a frozen model and proper scoring rules to reward improvements in decision probability quality and applies a soft penalty to overlong reasoning traces. RLCD$^2$ raises the share of reasoning traces that terminate within the generation limit by up to 48 percentage points and cuts average reasoning length by up to 65%, while largely preserving decision accuracy. On the public subset of Decision Index 0.3, the Instant models outperform the strongest evaluated comparable-scale open-weight decision models by 7.4-16.9 points, and the 27B AutoThink model reaches 73.4. We also introduce DecisionPivot, a programmatically verifiable benchmark of computational decisions built from contrast pairs that differ in a single answer-changing detail. On DecisionPivot, AutoThink outperforms its Instant counterparts by 11.5-18.4 points in pair accuracy and leads among evaluated systems. The models run on vLLM, llama.cpp and MLX, with quantized variants for lower memory use. --- ### Calibrating LLM Explanations to Human Decisions with Reinforcement Learning Authors: Dong Shu, Ziyang Guo, Negar Kamali, Matthew Groh, Jessica Hullman Published: 2026-10-12 Categories: cs.HC, cs.LG arXiv: https://arxiv.org/abs/2610.17306v1 Explanations of LLM outputs are considered an important way to make model behavior legible, helping human users make good decisions on downstream tasks. However, default training approaches for improving explanations target model task performance or human preference rather than human decision quality. To bridge this gap, we introduce \textbf{HD-RL}, a reinforcement learning framework for optimizing LLM explanations for human decision making. Our approach calibrates a human decision simulator on observed human decisions, applying a proxy reward model to optimize the LLM to generate explanations that help people to make good decisions. We apply this framework to AI-generated text detection. In our initial data collection phase, we observed that while LLMs possess strong autonomous detection capabilities, the explanations they generate for users yield near-random human accuracy (51.3\%). By applying the HD-RL framework to the open-source Qwen 3.6 model, we generate optimized explanations that improve human performance, achieving a GLMM-estimated human accuracy of 63.7\% in a randomized between-subjects experiment with repeated measures and outperforming RLVR, RLAIF, and other baselines by over 8\%. --- ### Reliable Text-to-SQL in Resource-Constrained Settings with Small LLMs via Iterative Retry Workflows Authors: Bilel Abderrahmane Benziane, Xavier Schepler Published: 2026-10-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.17305v1 Large Language Models (LLMs) have recently improved Text-to-SQL generation, but their computational cost can hinder deployment in resource-constrained settings. This paper evaluates the Text-to-SQL capabilities of small and medium open-source LLMs (1B-8B parameters) under a controlled inference budget, focusing on how model specialization and prompt formulation affect performance. Using the Spider benchmark, we compare multiple prompt representations and assess the accuracy of generated queries. Our results show that SQL-specialized models are consistently more reliable than general-purpose and chat-oriented models at small scales, and that performance can vary substantially depending on the prompt used. To reduce this variability without resorting to larger models, we introduce three lightweight inference workflows that automatically retry with alternative prompts and/or models when failures occur, including an optional syntax-correction step. These workflows significantly improve end-to-end success rates, with a trade-off in additional inference calls. These results demonstrate a practical path to stronger Text-to-SQL performance with small LLMs, by trading modest additional inference cost for higher reliability. --- ### The Agent Knew: Internal States Forecast Unauthorized Actions and Stop Them, and the Lies That Follow Authors: Arya Fayyazi, Mehdi Kamal, Massoud Pedram Published: 2026-10-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.17301v1 Language-model agents sometimes act beyond their authorization and then misreport what they did. On CAPE-Bench, matched agent tasks in which one fact decides whether an action is authorized, frontier open-weight agents do both, and one behavior marks the lie: retroactive permission laundering, acting and then asking permission as if the action were pending, precedes a false report in 70% of 1081 fresh informed violations, against 8% otherwise (preregistered odds ratio 7.0); frontier agents on tau^2-bench instead fabricate the authorization before violating. A linear readout of the agent's residual stream forecasts the violation before the action (AUROC 0.94) and the false report before the report, and beats chain-of-thought monitors when the agent is pressured to hide its reasoning. Gating every proposed action on this forecast cuts violations over whole episodes in four model families, and sending repeated flags to an approver keeps authorized work (Gemma-4: violations 0.70 -> 0.09, completion 1.00; a model approver that escalates unclear cases keeps this gain with a person seeing 25% of asks), at about 10-8 of the agent's compute and 109 times less than a chain-of-thought monitor. On AgentDojo, an external prompt-injection benchmark, the same readout calibrated on 29 tasks, with the steering unchanged, cuts attack success on unseen tasks in two families (Gemma-4 11.7% -> 5.7%, gpt-oss 28.5% -> 17.5%) while keeping benign utility (Gemma-4 0.637 vs 0.637; gpt-oss 0.667 vs 0.681). Preventing the violation is also the most reliable way to prevent the lie (misreported violations 0.10 -> 0.01 pooled over three families, preregistered), whereas lie-specific fixes after a violation are weak. All tests are preregistered and hash-locked; code, data and the full record, including tests that did not pass, are at https://github.com/AryaFayyazi/Honesty. --- ### Towards Resilience: Slice-Driven Orchestration of Mobile IoMT in 6G-Edge-Continuum Authors: Muhammad Zeeshan, Hafiz Faheem Shahid, Erkki Harjula Published: 2026-10-12 Categories: cs.AI, cs.DC, cs.NI arXiv: https://arxiv.org/abs/2610.17296v1 Emerging healthcare services, such as real-time diagnostics, remote health monitoring and computer-assisted surgery, require stringent Quality of Service (QoS) guarantees while operating under limited and heterogeneous edge resources. Existing Internet of Medical Things (IoMT) orchestration methods primarily focus on communication metrics such as latency and bandwidth, while overlooking edge resource constraints and dynamic adaptation to workload and user mobility. This paper presents a novel resource-slicing-based adaptive orchestration framework that integrates 5G network slicing (NS), resource-aware orchestration, and mobility-aware task offloading into a single adaptive system. IoMT services are assigned to distinct 5G network slices while jointly considering CPU capacity, memory availability and amount of storage, enabling more efficient service placement and execution. In addition, the system supports user mobility and dynamic task offloading to maintain service continuity under changing network conditions. SimPy-based simulation demonstrates that the proposed method enhances service deployment efficiency, reduces request blocking, and improves user acceptance while maintaining reliable performance across diverse IoMT scenarios. --- ### PhysCodeGym: Benchmarking Coding Agents for Physically Verifiable 4D Reconstruction Authors: Shuai Shao, Jinchen He, Cunxin Fan, Zihan Guo, Shijian Wang, Qihan Ren, Kangning Zhang, Zunnan Xu, Haoyuan Li, Hao Wang, Jianghao Lin, Weiwen Liu et al. Published: 2026-10-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.17288v1 Building physical simulations from video requires coding agents to translate observations into executable models and refine them through tool use. We introduce PhysCodeGym, a benchmark for physically verifiable 4D reconstruction with $156$ tasks covering rigid-body, liquid, deformable, and wind-driven motion. Agents autonomously inspect videos, write and run Blender programs, and revise their scenes using simulation feedback. Six metrics combine rule-based measurements with rubric-based judgments to assess visual and physical reconstruction quality. Program inspection, scene measurements, and counterfactual interventions test physical consistency under original and modified conditions. Experiments with frontier coding agents reveal a tradeoff between artifact quality and completion across reasoning-effort settings, while harness comparisons and agent traces link verification behavior with reconstruction performance. Case studies show that matching visible objects and events can coexist with physical defects. Counterfactual tests further expose latent contact and support failures in reconstructions that pass ordinary physical checks, highlighting the gap between reproducing observations and building reliable physical models. Code is available at https://github.com/ShaoShuai0605/PhysCodeGym. --- ### Which Geometry on Which Layer? Measured Sign-Spectral Assignment in Mixed-Optimizer Training Authors: Hiroki Naganuma, Laura Gomezjurado, Mahdi Ghaznavi, Ganesh Talluri, Atsushi Nitanda, Seng Pei Liew, Ryuichiro Hataya, Ioannis Mitliagkas Published: 2026-10-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.17285v1 Modern neural-network training uses mixed recipes, assigning AdamW-like or sign-based updates to embedding and output layers and spectral updates to hidden matrices. These assignments are usually fixed by layer type, without a clear criterion for selecting the appropriate geometry. We turn sign-versus-spectral assignment into a measurable, layerwise decision problem. For ideal memoryless steps, we derive a finite-batch ratio of conservative descent-lemma lower bounds for spectral and sign updates. Its closed form separates signal efficiency from a geometry-dependent global curvature factor. In the positive-signal regime, the same smoothness assumption gives two-sided bounds that determine which step has the larger conditional expected decrease when the ratio crosses explicit noise-dependent thresholds. We then derive a local directional quadratic score from gradient alignments and Hessian-vector products and use it in Generalized-Scion (G-Scion) to control layerwise routing. In a controlled input-rank experiment, including directional curvature matches the measured same-iterate ordering in all seven aggregate settings, whereas the curvature-free proxy selects the opposite geometry. On 31M GPT-2, the output score routes the output layer from spectral warmup to sign, and G-Scion improves validation loss over fixed Scion in memoryless and matched-momentum comparisons. ViT-B/16 results further show that a spectral edge assignment can outperform fixed Scion outside language modelling. These results suggest that optimizer geometry need not be hard-coded by layer type and are a first step toward understanding how it should be assigned. --- ### The Surprising Expressivity of a Single Neuron with Autoregressive Chain-of-Thought Authors: Roey Magen, Nirmit Joshi, Gal Vardi Published: 2026-10-12 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2610.17283v1 The success of autoregressive language models trained with Chain-of-Thought~(CoT) supervision raises a fundamental question: How simple can a next-token predictor be while still enabling the efficient simulation of general computation through its autoregressively generated CoT? Surprisingly, we show that a single neuron suffices. For a broad family of activations, including threshold and ReLU, a single autoregressive neuron can simulate any feedforward circuit with the same activation. Specifically, a size-$s$ circuit on $n$ inputs can be simulated by a neuron of dimension $O(ns+s^2)$ using $O(s^2)$ generation steps, with both bounds independent of circuit depth and tight under natural assumptions. For threshold activations, this improves upon the simulation of Joshi et al. (COLT 2025), whose bounds scale exponentially with circuit depth. Consequently, autoregressive threshold neurons can simulate polynomial-time Turing machines, while remaining efficiently learnable from CoT supervision. Our main expressivity result relies on a novel connection to Sidon sets from additive combinatorics. As an experimental illustration, we efficiently train a single autoregressive ReLU neuron to mimic a neural network teacher with nontrivial test accuracy on CIFAR-10. --- ### Colored Graph Signal Diffusion Models Authors: Yiğit Berkay Uslu, Samar Hadou, Shirin Saeedi Bidokhti, Alejandro Ribeiro Published: 2026-10-12 Categories: eess.SP, cs.LG arXiv: https://arxiv.org/abs/2610.17282v1 Standard diffusion processes with isotropic noise corruption are not spectrally neutral. They inherit a coarse-to-fine generation hierarchy from the nonuniform data spectrum, because each frequency band loses signal-to-noise ratio (SNR) at its own rate. For signals on a graph, the relevant spectrum is that of the graph shift operator (GSO). A natural construction, therefore, builds both the diffusion dynamics and the denoiser from graph filters of the GSO, and any such design also takes a position on this hierarchy. We expose this hierarchy as a tunable axis through a family of colored score-based diffusions. Fixing the terminal prior to a Gaussian colored by the GSO couples the drift and diffusion through a positive spectral rate, which acts as a clock for each graph-frequency band. The clock sets when a band loses and recovers information, and the forward processes of standard and certain graph-aware diffusions appear as members of this family. A GSO-valued EDM preconditioning splits the denoiser into an analytic Wiener head that carries the Gaussian second-order structure and a graph neural network (GNN) that learns the remaining non-Gaussian dependencies. Numerical experiments show that colored diffusions reach a given generation quality in far fewer sampling steps than standard diffusion. --- ### Phase-Conditioned Affordance Fields for SE(3)-Equivariant Visuomotor Policies Authors: Xinzhe Chen, Liqi Huang, Sihua Ren, Haowen Sun, Mingyang Li, Zeyang Liu, Xingyu Chen, Xuguang Lan Published: 2026-10-12 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2610.17281v1 SE(3)-equivariance provides a useful geometric inductive bias for visuomotor policies, encoding that actions covary with rigid transformations of the observation. However, existing SE(3)-equivariant visuomotor policies build this bias on a global equivariance assumption that treats the entire observation as governed by a single rigid transformation, which breaks down in real-world manipulation tasks where the task-relevant region changes across different objects. We address this by learning a phase-conditioned affordance field (PAF) over the observed point cloud, a per-point score that the SE(3)-equivariant policy uses in two complementary ways. Its score-weighted centroid serves as a learned, phase-conditioned anchor that canonicalizes the observation and the action around the active region, replacing the fixed gripper-frame reference, and the score itself is appended as a per-point feature. This introduces a local geometric inductive bias, while preserving the policy's global SE(3) equivariance. We validate on multiple MimicGen tasks under varying spatial randomization, and PAF consistently improves the success rate of the underlying policy. On multi-object real-robot tasks, PAF outperforms baselines and keeps its lead under lighting variations. --- ### Nufo: A Benchmark for Ewe Automatic Speech Recognition Authors: Christ Kekeli Keli, Steve Sanogo, Patrice Sebastiano, Hamad Aldenawi, Ryan Whetten Published: 2026-10-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.17278v1 Automatic speech recognition (ASR) remains challenging for low-resource languages, where the scarcity of transcribed speech limits the development of accurate systems. This challenge is particularly acute for African languages such as Ewe, which has millions of speakers but remains underrepresented in publicly available ASR resources and benchmarks. In this work, we consolidate, normalize, and partition existing Ewe speech resources into a standardized 174-hour Ewe ASR benchmark, the largest to date to our knowledge. We fine-tune and evaluate pretrained speech models, including Whisper and AfriHuBERT, to establish strong baselines on our benchmark. Whisper-medium achieves a word error rate (WER) of 37.98%, while AfriHuBERT achieves 39.70% on the test set. We further provide a qualitative analysis of common recognition errors. We release the benchmark under the name Nufo, derived from the Ewe word for "talk", accompanied by models and evaluation resources, to facilitate future research on Ewe and other underrepresented African languages. --- ### Reasoning for Propaganda Detection via Label-Guided CoT Optimisation Authors: Zeba Afroz, Harsh Vardhan, Md. Shad Akhtar Published: 2026-10-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.17271v1 Propaganda detection systems usually operate as black boxes, lacking explanations. To address this, we hypothesise that persuasive techniques contain definitional characteristics with respect to their social-political setting. We introduce ReCoT, a reasoning-conditioned detection framework that captures definitional cues of persuasive techniques via population-level refinement and performance-guided resampling, without requiring additional explanation annotations. On INDI-PROPspan, ReCoT achieves a macro F1_LCS of 0.364, surpassing baselines and reaching 88% of the SFT upper bound on Avg F1_LCS. Similarly, on PTC, ReCoT reaches 85% of the SFT upper bound on Avg F1_LCS, closing much of this gap while remaining interpretable. Importantly, the analysis of the reasoning pool's convergence and update pattern for ReCoT shows effective refinement of reasoning CoTs. --- ### Measuring Learned Equivariance: An Information Theoretic Approach Authors: Claire Schlesinger, Wolfgang Gatterbauer, Robin Walters Published: 2026-10-12 Categories: cs.LG, cs.AI, cs.IT arXiv: https://arxiv.org/abs/2610.17269v1 Learning symmetries through data augmentation offers an alternative to architectural equivariance, but does not guarantee that a network respects those symmetries. Measuring learned equivariance is especially difficult for intermediate representations, whose group actions are not specified. In a finite discrete setting, we show that equivariance requires representations of original and transformed inputs to determine one another exactly, yielding a test based on normalized mutual information (NMI). For high-dimensional activations, we use centered kernel alignment (CKA) as a scalable test, with an exact guarantee for orthogonal feature transformations. Across architectures and tasks, augmentation usually increases transformation consistency, showing that learned equivariance can be probed directly from representations without recovering the hidden transformation rules that relate them. --- ### RL Post-Training Diffusion Language Models Along Their Own Generation Paths Authors: Vaibhav Singh, Eugene Belilovsky Published: 2026-10-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.17266v1 Diffusion language models are a promising and more efficient alternative to autoregressive models. However, most RL post-training techniques are not easily adapted to these models. One issue is that diffusion language models generate answers through many intermediate states, deciding at each step which masked positions to reveal and which tokens to place in them. Many existing RL methods used in this setting approximate intractable sequence likelihoods or weight every denoising step by the same advantage, without explicitly distinguishing how these intermediate states of the denoising trajectory affect the expected reward. To address this issue of trajectory blindness, we introduce PACT (Potential-Anchored Consistency of Transitions). Motivated by a reward-tilted reference distribution, PACT jointly learns the policy and a scalar potential that scores each intermediate state, anchored by terminal reward. For each sampled denoising transition, a consistency loss matches the policy-to-reference log-probability ratio of revealed tokens to the change in this potential. This formulation requires neither sequence-likelihood estimation nor importance-ratio clipping. On four tasks, PACT improves LLaDA-8B-Instruct by +9.9 points on GSM8K, +12.0 on MATH500, +55.7 on Countdown, and +72.6 on Sudoku, and reaches the best average accuracy across the four tasks reported for this model, +3.7 points over the next best method. Further compared to AGRPO, it reaches that baseline's best accuracy in about half the training compute on GSM8K. --- ### Protocol Choices Matter More Than the Aggregation Algorithm: Federated Learning for In-Hospital Mortality Prediction in Care-Unit and Multi-Hospital Federations Authors: Rodrigo Tertulino, Ricardo Almeida, Laércio Alencar Published: 2026-10-12 Categories: cs.LG, cs.CY, cs.DC arXiv: https://arxiv.org/abs/2610.17265v1 Federated learning allows hospitals to train a shared mortality model without pooling their records, but published comparisons of aggregation strategies rarely control the evaluation protocol. This study compared seven strategies (FedAvg, FedProx, SCAFFOLD, FedAdagrad, FedAdam, FedYogi and FedCluster) on two federations built with one pipeline: 12 care units of a hospital in MIMIC-IV and 49 hospitals in eICU-CRD. Each strategy was tuned and selected on validation data by the same rule, and every comparison was repeated across 10 seeds with Friedman and Holm-corrected tests. SCAFFOLD ranked first in both federations (AUC-ROC 0.886 and 0.819) and in 17 of 18 variants, but its margin over the runner-up never exceeded 0.008, and a control sharing its local optimizer attributed most of its margin over FedAvg to drift correction. On the multi-hospital federation, federated training matched centralized training. In the care-unit federation, three protocol choices changed discrimination by more than the choice of strategy did: discharge-coded predictors (+0.038 in AUC-ROC), client-level SMOTE (up to -0.074), and evaluating the last instead of the best validation round (up to -0.084). Platt scaling on validation data repaired the risks distorted by imbalance corrections without loss of discrimination. Studies should therefore fix the protocol before ranking algorithms. --- ### Does a Governed Confidence Score Know When a Text-to-SQL Answer Is Right? An Exploratory Study on BIRD and a Pre-registered Confirmation on Spider Authors: Raghu Venkat, Tricha Anjali Published: 2026-10-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.17256v1 Conversational analytics lets people ask questions of records spread across many systems and get answers in plain language; it is useful only if each answer can be trusted and explained. A production system of this kind attaches a confidence score to every answer it writes over a database and uses it to show the answer, show it with a warning, or withhold it. The score's weights, caps and thresholds were set by design. This paper audits that design. On the 1,534 questions of BIRD dev, answered by GPT-5.1 with a benchmark-adapted production prompt and five samples per question, the designed score separates right from wrong answers weakly (AUROC 0.624, 95% CI 0.595-0.652) and withholds 35.7% of correct answers. Nearly all of its ranking signal comes from agreement among the samples, and most of it is lost where agreement is combined by a minimum with a checklist that drops to zero on any unsupported claim, including claims in commentary. We froze a rule in which agreement with the shown answer is the score and deterministic checks act as vetoes and caps, and pre-registered a test on Spider dev before any Spider answer existed. The primary hypothesis held: AUROC rose from 0.566 to 0.725 (paired difference +0.159, 95% CI +0.097 to +0.221), and correct answers withheld fell from 49.0% to 8.8% with PASS accuracy 95.7%. Under one matching policy the choice of agreement statistic matters little; the gain comes from how agreement enters the score. Whether added checks help depends on how correctness is defined, while they always cost unqualified coverage. A pre-registered empty-result check did not meet its effect-size criterion on Spider. Correctness here means the core answer; labels are model-judged, and a blinded two-person audit, not yet complete, will be reported in a revised version. --- ### Value-Preserving Action Quantization Authors: Max Muchen Sun, Jueun Kwon, Benjamin Riviere, Todd Murphey Published: 2026-10-12 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2610.17252v1 Search-based policy learning, such as Monte Carlo tree search (MCTS), offers the flexibility to trade runtime computation for data efficiency and adaptation to novel environments. For robot learning, however, applying search requires discretizing the continuous action space and associated dynamics, typically through action quantization. While reconstruction-based quantization is sufficient for representing the continuous action space alone, policy learning additionally requires the quantized actions to preserve their effects on future states and values. We show that such requirement is not necessarily captured by action reconstruction error. Instead, we prove that the error in the value function resulting from action quantization is tightly bounded by the reconstruction error of state reachability under the quantized actions. Based on these results, we propose value-preserving action quantization (VAQ), which quantizes actions by preserving state reachability. We further combine VAQ with MCTS (VAQ-MCTS) as a value-preserving, search-based policy learning framework for behavioral cloning. Using a wide range of object pushing tasks as a controlled benchmark, we evaluate VAQ-MCTS against state-of-the-art behavioral cloning methods. VAQ-MCTS matches or exceeds their performance under standard settings, while substantially improving data efficiency and robustness to heterogeneous demonstrations, while enabling zero-shot adaptation to novel environments. Hardware experiments further demonstrate the effectiveness of VAQ-MCTS, completing all 30 real-world object pushing trials with only 10 minutes of demonstration data. --- ### HybridDualPathNet: Cross-Fusion Attention of EfficientNetV2 and Swin Transformer for Brain MRI Classification of Alzheimer's and Parkinson's Disease Authors: Jarpula Nirjala, Rahul Patel Published: 2026-10-12 Categories: cs.CV, cs.LG, cs.SE arXiv: https://arxiv.org/abs/2610.17251v1 Separating Alzheimer's Disease (AD), Parkinson's Disease (PD), and Healthy Controls (HC) using structural MRI remains challenging because disease signatures overlap and model performance can be strongly affected by data partitioning. We present HybridDualPathNet, a hybrid architecture combining EfficientNetV2-S for local features and Swin-Tiny for global context through a Cross-Fusion Attention (CFA) module. We evaluate the model in two experiments. First, on the Kaggle APD-3-Class dataset using an image-level split, the model achieves 98.25% accuracy. Second, on a combined Kaggle and Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset containing 17,859 slices, we use a per-source split with patient-wise separation for ADNI subjects. In this setting, the model achieves 73.37% standard accuracy and a macro AUC of 0.880. Source-stratified evaluation reveals a substantial domain gap, with 91.2% accuracy on Kaggle test images and 59.2% on ADNI test images. Temperature scaling reduces expected calibration error from 0.130 to 0.015, while split-conformal prediction achieves 89.5% coverage. Saliency analyses using Grad-CAM++, Integrated Gradients, and occlusion indicate that model activations concentrate on brain tissue. These results highlight the importance of patient-level separation, cross-dataset evaluation, and uncertainty estimation when assessing MRI classification systems. The findings also show that strong performance on a single dataset does not necessarily translate to reliable generalization across imaging cohorts. --- ### Tight End-to-End Accounting for Differentially Private Synthetic Data Authors: Georgi Ganev, Vadym Doroshenko, Arun Ganesh, Juan Felipe Gomez, Ryan McKenna, Bogdan Kulynych Published: 2026-10-12 Categories: cs.CR, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2610.17249v1 Differentially private (DP) pipelines often combine heterogeneous mechanisms, yet their guarantees are best analyzed using different notions of privacy (e.g., bounded range, zCDP, ADP). When composing them, we have to analyze the guarantees through a reduced common representation that loses accounting precision. This issue is particularly relevant in DP synthetic data generation, where data preprocessing, generation algorithms, and DP-SGD could appear within the same pipeline. We develop novel tools for tight end-to-end accounting of such compositions using privacy loss distributions (PLD), $f$-DP, and Gaussian DP (GDP). In particular, we derive PLD and GDP analyses of bounded-range mechanisms such as the Exponential mechanism. Building on these theoretical results, we introduce AIM-GDP, a GDP-native variant of AIM (a state-of-the-art DP synthetic data mechanism) that enables easy composability with complex pipelines via PLD, attack-aware risk calibration, and tight end-to-end auditing while consistently achieving better utility; and MixCal, an algorithm for calibrating adaptive mixed compositions using PLD accounting. Overall, our tools enable tighter end-to-end accounting and thus less noise at the same privacy level in DP synthetic data pipelines. --- ### LLM-to-Flow Distillation: Teaching Natural Language Goals to Scientific Generators Authors: Riccardo De Santi, Federico Di Gennaro, Angelo Gnazzo, Sophia Tang, Pranam Chatterjee, Fanny Yang, İsmail İlkan Ceylan, Michael M. Bronstein, Andreas Krause Published: 2026-10-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.17246v1 Generative discovery in science requires coupling high-level scientific reasoning with the ability to generate samples respecting the structure of a design space. Yet these capabilities remain largely separated: foundation LLMs encode broad chemical and biological knowledge, while domain-specific flow- and diffusion-based generators capture the priors needed to produce valid sequences and geometries. We study how to align such scientific generators to high-level natural-language discovery goals without requiring an explicit proxy reward, which is often unavailable or poorly captured by learned predictors in experimental sciences. We introduce LLM-to-Flow Distillation (LFD), where a frozen LLM acts as an adaptive teacher for a domain-specific generator. Given a goal such as 'generate peptides with promising anticancer activity', the teacher constructs a curriculum of intermediate sub-goals aware of the flow's current capabilities, and progressively directs them toward the original discovery goal. At each round, the LLM judges sampled candidates under the current objective. These judgments induce preferences that are iteratively distilled into the generator through DPO. This procedure provides dense learning signals even when the initial model places negligible probability on designs satisfying the final goal, enabling adaptation toward poorly covered, out-of-distribution regions. Experiments on therapeutic peptides and small-molecule structure design demonstrate that LFD enables a new form of generative control: aligning arbitrary domain-specific scientific generators to scientific discovery tasks expressed via high-level natural-language goals. --- ### MIRRA: Fast, High-Fidelity Molecular Generation with Chemistry-Informed Discrete Flow Matching Authors: Ge Sun, Juan J. de Pablo Published: 2026-10-12 Categories: cs.LG, physics.chem-ph, physics.comp-ph arXiv: https://arxiv.org/abs/2610.17244v1 Fast, high-fidelity molecular generation requires accurate chemical choices and efficient sampling. Chemical building blocks reduce graph size, but make each node a choice among tens of thousands of related identities. We introduce MIRRA (Molecular Identity Representation, Refresh and Assembly), a discrete flow-matching generator that learns from chemical knowledge and evaluates identity probabilities only when needed, while keeping every identity in its vocabulary available. Chemical features share information across related blocks, and learned identity corrections distinguish them in molecular context. By deciding which positions will refresh before computing their probabilities, the sampler avoids unused predictions while preserving each sampling transition. Against the strongest baselines in each task, MIRRA reduces chemical and graph distribution errors on ZINC250k by 29-31% and 53-60%, respectively, with generation up to 8.6 times faster. Property targeting yields an estimated 7.8-20.8 times more distinct novel hits per second. On a held-out polymer test set, MIRRA achieves 100% periodic validity with known chain topology, versus 57.0% for a polymer variational autoencoder. These results demonstrate fast, high-fidelity generation with the full chemical vocabulary available throughout sampling. --- ### From Conceptual EneMonIE to an Executable Backend: A Modular Architecture for Energy Information Extractionand Grounded Question Answering Authors: Janik Lesage, Khadim Lô, and Jean-Sébastien Dessureault Published: 2026-10-12 Categories: cs.CL, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2610.17243v1 The original EneMonIE proposal describes a Web-based semantic system for continuously monitoring energy trends through targeted information extraction from heterogeneous online media. This article presents EneMonIE-Backend, an implementation-derived redesign that converts that conceptual pipeline into a modular, executable, and application-independent backend. The architecture separates five concerns: data sources, acquisition and normalization, semantic processing, knowledge organization, and persistent storage. It operationalizes configurable connectors for RSS feeds, URL collections, arXiv, social-media JSON files, and open-data CSV files; it also introduces question-driven Web search and scraping. Relevant documents pass through energy categorization, named entity recognition, temporal and event extraction, source sensitive sentiment analysis, and extractive summarization. The resulting semantic representations support entity co-occurrence graphs, cross-document interlinking, cluster-level information fusion, and relational persistence in SQLite. Three grounded question-answering paths are exposed at the backend level: live Web evidence, the stored corpus, and selected configured resources. Answer generation uses a language model when configured and otherwise falls back to deterministic extractive output. Unlike the original proposal, the presented architecture deliberately excludes the user-interface and server-side application layers, allowing the semantic core to be embedded in different applications. A deterministic smoke validation confirms relevance filtering, persistence, clustering, evidence retrieval, and document deletion. The work provides a reproducible architectural basis for future evaluation on larger multilingual energy corpora. --- ### When Left Is Right? Camera-Motion Understanding beyond Screen Authors: Chong Cheng, Ran Zhang, Xinyuan Li, Alan Zhao, Hao Wang, Xi Wang Published: 2026-10-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.17242v1 Can a vision-language model tell left from right? Modern VLMs solve visual puzzles and follow hour-long videos, yet when asked whether the camera moved left or right, most do no better than a coin flip. Adding camera-motion data or geometric representations has been tried, separately, and neither closes the gap. We argue that camera-motion understanding needs two conditions at once: the representation must couple off-screen camera motion with on-screen flow dynamics, and it must be interpreted by the language model rather than trained as a standalone pose or depth estimator. We propose CameraVLM, which pairs a motion-state representation with state-language alignment. Camera tokens capture how the camera moves off screen, flow tokens capture how the subject and background move on screen, and a two-stage training strategy keeps language in the loop so that both are learned together with camera-motion semantics. With only 9B parameters, CameraVLM outperforms all open-source and camera-motion-specific models by a wide margin across three benchmarks and more than 20 baselines, and matches or surpasses GPT-6 Astra as well as human viewers in a 48-participant study. Project page: https://3dagentworld.github.io/CameraVLM/ --- ### IsoVRBench: Video Reward Modeling Without Human Feedback Authors: Shuyue Stella Li, Jacqueline He, Jiahui Chen, Sreya Dutta Roy, Yulia Tsvetkov, Luke Zettlemoyer, Marjan Ghazvininejad, Xiaochuang Han Published: 2026-10-12 Categories: cs.AI, cs.CV arXiv: https://arxiv.org/abs/2610.17234v1 Video reward models are trained and evaluated on human preferences between videos that often differ simultaneously on properties such as prompt alignment, visual fidelity, motion, and generator identity. As a result, aggregate accuracy does not reveal which video properties a reward model can reliably distinguish. We construct preference pairs by controlled interventions that change one property of a generated video while holding the rest fixed. The resulting pairs, by construction, provide preferences for how the videos differ along a specific dimension, without requiring any human annotation. We propose IsoVRBench, a video generation reward modeling benchmark of 8,000 such pairs across eight interventions, and show that state-of-the-art models separate broad quality differences between generators but miss important features such as temporal order. The best reward model reaches only 60.8% on reordered frames against 100% for humans, and rankings on existing benchmarks do not predict this failure. Using the synthetic isolated intervation pairs as training data leads to 1) IsoVRM, a reward model outperforming its counterpart trained with a larger human labeled preference dataset by 3.8 points on VBench-2.0, 2) IsoWan, the video generator post-trained with IsoVRM, outperforming its human-data counterpart in human preferences, and 3) gains that stack when combined with human data. Because intervention pairs are automatically generated rather than collected, the benchmark and training data can be easily extended as generators evolve. --- ### Beyond Sparse Captions: Aligning Slide-Level Text and Patch-Level Vision in Pathology Authors: Daniel Shao, Dongmin Bang, Luca L. Weishaupt, Sophia J. Wagner, Nic G. Reitsam, Ming Y. Lu, Long P. Le, Richard J. Chen, Faisal Mahmood Published: 2026-10-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.17233v2 Contrastive vision-language (VL) pretraining in computational pathology has generally relied on curated image-caption datasets sourced from social media, educational videos, and research publications. These corpora are sparse relative to the diversity of tissue morphology and difficult to scale further, as pathologists do not routinely produce descriptive captions in clinical practice. We propose to instead leverage slide-level pathology reports which can be generated during routine diagnostic workflows in a scalable manner. A key challenge in this weakly-supervised setting is that pathology reports describe macroscopic, diagnostic findings while patch-level visual features describe microscopic findings. We introduce Locked Image Multiple Instance PreTraining (LIMIT), which addresses this gap by freezing a pretrained vision encoder and fine-tuning only the text encoder: report embeddings serve as cross-attention queries over bags of patch features, producing report-conditioned slide representations optimized via InfoNCE. Using LIMIT, we establish CONCH-Z, which aligns the text encoder of CONCH v1.5 to 335k clinical reports. Evaluated across 22 tasks spanning patch-level classification, tumor detection, and slide-level subtyping, CONCH-Z establishes state-of-the-art zero-shot performance over VL encoders trained on curated caption datasets, while simultaneously closing the gap with slide-level foundation models trained with substantially more parameters and compute. The code and model is available at https://github.com/mahmoodlab/LIMIT. --- ### AReA: Adaptive Receptive-Field Attention for Efficient High-Resolution Diffusion Transformers Authors: Javad Rajabi, Koorosh Roohi, David B. Lindell, Babak Taati Published: 2026-10-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.17227v1 Generating images beyond the training resolution of Diffusion Transformers (DiTs) remains challenging, as the number of tokens grows rapidly with resolution, full attention becomes expensive, and outputs often suffer from structural distortions and degraded detail. We identify uniform full attention as the common source of both problems. Attending to all tokens at every step causes quadratic cost and exposes the model to more tokens and relative distances beyond the training range, pushing the model out of distribution. We observe that attention's effective receptive field narrows during denoising, from global in early steps that form structure to local in later steps that refine details. We propose AReA, a training-free attention mechanism whose receptive field evolves from coarse to fine, following the denoising progression. In early steps, AReA applies cross-scale coarse attention over downsampled keys and values, capturing global context, while in later steps it applies local attention within progressively shrinking windows. Without additional parameters or training, experiments show that AReA consistently outperforms state-of-the-art training-free baselines across target resolutions and different models, while also being faster and more efficient. --- ### Solvating machine-learning interatomic potentials for solution-phase chemistry Authors: Anton Z. Ni, Joonho Lee Published: 2026-10-12 Categories: physics.chem-ph, cs.LG arXiv: https://arxiv.org/abs/2610.17226v1 Most machine-learning interatomic potentials (MLIPs) are trained on gas-phase data, which limits their use for chemistry in solution. Here, we introduce AnySolv, a transferable implicit solvation potential that provides solvent-dependent energy and force corrections to existing gas-phase potentials without retraining them. It is trained on 1.4 million solvation energies and forces computed with density functional theory (DFT) and SMD in 36 solvents, spanning charged, open-shell, and transition-state structures. Because solvents are represented by continuous physical descriptors, AnySolv supports 179 solvents, including those absent from training. On external benchmarks, AnySolv reproduces DFT-SMD solvation energies to 2-4 meV mean absolute error at more than three orders of magnitude lower cost, and it matches the accuracy of DFT-SMD against experimental solvation free energies. This enables screening of the mechanisms of 120 nucleophilic aromatic substitution reactions in six phases as well as molecular dynamics simulations that reproduce the experimentally observed solvent-dependent conformational preferences of alanine dipeptide. By providing transferable solvation corrections to existing MLIPs, AnySolv enables scalable simulations of solvent-dependent chemical reactivity and molecular dynamics. --- ### CodeLift: Your Test Suite Is Secretly a Dense SWE Curriculum Authors: Junjielong Xu, Huachao Zhu, Alyssa Wu, Zhichao Hu, Pinjia He Published: 2026-10-12 Categories: cs.LG, cs.SE arXiv: https://arxiv.org/abs/2610.17224v1 The pass-all-test binary reward has become a standard recipe for training software engineering agents, but its sparsity eliminates difference of partially correct patches. The test pass-rate is a natural alternative. However, we find that it is not a reliable indicator of patch quality. A functionality being tested can be covered by either one challenging test or one hundred trivial tests, where the majority might be already satisfied pass-to-pass tests. We introduce CodeLift, a reinforcement learning method that dynamically calibrates pass-rate rewards, turning the test suite into an adaptive curriculum. At each iteration, CodeLift groups tests that kill the same patches and patches that pass the same tests, then gives more weight to test groups that fewer patch groups pass. This reduces the impact of majority simple tests and focuses more on what is still challenging. Within each rollout, CodeLift applies the same scoring rule to repository snapshots, assigning credit to useful actions even when later ones introduce regressions. Experiments on SWE benchmarks show that CodeLift consistently improves pass@1/2/4/8 over binary and pass-rate baselines. Analyses show that CodeLift provides dense, stable learning signals and unlocks the inherent curriculum in the test suite. --- ### Compute-optimal data scaling for neural surrogates via multi-fidelity training Authors: Paul Setinek, Fabian Paischer, Nils Thuerey, Johannes Brandstetter, Felix Koehler Published: 2026-10-12 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.17221v1 Neural surrogates for Partial Differential Equations (PDEs) are usually trained on synthetic data from numerical simulators. As models grow and scaling laws demand larger datasets, the cost of data generation often outweighs the training cost and becomes the bottleneck in the scaling quest. Unlike data in other domains, however, each PDE sample has a tunable cost that depends on its numerical fidelity, with the resulting cost-accuracy trade-off governed by known convergence rates. We exploit this property by formalizing neural surrogate training as a function of both data quantity and fidelity under a fixed data generation compute budget, treating fidelity as a fine-grained discrete spectrum rather than a binary distinction. Building on this, we show that multi-fidelity training enables Pareto-optimal error scaling against data generation compute. By using simulations at lower fidelities as an additional training signal, training on the optimal fidelity mixture matches the accuracy of high-fidelity-only training, with up to $6.3\times$ less data generation compute across our settings. We validate these findings across six PDE problems spanning structured grids and unstructured meshes, two distinct error sources (discretization and iterative-solver error), and four surrogate architectures, totaling over 7,000 training runs. --- ### Density-Matrix Reinforcement Learning Authors: Chiuman Ho Published: 2026-10-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.17214v1 What information does a reinforcement learning policy omit? At each state, a standard policy stores one probability per action. It has no place to record how actions relate to each other, such as which pairs go together and which conflict. We ask when this missing structure matters, and we give exact answers. We store the policy at each state as a density matrix, a positive semidefinite, unit-trace matrix borrowed from quantum information theory. We use it here as a purely classical data structure, computed on ordinary classical hardware. The diagonal holds the usual action probabilities. The off-diagonal entries, called coherences, are new parameters. This gives density-matrix reinforcement learning (DMRL). Coherences change outcomes in two settings. First, suppose a policy is regularized toward a coherent reference policy using matrix relative entropy. The optimum then has coherences that no diagonal reference policy produces, and its action probabilities can depend on the reference policy's coherences. This is relevant to fine-tuning of large language models (LLMs) with a Kullback--Leibler penalty. Second, suppose the agent chooses a unit-vector action and the reward is a quadratic function of that vector. This could arise when an LLM judge scores a weighted consolidation of reasoning paths, or when coupled robotic sensors each respond to a mix of actions. Then some coherent policies earn strictly more expected reward than every classical policy with the same action probabilities, and we give the margin in closed form. In a two-action example, both policies assign probability $0.5$ to each action, yet the classical one earns expected reward $0$ while the coherent one earns $1$, the maximum. Outside these two settings, DMRL matches or transfers the classical results. This is a theory paper. All results are proved, and we report no empirical evaluation. --- ### DexNinja: Learning Robust Dexterous Cutting Policy with a Real-to-Sim-to-Real Data Engine Authors: Haozhe Lou, Runyi Yang, Wanqi Zhong, Caiyun Liu, Yicheng Liu, Wenhao Liu, Wenlong Ma, Jiawei Xia, Kanzhi Wu, Danda Pani Paudel, Luc Van Gool, Hang Zhao et al. Published: 2026-10-12 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2610.17208v1 Cutting a piece of food looks effortless in human hands. For a robot, however, every cut is a high-contact interaction with a deformable, elasto-plastic object whose behavior changes with pose, contact mode, and cutting stage. Collecting real-world data is expensive and wasteful: each trial typically contaminates or damages the food, so obtaining scalable real world data for dexterous cutting is expensive and difficult. Simulation is an appealing alternative, but a large sim-to-real gap exists in both physics and perception. This gap is especially severe for topology-changing interactions like cutting, where small errors in contact, friction, or material and elasticity responses quickly compound. We propose \textsc{DexNinja}, a real2sim2real framework that turns a handful of real demonstrations into a dense and realistic training distribution. \textsc{DexNinja} (i) reconstructs object instances from real captures, (ii) randomizes physically meaningful parameters under category-level constraints, and (iii) produces augmented dexterous manipulation episodes using a custom differentiable simulator that couples robot dynamics, tactile contact, and deformable cutting. We evaluate \textsc{DexNinja} on a dexterous food-slicing task and show that (1) with tens of real demonstrations and hundreds of augmented simulator data, the success rate could reach more than 60\%. (2) the augmented data consistently improves success rates when only using real data with more than 20\% via sim-to-real, and (3) the resulting policies generalize to out-of-distribution objects with varying shapes and sizes. --- ### AutoMARS: Automatic and Scalable Multi-Agent Large Language Model Framework for Supply Chain Risk Assessment Authors: Yinzhu Quan, Zefang Liu, Frederick Benaben, Benoit Montreuil Published: 2026-10-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.17206v1 We propose AutoMARS (Automatic Multi-Agent Risk Assessment), an agentic framework for automatic and scalable comparative risk assessment in supply chain networks. The framework enables end-to-end execution of analytical workflows by automatically planning tasks, coordinating specialized agents, invoking external analytical tools, and synthesizing domain-specific results into integrated risk evaluations. AutoMARS further supports scalable risk comparison across multiple locations by parallelizing independent analytical tasks. The framework adopts a multi-domain, multi-agent, and multi-tool architecture that integrates heterogeneous risk factors from socioeconomic, disaster, environmental, and transportation domains. Through coordinated agent interactions and tool integration, AutoMARS enables structured, systematic, and interpretable comparative analysis to support supply chain risk-aware location evaluation. --- ### Releasing the Inner Jev: A Simple Recipe for Open Decision Models Authors: Jonathan Geuter, Andrew Cheng, David Alvarez-Melis Published: 2026-10-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.17205v1 LLM-based decision-making systems, also called System One models, have recently gained popularity, most notably through Jev (Almeida, 2026). Given a typed input state, a question, and a set of options, they return a probability for each option in a single forward pass, without text generation. We show that existing open instruction-tuned language models can achieve comparable performance \textit{without any additional training}, by reading out answers from letters (A, B, C, etc.) in the model's output logits at the last token position. Furthermore, we show how a simple supervised fine-tuning recipe can improve their performance further. We evaluate four open instruction-tuned language models: Gemma 4 31B, Gemma 4 12B, Qwen3.6-27B, and Qwen3.5-4B. We fine-tune each using LoRA and a decision head initialized from a slice of the language model head. Furthermore, we introduce OpenDecisions, a novel 2,352-question validation dataset designed to reflect the task composition of JevBench (JevBench main- tainers, 2026) and which computes a Capability score based on accuracy and calibration metrics. Without fine-tuning, Gemma 4 31B scores 79.6 on OpenDecisions, compared to Jev's 80.1. After undergoing our fine-tuning recipe, it scores 84.4 on OpenDecisions and 81.5 on JevBench v1.7, outperforming Jev by 4.3 and 4.4 Capability points respectively and setting a new state-of-the-art on OpenDecisions. On a suite of public decision datasets, our models achieve accuracy comparable to Jev, with lower calibration error. Our results show that open language models already possess System One capabilities, and with simple fine-tuning they outperform Jev on a wide range of decision tasks. We release our models, serving code, and OpenDecisions. --- ### Online LLM Personalization from Pairwise Preferences Across Users Authors: Romain Puech, Georgy Salakhutdinov, Dimitris Bertsimas Published: 2026-10-12 Categories: cs.LG, cs.CL, stat.ML arXiv: https://arxiv.org/abs/2610.17203v1 Large language models can answer the same question in different styles, but users' preferred styles are hidden and vary across users and questions. We study inference-time personalization through online selection from a fixed set of prompts, each representing a persona. Users arrive sequentially, each asks a short sequence of questions, and the system displays two responses per question and observes one pairwise choice. We formulate this interaction as a variant of the contextual dueling bandit problem in which the learner starts without preference data, adapts within each session, and exploits information shared across users. The objective is to minimize cumulative strong regret, summing the utility gaps of both displayed responses relative to the user's best response among the available options. We make two contributions. First, we introduce the problem and release a reproducible preference benchmark and dataset built around a tutoring case study, containing educational questions, LLM-generated answers in six teaching styles, and pairwise judgments from LLM-simulated students with hidden preference profiles. We fit Bradley-Terry models to these judgments to obtain reference utilities for regret evaluation. Second, we propose a baseline that learns a mixture prior over users from completed sessions and adapts to each new user within the session. On students and topics never used in development, it removes 44-48% of random pairs' excess regret and achieves over half the performance of a per-user linear oracle fitted in hindsight. We release code, prompts, and the benchmark. --- ### MLAfication: Efficiently Enabling High-Fidelity MLA for Modern LLMs Authors: Zile Wang, Zhide Xie, Tao Ji Published: 2026-10-12 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2610.17202v1 Multi-Head Latent Attention (MLA) compresses the KV cache into a latent representation, reducing inference memory and bandwidth. Existing MHA2MLA/TransMLA methods do not support QKNorm and require costly recovery on modern LLMs, especially MoE. We present MLAfication, a QKNorm-compatible, parameter-efficient extension of MHA2MLA. It combines calibrated KNorm, parameter-efficient distillation, contribution-aware Partial-RoPE, and activation-aware joint KV initialization. Across MHA and GQA models, including QKNorm- and MoE-equipped variants, MLAfication preserves performance under substantial KV-cache compression, surpasses the current SOTA on commonsense and long-context benchmarks, and extends MLA conversion to modern architectures. On Qwen3-30B-A3B, MLAfication delivers up to $5.35\times$ the serving throughput of BF16 GQA and, combined with 4-bit KV quantization, reduces the KV-cache footprint by $94.73\%$. Our code is available at https://github.com/JT-Ushio/MLAfication. --- ### Multics: Generative Multi-Player World Model with Hierarchical Communication Authors: Kaiyi Huang, Wangbo Yu, Yukun Huang, Jiwen Yu, Kunhao Liu, Donglin Yang, Wenbo Hu, Ying Shan, Xihui Liu Published: 2026-10-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.17201v1 Multi-player interactive world models aim to simulate shared environments from multiple players' perspectives, but achieving robust generation while scaling to more players remains challenging. Existing approaches that rely on fully-connected communication (e.g., Solaris) incur quadratic attention costs as the number of players grows, while centralized approaches (e.g., $γ$-World) suffer from interference between unrelated events in a shared global representation. To address these challenges, we present Multics, a multi-player video generation framework with hierarchical communication that structures information exchange across player, group, and global levels. This hierarchy introduces group tokens into self-attention as intermediate group-level representations that aggregate locally relevant player information. These tokens connect to global tokens for cross-group communication, while the hierarchical topology limits direct mixing between unrelated local events. Group-token parameters are shared across group slots, allowing the same communication module to accommodate varying numbers of players without introducing new group-specific parameters. We further propose budget-constrained dynamic grouping based on recent camera trajectories, which adaptively groups relevant players while limiting unnecessary communication. Experiments demonstrate that Multics achieves state-of-the-art performance in 4- and 6-player settings, with improved cross-player consistency, player-specific action and camera controllability, and interference robustness. Moreover, Multics generalizes from 4-player training to 6-, 8-, and 10-player inference without retraining, while reducing self-attention computation compared with fully-connected communication. --- ### Deleting Code Without Losing Knowledge: Regenerative Software for Python Libraries Authors: Thomas Bartz-Beielstein Published: 2026-10-12 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2610.17197v1 In the age of "Software 3.0", when a complete program can be rewritten in minutes by an agent, the traditional approach of relying on code as the sole source of truth becomes questionable. Fowler advocated for a set of seven primitives, which lay the framework for regenerative software, so that programs can be deleted and rebuilt without losing their knowledge. The knowledge lives in machine-readable records in a tracked directory, from which a *regeneration bundle* is built for each unit. The regeneration bundle is a single file with the module's architecture, intent, decisions, public contract, evaluations, and consumers, but no implementation, plus the one dependency module it may import. The open-source package spotregen implements these primitives and provides a graphical user interface. This report presents a first application of Fowler's primitives to the safety-critical forecasting library spotforecast2-safe. During the first experiments, the Claude Code session that orchestrated the study consumed more than 43 million tokens, almost all of them its own history re-sent with every request. This motivated the switch to an architecture that is built on local models. Deterministic checks and the maintainer judged the results. The report contains executable examples for every primitive. Each example runs spotregen against the repository or against a throw-away copy of it. --- ### Welcome to the Age of Agent Ads: Using On-Policy Attacks to Steer Agentic Decisions Authors: Tim R. Davidson, Marija Šakota, Joshua Joseph, Robert West Published: 2026-10-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.17195v1 People increasingly delegate option-ranking tasks (e.g., shopping, job search, travel) to AI agents, which creates incentives to steer agentic decisions via "agent ads." To defend against such steering attacks, people count on models' alignment training and platforms' terms of service, and consequently the most effective existing attacks are designed to trigger off-policy behaviors. Exposing a new attack surface, we introduce on-policy attacks, which steer agentic decisions without pushing individually aligned behaviors off policy. Our example attack consists of two steps: To remain compliant with platforms' terms of service, we first inject a truthful negation about a fictitious concept ("Does not contain blizyester") into a product description. This triggers an agent to search the web ("What is blizyester?"), which surfaces planted websites full of fabricated information associating the fictitious concept with harmful implications ("Blizyester linked to dementia"). Trained to keep users safe from harm, the agent penalizes every option missing the truthful negation. Evaluating our attack across four real-world listing datasets, we find some frontier models exposed, enabling an adversarial actor to penalize competitors without violating existing platform-listing guidelines. We discuss the broader challenge of regulating advertising aimed at AI agents and provide recommendations to model developers and platform providers. ---