# Research Papers — 2026-09 · bundle page 37 of 266 > Full-text markdown of papers #1801–1850 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/37 [← Previous bundle](https://aipod.dev/papers/archive/2026-09/page/36.md) [Next bundle →](https://aipod.dev/papers/archive/2026-09/page/38.md) ### Deep Epistemic Value Functions for Optimistic Exploration Authors: Leander Diaz-Bone, Marco Bagatella, Jonas Hübotter, Andreas Krause Published: 2026-09-28 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.35525v1 Principled exploration in reinforcement learning requires an agent to quantify its epistemic uncertainty and act to resolve it. Uncertainty over the value function provides a natural signal for exploration, yet existing deep approximations remain brittle and perform inconsistently. The central challenge is therefore to scale these ideas robustly. We conduct a systematic empirical study of how epistemic uncertainty is represented, propagated, and optimized in deep epistemic value functions, and uncover distinct failure modes along each of these axes. These findings motivate DEVOTE, a model-free reinforcement learning algorithm that controls how uncertainty generalizes beyond observed data, stabilizes its temporal propagation, and preserves adaptation to the resulting non-stationary exploration objective. Across reward-free exploration and challenging continuous-control tasks, DEVOTE reaches novel states more effectively and achieves higher task return than strong model-free and model-based exploration baselines. These results provide evidence that deep epistemic value functions are a promising path toward scalable, principled exploration. --- ### Beyond Token Scale: Chunk-Level Sparse Autoencoders for Reliable Semantic Feature Discovery Authors: Xu Wang, Yifan Yang, TingHao YU, Difan Zou Published: 2026-09-28 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.35521v1 Sparse autoencoders (SAEs) expose features that help us understand and steer language models, but faithful reconstruction does not guarantee informative concepts. Token-level objectives reward lexical and formatting details alongside semantic content, all competing for a limited sparse budget. We introduce a family of chunk-level SAEs that encode mean-pooled activations over chunks, each a contiguous span of tokens: Mean-Chunk reconstructs the observed chunk, Cross-Chunk predicts an independently processed neighbor, and Joint-Chunk combines both targets. These designs separate the effect of a larger observation unit from that of predicting information shared across passages. With matched training data, chunk-level SAEs remain powerful interpretability tools while learning reliable semantic features that capture high-level concepts and respond selectively to relevant content. Their strengths are complementary: Mean-Chunk improves high-level feature discovery, reasoning detection beyond surface cues, and steering; Cross-Chunk leads document retrieval and classification transfer while producing selective, persistent features. Changing what an SAE sees and predicts yields reliable semantic features for more meaningful tasks. We demonstrate their practical value through gains across downstream tasks such as retrieval, reasoning detection, and steering. --- ### Reward-Aligned Reweighting for On-Policy Distillation Authors: Haofeng Xu, Junwei Su, Lansong Diao, Wenchao Zhou, Chuan Wu Published: 2026-09-28 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.35517v1 On-policy distillation (OPD) trains a student language model with dense feedback from a stronger teacher on student-generated trajectories. Yet standard OPD weights token-level distillation terms uniformly, implicitly treating local teacher preference as a proxy for correction utility. A decision's task value, however, depends on how the student completes the subsequent reasoning. This mismatch can cause imitation to suppress viable student strategies or reinforce paths the student cannot reliably execute. Verified trajectory outcomes provide complementary evidence about continuation quality, but do not directly identify the utility of individual decisions. We introduce Reward-Aligned Reweighting for On-Policy Distillation (R$^{2}$-OPD), which uses outcome agreement and the magnitude of teacher--student disagreement to continuously reallocate teacher supervision. It gives reward-aligned corrections greater relative influence while retaining dense feedback, moving beyond uniform imitation and hard filtering. Our analysis formalizes the mismatch between local teacher preference and student continuation value and establishes sufficient conditions for reallocation to improve first-order task progress over uniform OPD. Across seven mathematical reasoning benchmarks, R$^{2}$-OPD achieves the highest average accuracy among the compared training methods in both cross-size and same-size distillation. It outperforms standard OPD on all seven benchmarks, with average gains of 3.5 and 2.4 percentage points for 1.7B and 4B students, respectively. An extension to code generation yields an average gain of 1.6 percentage points over standard OPD. These results highlight outcome-guided supervision allocation as an effective way to translate dense teacher feedback into stronger student performance across model scales and task domains. --- ### MechBench: Can AI Scientific Agents Discover Mechanisms Beyond Phenomenal Laws? Authors: Zihan Yu, Jiadong Zhang, Jialin Cheng, Jingtao Ding, Yong Li Published: 2026-09-28 Categories: cs.AI, cs.LG, cs.SC arXiv: https://arxiv.org/abs/2609.35515v1 Scientific discovery requires not only recovering mathematical laws that describe observable behavior, but also identifying the mechanisms that generate them. Existing benchmarks for symbolic regression and scientific agents primarily evaluate phenomenal-law recovery, leaving mechanism discovery largely untested. We introduce MechBench, a benchmark that explicitly separates these two capabilities. Each task is defined by a mechanistic model, a structured set of scientifically meaningful relations whose joint consequences entail an observable phenomenal law, while agents receive only observational data and scientific context. We evaluate mechanism recovery through mechanism probes, which query internal scientific consequences that cannot be inferred from the phenomenal law alone. To reduce reliance on memorized textbook mechanisms, we construct unfamiliar variants through controlled, scientifically interpretable mutations of canonical mechanisms, and screen for mechanistic indistinguishability to exclude ambiguous instances admitting comparable competing mechanisms. Experiments across representative scientific agents reveal a substantial phenomenal--mechanism recovery gap: for Codex with GPT-5.6-sol, phenomenal-law accuracy reaches 35.00% on the Core-set while mechanism accuracy is only 13.75%, with mechanism recovery failing in 64.29% of cases where the phenomenal law is correctly recovered. The gap widens as mechanisms become increasingly mutated, and even providing the correct phenomenal law leaves mechanism recovery below 50%. These results reveal a substantial generalization gap in mechanistic reasoning and establish mechanism discovery as a distinct challenge beyond recovering observable scientific laws. --- ### One Proposal for Every Margin: Zero-Shot Amortized Sequential Importance Sampling for Binary Matrices Authors: Ruishuo Chen, Weijia Li, Xun Wang, Yu Chen, Leheng Cai, Longbo Huang Published: 2026-09-28 Categories: cs.LG, stat.CO arXiv: https://arxiv.org/abs/2609.35514v1 In ecology, psychometrics, and the analysis of social and financial networks, binary matrices are often analyzed conditional on their observed row and column sums, which restricts the problem to a finite sample space of matrices with the same margins. Two fundamental problems are to count this space and to sample uniformly from it. Sequential importance sampling (SIS) addresses both with independent weighted samples and an unbiased count estimator, but its efficiency depends critically on the proposal distribution. Existing proposals are analytically designed, and their accuracy can vary substantially with the margins. We show that the ideal SIS proposal, under which every weight equals the count and the variance vanishes, is exactly the policy of a generative flow network (GFlowNet) with unit reward on every matrix that has the given margins. We therefore propose MarginFlow, a framework that turns the design of the proposal into a learning problem and amortizes it across margins by exploiting their self-similarity. Every partial matrix is itself an instance with reduced margins, so one set transformer that reads the remaining margins serves every margin. We train MarginFlow on a pool of 1904 margins and evaluate it zero-shot on 1190 held-out margins, synthetic and real, from $3\times3$ to $870\times6$. On 1187 of the 1190 margins it matches or beats the best of 31 analytically designed configurations, chosen post hoc for each margin, and its median effective sample fraction is 99.8%. On the 56 margins where that best loses more than one nat of effective sample size, MarginFlow wins every one and raises the median effective sample fraction from 10.3% to 94.1%. --- ### Improving Generative Model Self-Training with Geometrically Modified Outputs Authors: Patrick Batsell, Thomas Walker, Richard Baraniuk Published: 2026-09-28 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.35512v1 Self-training generative models - the continued improvement of a model using its own outputs - is becoming increasingly important as high-quality training data becomes scarce. However, naively finetuning on model-generated samples leads to degradation through model collapse and the model autophagy disorder. Negative-guidance self-training methods turn this degradation into a useful signal, using a model finetuned on its own outputs to guide the original model toward improved generation. Existing methods, however, take the negative signal in standard model outputs as given. We instead ask whether this signal can be explicitly strengthened. We introduce Geometrically Modified Outputs (GMOs), which reweight the singular values of the generator's input-output Jacobian to increase the influence of its leading singular directions. This geometric modification amplifies the mode-seeking behavior and distortions of standard outputs, providing a stronger and more targeted negative signal for self-training. Across a range of one-step generative models, GMOs consistently improve the performance of negative-guidance methods, including Neon and SIMS, compared with using standard model outputs. --- ### ReVA: A Scene-Centric Dataset Beyond Repetition for Remote Sensing Video Question Answering Authors: Zhen Yao, Likai Wang, Yuming Yang, Zhihao Zheng, Bo Lang, Qiuyu Tang, Jialu Sheng, Jingqi Xu, Yuehai Yang, Jumal Barker, Xiaowen Ying, Mooi Choo Chuah Published: 2026-09-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.35507v1 Multimodal Large Language Models (MLLMs) have demonstrated remarkable advances in remote sensing. However, existing remote sensing multimodal reasoning benchmarks exhibit two critical limitations: they rely on (i) template-driven questions, which causes repetitive questions; and (ii) static images that fail to capture the inherent temporal nature of drone/UAV videos. This leaves systematic evaluation of remote sensing video reasoning largely unexplored. To address this gap, we introduce ReVA, a new dataset for remote sensing video question answering, designed to assess spatiotemporal, scene-centric, and reasoning-oriented capabilities of MLLMs. ReVA comprises 2,438 drone videos spanning 18 cities worldwide (580K frames) and 22K high-quality question-answer pairs across 11 challenging QA tasks. We develop a semi-automatic annotation pipeline that leverages Text LLMs and MLLMs for question-answer generation with human verification. We evaluate 23 proprietary and open-source Video LLMs on ReVA, exposing fundamental limitations of current models. These findings position ReVA as a critical benchmark toward better remote sensing video understanding and temporal reasoning capabilities for real-world deployments. Our code and dataset are available at: https://github.com/zyaocoder/ReVA --- ### An RL View of OPD: Least Square Policy Distillation for Sample-Efficient LLM Reasoning Authors: Shangzhe Li, Yuxiao Yang, Tianrun Yu, Kaixiang Zhao, Xiaoyun Wang, Taylor W. Killian, Weitong Zhang Published: 2026-09-28 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.35505v1 We study on-policy distillation (OPD) through the lens of reinforcement learning, establishing a connection between the reverse-KL objective in OPD and KL-regularized policy optimization. Building on this connection, we introduce Least-Square Policy Distillation (LSPD), an RL-inspired framework that brings optimistic exploration and off-policy data reuse from value-based RL into policy distillation. LSPD preserves policy diversity through exploration while improving rollout efficiency by repeatedly learning from previously collected trajectories. Our theoretical analysis connects LSPD to optimistic value-based learning and shows that its idealized formulation achieves a sharp $\tilde{\mathcal O}(\log K)$ regret bound under online exploration. Empirically, LSPD consistently outperforms existing distillation baselines across six mathematical reasoning benchmarks and diverse teacher-student settings, with average gains of +1.59 points in Avg@16. Remarkably, through Pass@k evaluations up to k=64, we found that LSPD better preserves policy diversity by achieving stronger performance as k grows. Its fully off-policy variant achieves comparable performance to vanilla OPD using only the first 25% of rollout batches. Together, these results provide an RL perspective on OPD that offers both a principled interpretation and a practical route toward more effective and rollout-efficient language model distillation. --- ### SolveEdit: Benchmarking Visual Problem Solving in Generative Models Authors: Wenjie Shu, Yexin Liu, Harold Haodong Chen, Xuerui Qiu, Zehan Wang, Yidi Zhang, Yizhan Chen, Zunwei Wang, Minghao Liu, Qi Chen, Harry Yang, Xiaogang Xu Published: 2026-09-28 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.35504v1 Machine intelligence is often evaluated through abstract reasoning problems, yet many real-world problems are visual, such as arranging objects, repairing layouts, or tracing routes. Solving these problems requires understanding a scene, inferring what must change to achieve a goal, and realizing that change without disturbing unrelated content. However, existing benchmarks mainly evaluate perception, generation, or explicitly specified transformations, leaving goal-driven visual problem solving underexplored. To bridge this gap, we introduce SolveEpIT, a benchmark for visual problem solving through scene transformation. Given an image and a goal, a model must infer a valid transformation from the request, the scene, or a visually expressed rule, then execute it while preserving unrelated content. SoLvEEDrr contains 2,728 cases. Atomic transition contracts specify required and protected conditions, enabling SoLvEScoRE to measure completion and unintended changes without a single reference output. The strongest evaluated model achieves only57.0% SolvEScore. We further introduce SolveEdiT-PLAN, a two-stage visual planner that instantiates the transition before generation. Under matched single-generation evaluation, it improves SoLvEScoRE by 9.1 points on average across three tested generators, including a gain from 57.0% to 71.6% for GPT-Image-2, without modifying the editor. --- ### Structured Latent Modeling for Supervised Multimodal Information Decomposition Authors: Wanting Huang, Sanvesh Srivastava, Weiran Wang Published: 2026-09-28 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.35502v1 Multimodal prediction relies on diverse forms of evidence: information repeated across modalities, cues specific to a single source, and complex cross-modal dependencies that emerge only when inputs are considered together. While recent methods promote richer interactions, they lack a principled way to isolate these target-relative contributions within learned continuous representations. We introduce a framework that applies contrastive or masked objectives at intermediate layers, coupled with source-wise invertible normalizing flows and a supervised, low-rank latent variable model. This architecture explicitly factorizes the joint distribution into shared task-relevant variation, modality-specific predictive variation, and task-irrelevant dependence. Drawing connections to prior multimodal learning assumptions, our approach evaluates how modalities independently and jointly contribute to the target. Ultimately, this framework unites intermediate representation learning with structured likelihood-based guidance, offering a practical latent-variable lens for characterizing continuous multimodal interactions. Empirically, we demonstrate the effectiveness of our approach across diverse multimodal benchmarks, showing robust improvements in predictive performance. --- ### SRHarness: A Harness for Agentic Symbolic Regression Authors: Zihan Yu, Shixuan Zhou, Hao Huang, Jingtao Ding, Yong Li Published: 2026-09-28 Categories: cs.AI, cs.LG, cs.SC arXiv: https://arxiv.org/abs/2609.35501v1 Recent agentic symbolic regression approaches increasingly rely on large language models to analyze data, select scientific operations, and refine hypotheses over long search trajectories. In such systems, performance depends not only on the underlying model and search strategy, but also on the runtime infrastructure that supports scientific search. We introduce SRHarness, a domain-specific harness for agentic symbolic regression built around three mechanisms: composable scientific actions that provide a common interface over raw, transformed, and candidate-derived quantities; persistent scientific state that retains evaluated hypotheses and exposes compact model-facing views; and trajectory lifecycle management that coordinates continuation, branching, restart, and termination. On LLM-SRBench, SRHarness consistently improves both numerical generalization and symbolic recovery under matched LLM backbones. With DeepSeek-v4-flash-0731, it achieves 93.69% symbolic accuracy on LSR-Transform, compared with 62.16% for SR-Scientist, and retains 72.97% accuracy on an anonymized variant that removes scientific descriptions and variable semantics, versus 39.64% for SR-Scientist. Under the same DeepSeek-v4-flash-0731 backbone, SRHarness also substantially outperforms Codex (72.97% vs. 20.72%) and reaches performance comparable to Codex with GPT-5.5, while simply providing Codex with the same scientific tools does not reproduce this advantage. These results show that effective agentic symbolic regression depends not only on models or tools, but also on structured runtime support for organizing scientific actions, accumulated hypotheses, and long-horizon search. --- ### Physics-Guided Conditional Diffusion Model for Rare Event Synthesis and Diagnosis for the Water-Gas Shift Reaction Authors: Md Abrar Rafid Siddique, Bibek Aryal, Qiugang Lu Published: 2026-09-28 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.35499v1 As the world moves towards sustainable energy sources, hydrogen (H2) can be treated as an eco-friendly alternative to fossil fuels due to its high energy density and zero carbon emissions. The water-gas shift (WGS) reaction is a widely used industrial process for hydrogen production by converting carbon monoxide and steam into hydrogen and carbon dioxide. However, occurrences like severe fouling, catalyst deterioration, and thermal runaway can hamper the reaction kinetics/process safety and decrease the yield of H2. These incidents are rare, and gathering process data under such abnormal conditions is challenging. In this work, we propose a physics-guided conditional diffusion model to generate realistic rare-event trajectories for the WGS reaction. The proposed model integrates a conditional denoising diffusion probabilistic model (CDDPM) with governing laws of the reaction to generate physically consistent process trajectories. The conditioning features allow the model to produce high-quality synthetic profiles for rare-event domains that are typically beyond the training regimes. The generated rare-event trajectories then augment the raw dataset for a balanced distribution between normal and abnormal conditions. We further propose a hazard score to assess the risk severity of the operating condition based on the operating trajectory. Deep learning models are trained with the augmented dataset to diagnose the health status of the reaction. Simulation results show that the proposed physics-guided diffusion model outperforms data-driven models in terms of the quality of synthetic data and diagnosis performance for rare events. --- ### Sprout: Building Dynamic Memory While Reasoning for Agentic Video Understanding Authors: Wei Chen, Xuanyu Zheng, Yancheng Long, Haoyang Xu, Kaiyu Jiang, Bin Wen, Tingting Gao, Han Li, Long Chen Published: 2026-09-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.35497v1 Long video understanding relies on video memory to overcome the context limits of multimodal large language models. Existing methods follow a build-then-reasoning pipeline: memory is built offline for the entire video, then reasoned over as a static source. In practice a long video is shared by several questions, and this pipeline is costly at both ends: with few questions, building memory for the whole video costs far more than answering them; with many questions, the memory is never updated, so what is learned while answering questions is lost to the next question. To alleviate these, we introduce Sprout, an agentic framework that builds memory while reasoning: a temporal tree that sprouts detailed nodes as questions are answered. The agent watches the video segment by segment at a low frame rate, stopping when the current question can be answered, remembers each segment as a coarse node of the tree, and revisits key intervals at a higher frame rate to refine the tree with the recovered details. Once a segment is recorded as text, its video input is removed from the context history, while the original video remains reachable through the video tools. The memory tree and prior question--answer records persist across questions, so the memory is online and dynamic: built from the first question onward and updated by every question thereafter. We find that replacing accumulated video inputs with textual memory substantially reduces context usage while maintaining accuracy, with slight improvements in some settings. Across benchmarks on three models, Sprout achieves competitive or improved accuracy relative to representative offline memory methods, with no upfront construction stage and lower context cost per question. --- ### From Scores to Samples: Elastic Forcing for Autoregressive Video Generation Authors: Chi Zhang, Yueyi Liu, Haoyang Shi, Ruichuan An, Haoyu Li, Yuhang Wu, Sen Cui, Miao Liu Published: 2026-09-28 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.35491v2 Few-step autoregressive video generation commonly relies on Distribution Matching Distillation (DMD), requiring a bidirectional diffusion teacher and an online fake-score model. We instead learn the rollout distribution directly from reference videos, eliminating both score models during post-training. Our framework minimizes maximum mean discrepancy (MMD) in frozen self-supervised video representation spaces, using a hybrid Nyström--Monte Carlo estimator to balance approximation bias and sampling variance. Memory-efficient replay and gradient subsampling make this objective practical. Using the same architecture and initialization as Self-Forcing, our 1.3B model improves the VBench Total score from 83.80 to 84.64 while retaining 17 FPS. Removing auxiliary score models also enables 14B post-training on eight H200 GPUs. Beyond distillation, learning from reference videos enables the acquisition of new visual styles, semantic concepts, and spatial priors without a target-specific diffusion teacher. --- ### AHMAD: Adaptive Hybrid Multi-task Vision Learning with Assisted Distillation for Keypoint Detection Authors: Mohammad Mahdi, Nedyalko Prisadnikov, Yuqian Fu, Carmelo Scribano, Danda Pani Paudel, Luc Van Gool Published: 2026-09-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.35490v1 Generalist multitasking vision models aim to unify multiple vision tasks within a single framework, enabling more efficient and versatile learning. However, handling diverse vision tasks -- spanning dense and sparse predictions -- remains challenging due to their inherently varying output structures. In this paper, we propose AHMAD, a simple yet effective framework for generalist multitask learning that integrates different key vision tasks: semantic segmentation, instance segmentation, depth estimation, keypoint detection, and object detection. Our approach incorporates these five tasks into a unified structure: a shared encoder-decoder with several lightweight task-specific projectors. Under the multitask learning paradigm, we observed a complementary performance gain, achieving a state-of-the-art PQ of 53.1 and an mIoU of 66.5 for COCO-val panoptic and semantic segmentation, respectively. Additionally, for top-down keypoint detection, which typically incurs high computational overhead due to multiple forward passes, we introduce a knowledge distillation-based method that enables a single forward pass over the entire image, greatly improving efficiency. Ultimately, our model delivers a lightweight yet effective generalist multitask learning framework, demonstrating strong performance across five vision tasks. --- ### Who Is Left of Whom? Tracing Spatial Evidence and Role Binding in Relative-Position Reasoning Authors: Yingjin Song, Denis Paperno, Albert Gatt Published: 2026-09-28 Categories: cs.CL, cs.CV arXiv: https://arxiv.org/abs/2609.35486v1 High instance-level accuracy can mask inconsistencies in spatial reasoning when objects exchange positions or their roles are reversed in the query. The internal representations supporting relative-position reasoning remain poorly understood. We investigate two complementary components of this process: tracking object locations in the input and representing their query roles. Across three VLMs with visual or textual inputs and their language-model backbones, activation patching reveals a staged progression from early-layer source representations through intermediate-layer query-object representations to late-layer answer states. Targeted interventions further establish causal links along this progression: manipulating source-side representations shifts location information at query-object mentions and ultimately alters relation predictions. Beyond object-location information, we also identify a stable query-side direction associated with the roles of the two objects in the comparison. Steering along directions estimated on synthetic scenes generalizes to natural-image benchmarks, improving accuracy and both forms of paired consistency in most settings without retraining. Our findings reveal complementary components of relational reasoning across visual and textual settings and show how targeted interventions can improve the consistency of models' behavior. --- ### Universal Approximation of Measure-to-Measure Operators by Pushforwards Authors: Takashi Furuya, Nicholas H. Nelsen, Frank Cole Published: 2026-09-28 Categories: cs.LG, math.NA, stat.ML arXiv: https://arxiv.org/abs/2609.35483v1 Many learning tasks map an input distribution to an output distribution. A natural way to model such an operator is to transform each input sample using a continuous function that may depend on the entire input distribution, and then take the distribution of the transformed samples. This defines a measure-dependent pushforward model and includes measure-theoretic formulations of transformers. We ask when such models can approximate arbitrary continuous operators between spaces of probability measures. We first show that universal approximation fails when atomic inputs are allowed: some continuous measure-to-measure operators that split or redistribute atomic mass cannot be approximated arbitrarily well by deterministic pushforward models. We then introduce the uniform level set condition, which requires a continuous measure-dependent scalarization whose shrinking level set neighborhoods carry uniformly vanishing mass over the input family. This condition is satisfied, in particular, by compact families of absolutely continuous measures. On every compact family satisfying this condition, we prove that any continuous measure-to-measure operator with outputs of finite $p$-th moment can be uniformly approximated, in the $p$-Wasserstein distance, by continuous measure-dependent pushforwards. Combining our theorem with existing approximation results for measure-dependent in-context maps yields universal approximation by measure-theoretic transformers. We also extend the framework to continuously-varying source measures, yielding a corresponding universality result for a class of pushforward models that are closely aligned with cross-attention architectures. --- ### TopoEP: Topology-Aware Load Balancing for Expert-Parallel MoE Training Authors: Jiacheng Zhu, Xie Zhao, Gongming Zhao, Hongli Xu, Yao Fei, Jin Fang Published: 2026-09-28 Categories: cs.DC, cs.LG arXiv: https://arxiv.org/abs/2609.35481v1 Dynamic routing creates severe load imbalance in large-scale expert-parallel Mixture-of-Experts (MoE) training, turning GPUs that host hot experts into stragglers. As each MoE layer waits for its slowest rank, these stragglers prolong the expert-parallel stage and reduce overall training efficiency. Existing expert-parallelism load-balancing (EPLB) systems commonly compute load-balancing plans on the CPU, incurring device--host data transfers and cross-rank synchronization that make scheduling at every layer and microbatch expensive. Their planning formulations also overlook the hierarchical communication costs of modern scale-up and scale-out GPU clusters. We present \textit{TopoEP}, a GPU-native, topology-aware load-balancing system for large-scale MoE training. At each MoE layer and training microbatch, \textit{TopoEP} converts the current routing result into hot-expert replication and token-rerouting decisions and executes the resulting plan without data-dependent host synchronization, reducing critical-path overhead. To generate these decisions, \textit{TopoEP} uses a deterministic GPU solver that performs inter-node placement followed by intra-node refinement, allowing all ranks to independently produce bitwise-identical plans. On a 32-GPU NVIDIA H800 cluster, integrating \textit{TopoEP} with Megatron-LM improves end-to-end training throughput by 6.2\%--11.4\% across three representative MoE models. --- ### Analog Computing revisited: A fully analog and minimalistic Damage Detector for Ultrasonic Testing enabling Material-Integrated Structural Health Monitoring Authors: Stefan Bosse Published: 2026-09-28 Categories: cs.AR, cs.AI arXiv: https://arxiv.org/abs/2609.35478v1 Ultrasonic Testing (UT) is commonly used to detect damage in structures, e.g., metal plates. A sensor acquires Ultrasonic waves, e.g., by using PZT transducers. The time-resolved sensor signal must be processed with analog electronics, e.g., amplified and filtered. Commonly a digitalization follows using an Analog-to-Digital converter, finally processing the digital sensor signal, applying digital signal processing, feature extraction, and Machine Learning by using powerful microprocessor systems. The disadvantages of digital processing systems are their high number of transistors (microchip area), energy consumption, state-dependent processing and therefore sensitivity to energy supply interruption. Beyond silicon electronics, printed organic electronics gains interest. But printed electronics is still limited to low transistor and electronic component counts (typically 100). We will investigate and demonstrate a fully analog signal processing and feature extraction system consisting of an analog Hilbert transform deriving the signal envelope, simple analog arithmetic calculations for feature extraction, and finally damage classification and regression using an analog Artificial Neural Network. We expect a full damage detection system with less than 100 transistors. We will test our damage detection system with PZT transducer signals from Steel plates with circular defects. The focus of this work is the analog computation of the signal envelope (using all-pass filter networks for approximation of the Hilbert transform) and the analog feature extraction as well as the prediction of damage, forming an analog computer which can perform in-sensor computation, computing without a digital computer. --- ### Spontaneous Context Restoration: How Language Models Recover from Corrupted Inputs Authors: Pranjal Garg, Jacob Beck Published: 2026-09-28 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2609.35475v1 Language models sometimes produce correct outputs even when their inputs are corrupted by deletion, replacement, or misspelling. We study the internal processes accompanying this behavior, which we call context restoration, in controlled attention-only transformers and five pretrained LLMs (1B-32B parameters) across arithmetic, reading comprehension, and multiple-choice reasoning tasks. In the attention-only transformers, restoration emerges spontaneously despite training exclusively on clean sequences, without corruption training or an explicit denoising objective. We find that context restoration follows a two-phase process: early layers localize effects associated with repair at corrupted positions, while later layers accumulate these effects at uncorrupted positions through the residual stream and ultimately concentrate them at the output position. Repair outcome is predictable from hidden states: cosine alignment with the clean state is highly predictive in attention-only models, while linear probes recover additional information in pretrained LLMs. A linear probe using only the corrupted prompt's first-block hidden state predicts failure with mean ROC-AUC 0.78. This enables failure triage under matched or even partially shifted deployment conditions and may reduce unnecessary verification or computation. Failed examples also show substantially greater nonlinearity along corruption directions. Moderate-corruption finetuning increases corruption tolerance while simultaneously reducing displacement-normalized linearization error, associating improved robustness with a more nearly linear response to corruption. --- ### Handwritten Text Recognition Lives in the High-Pixel Variance Subspace Authors: Carlos Garrido-Munoz, Jorge Calvo-Zaragoza Published: 2026-09-28 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2609.35473v1 In self-supervised pretraining for Handwritten Text Recognition (HTR), pixel reconstruction methods outperform contrastive methods, unlike in natural-image classification. We argue that this difference follows from where discriminative signal lies in pixel space: for HTR, it is concentrated in high-variance directions and largely absent from low-variance ones. This predicts that objectives preserving high-variance pixel content will transfer best. We test six SSL methods from three families (pixel-grounded MIM, JEPA, and contrastive) under matched encoder, data, and evaluation protocols on six handwriting benchmarks across five languages. With full labels, pixel-groundrounded SSL achieves the lowest CER on every benchmark and both frozen probes, exposes per-position character information that other families recover only through the readout, and is the only family to benefit from pretraining on real handwriting. Pixel-grounded representations are also more label efficient. Across datasets, encoder alignment with the high-variance pixel subspace predicts CER within every method. With a pretrained LLM decoder, a frozen pixel-grounded encoder is competitive with fully fine-tuned supervised baselines; full fine-tuning achieves the lowest mean CER and ranks first or second on every benchmark. These results show that the value of pixel reconstruction depends on where discriminative signal lies in the input. --- ### Why Deterministic PRM Guidance Underperforms in Discrete Diffusion Reasoning Authors: Yan Zhan, Shaobo Liu, Zhijun Gao Published: 2026-09-28 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.35472v1 Discrete diffusion language models (dLLMs) expose a denoised solution at every step, which makes process reward model (PRM) guidance look like a way to spend compute at test time. We show that once denoising, PRM scoring, and outcome reward model (ORM) scoring are charged in the same budget of forward passes, its deterministic form loses to a much simpler baseline. Our PRMs score intermediate denoising states and are trained on the correctness of the final answer. On Dream-v0-Instruct-7B with 8 candidates per GSM8K problem, keeping the candidate with the highest PRM score at every scoring step reaches 65.18%, while independent sampling plus an ORM reranker trained for the task reaches 75.13%. The gap grows to 12.69 percentage points (pp) with 32 candidates, and is 9.85 pp on MATH and 12.16 pp on MBPP. We trace it to two separable failures. First, guidance prunes on a weak signal: on GSM8K, PRM ROC-AUC falls from 0.77 to 0.54 as the mask ratio rises, a decay that persists when states are relabeled with fresh rollouts, and pruning lowers the best accuracy reachable from the candidate pool from 81.05% for independent samples to 67.30%. Second, on GSM8K and MATH, the PRM is a poor final judge: a sequential Monte Carlo sampler at the same budget restores that ceiling to 77.89%, yet selecting with the PRM gives 65.48%, on par with deterministic guidance, while a PRM retrained on final states matches the ORM on identical candidates. MBPP separates the two: there the PRM reaches 65.47% when reranking finished programs, on par with the ORM, but 50.88% when it guides denoising. The results point to two targets for dLLM guidance: keep correct partial solutions alive through early denoising, and leave the final choice to a verifier trained on final states. We release the corpus of denoising states with outcome labels and evaluation toolkit for reproducible comparisons at matched compute. --- ### Rethinking Causal Action Tokenization with Conditional Annealing in Flow Matching Authors: Chenyu Zhang, Yuhang Cao, Daru Du, Yingxi Lu, Jing Shao, Ruoqu Chen, Jiajun Liu, Liu Cao, Yicheng Liu, Hang Zhao, Mengdi Xu Published: 2026-09-28 Categories: cs.RO, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.35469v1 Autoregressive Vision-Language-Action (VLA) models offer a scalable path to robot learning, yet existing action tokenizers treat tokenization as a compression problem, producing representations that are semantically misaligned with the autoregressive backbone. We propose CATok, a causal action tokenizer that reframes tokenization as a causally structured generative process. CATok introduces a conditional annealing mechanism that extracts action tokens by progressively annealing a flow-matching process: each token is conditioned on all preceding tokens and encodes the residual reconstruction signal at a specific noise level, establishing a coarse-to-fine causal token space whose generative semantics are structurally aligned with autoregressive modeling. A token-conditioned flow-matching decoder built on Multimodal Diffusion Transformer (MMDiT) reconstructs continuous action chunks from these discrete tokens with the precision of hybrid diffusion-head architectures. This discrete bottleneck enforces knowledge insulation by design, cleanly separating high-level semantic reasoning from low-level motor execution without requiring explicit attention masking. Extensive evaluations across three simulation benchmarks and real-world robotic manipulation tasks demonstrate that CATok consistently surpasses existing tokenization methods in both reconstruction fidelity-compression tradeoff and inference efficiency, while improving VLA task success rate and training efficiency, establishing a high-performance, scalable foundation for purely autoregressive VLA systems. --- ### An analysis of Mirror-Descent Soft Actor-Critic Authors: Denis Zorba, Michal Valko Published: 2026-09-28 Categories: cs.LG, math.OC arXiv: https://arxiv.org/abs/2609.35466v1 Soft Actor-Critic (SAC) is widely used for entropy-regularised reinforcement learning with continuous action spaces, and practical implementations perform only a few actor steps towards an evolving target. In this work, we prove convergence guarantees when the target policy arises from policy mirror descent and compare it with the classical Gibbs target. We derive sufficient conditions for the strong convexity and smoothness of the actor objective, characterised by the curvature of the $Q$-function estimate through the Legendre differential operator, and establish an $\mathcal{O}\!\left(N^{-\frac{1}{5}}\right)$ best-iterate finite-time convergence rate up to actor and critic approximation errors. Moreover, the mirror-descent step size $λ$ directly controls the target drift and hence actor tracking error, whereas the analogous Gibbs bound contains a non-vanishing tracking term. --- ### Tetra: Serving Leech-Lattice Quantized LLMs at 2.7 Bits per Parameter Authors: Pier-Jean Malandrino Published: 2026-09-28 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.35465v1 Leech-lattice quantization gives good quality at two bits per weight, but its codebooks hold more than 10^14 points, too many for a lookup table. Our earlier kernel expanded the codes at load time and read 4.804 bits per weight from GPU memory for 2 bits of code. We present Tetra, a new codebook on the same lattice. A 24-weight block still takes 48 bits, most of which index a 64-state trellis of the Golay code and one shared 16 KiB table. The kernel decodes a block with six table loads and two small lookups inside the matrix-vector product, and reads 2.148 bits per weight. For full models, we retrain one scale per matrix row, store the matrices that lose the most as 4-bit integers, and pay for them with 4-bit embedding tables. Our Qwen3-4B, 8B and 14B files hold 2.73, 2.70 and 2.73 bits per parameter over the whole model. They score 63.37, 69.58 and 75.66 on the full MMLU test set, 4.76, 4.21 and 2.46 points below 4-bit AWQ at 5.3 to 6.0 bits per parameter. They generate 113.8, 95.0 and 57.2 tokens per second in our engine. On GSM8K, through the served kernel, they lose 9.63, 4.62 and 3.26 points to FP16. At 4B our file scores 23.6 points above llama.cpp's IQ2_XXS (2.48 bits per parameter). Every number we measured for a table or figure comes from one NVIDIA L40S GPU. We preregistered the main experiments. --- ### W2Rep: Learning Visual Representations by Watching the World Change Authors: Wen Huang, Hang Guo, Jiarui Yang, Zheng Liu, Tao Dai, Shu-tao Xia Published: 2026-09-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.35464v1 Images capture the world at one moment, whereas video reveals how it changes. Image self-supervision learns spatial structure from a single moment, while video methods commonly learn temporal relationships inside a representation computed jointly from several frames. We ask whether watching a scene change can instead improve features available from one image without sacrificing the ability to represent video. We introduce W2Rep, a masked feature-prediction framework in which an independently encoded source image participates in prediction at the same or another moment. The predictor is conditioned on visible video context, the queried location, and the signed time interval between source and target. This gives the cross-frame objective two complementary roles: the image path learns features that remain useful across time, while the video path must gather evidence that is missing from the source image. Across model scales and downstream tasks, W2Rep improves frozen and fine-tuned recognition under our comparison protocol, while joint video encoding provides further gains over frame-wise aggregation. Controlled experiments show that these gains depend on directly updating the source-image features and on using both video context and temporal displacement. Overall, change across a video can supervise a visual encoder whose representations remain useful at either image or video granularity. Code is available at~\href{https://wenooi.github.io/W2Rep}{https://wenooi.github.io/W2Rep}. --- ### A.D.A.M.O. (Agent for language-Driven Actions with Multimodal Observations): A Visual-Symbolic Framework for Virtual Humans Authors: Alessandro Emmanuel Pecora, Stefano Calzolari, Francesco Strada, Andrea Bottino Published: 2026-09-28 Categories: cs.AI, cs.GR arXiv: https://arxiv.org/abs/2609.35463v1 Creating believable vh requires the coherent integration of perception, reasoning, and action mediated by language. A central challenge is to combine these components into a control loop grounded in interactive 3D environments. To this end, we present A.D.A.M.O. (Agent for language-Driven Actions with Multimodal Observations), a visual-symbolic framework for language-driven vh that leverages a pretrained vlm with tool calling to unify perception, reasoning, and action within a single control loop. A.D.A.M.O. maintains a dual visual-symbolic world model that combines egocentric visual input and synchronized symbolic state to support grounded task-oriented behavior from natural language prompts. To support diagnostic evaluation, we introduce a controlled task suite organized by a cd taxonomy that breaks down spatial tasks into procedural and linguistic complexity. Experiments in controlled scenes show that semantic labeling strongly influences task completion and failure modes, reducing perceptual ambiguity while shifting failures toward downstream execution, whereas reasoning errors remain comparatively rare. --- ### CLIMB: A Clinical Multimorbidity Benchmark for Diagnosing Co-occurring Conditions through Multiturn Conversations Authors: Yusuf Kesmen, Aniruddha Mukherjee, Yena Chang, David Sasu, Trevor Brokowski, Alexandra V. Kulinkina, Kristina Keitel, Akhil Arora, Lars Henning Klein, Mary-Anne Hartley Published: 2026-09-28 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2609.35462v1 Patients often have several co-occurring clinical conditions, and the findings needed to identify and disambiguate them emerge over the course of a consultation. Evaluating clinical reasoning in this setting requires both multi-turn interaction and multi-label diagnosis. We introduce CLIMB, a benchmark in which a doctor model interviews a simulated patient to recover a ground truth set of co-occurring clinical conditions. Cases are synthesized from clinical decision algorithms and diagnostic datasets, grounding multimorbid presentations in structured clinical knowledge. Across six frontier and open models, none recovers the exact set of conditions in more than 10% of interactive cases. Diagnostic performance declines when conditions co-occur, even when models receive the full clinical record and the true number of conditions. Interaction reduces performance further. In controlled experiments, models behave like single-hypothesis trackers: they anchor on the diagnosis suggested by the opening findings, keep questioning around it, and recover a second condition mainly when a finding in view points to it. Questioning them further does not complete the set but adds mostly wrong diagnoses. We formalise this pattern with a theoretical reference model of single-hypothesis tracking. The benchmark, generator, and evaluation code are available at https://anonymous.4open.science/r/CLIMB-8340. --- ### AraDynFact: Dynamic Evaluation of Factual Knowledge in Arabic Authors: Ignacio Iacobacci, Faroq Altam, Zhaozhi Qian, Muhammad Alqurishi Published: 2026-09-28 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.35461v1 As Large Language Models (LLMs) continue to scale both in size and capabilities, their proficiency in the Arabic Language has seen significant advancement. However, a critical gap remains: the extent of their factual knowledge and cultural sensitivity to the diverse Arabic-speaking world remains largely underexplored. Current evaluation metrics often focus on translation or generic reasoning, failing to capture the rich historical, social, and regional nuances inherent to Arabic culture. In addition, most benchmarks rely on heavy work, with human intervention in some steps, making the evaluation of knowledge coverage expensive and slow. To address this deficiency, we introduce AraDynFact, a novel dynamic evaluation framework designed to rigorously assess the factual Arabic knowledge embedded in LLMs. Unlike static benchmarks, AraDynFact employs a dynamic approach to extract factual information and generate rich and answerable questions in a fast and automatic way. We apply AraDynFact to Arabic Wikipedia and audit the performance of several state-of-the-art models, ranging from Arabic-centric specialized LLMs to high-resource general purpose LLMs. In addition we found a high degree of correlation with existing, hand-crafted Arabic-centric benchmarks, confirming the potential of our dynamic approach. --- ### How Far Are We from Removing the Visual Encoder? Scaling Laws for Encoder-Free Multimodal Pretraining Authors: Lin Chen, Bolin Ni, Qi Yang, Lan Jiang, Kun Ding, Xiaoran Fan, Hower Yang, Ying Wang, Shiming Xiang Published: 2026-09-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.35457v1 Most modern multimodal large language models (MLLMs) build on a pretrained visual encoder that provides a strong visual prior. Encoder-free MLLMs instead learn visual representations directly from raw pixels, offering a simple and unified architecture, but their scaling behavior has not been systematically characterized. To fill this gap, we compare scaling laws for encoder-free and encoder-based MLLMs and report three main findings: (1) Removing the visual encoder shifts the compute-optimal allocation for the multimodal objective toward larger models, while leaving that for text nearly unchanged. (2) The two architectures exhibit nearly overlapping loss--compute frontiers on the text objective, but diverge on the multimodal objective: encoder-free models underperform at small scales yet are predicted to catch up at around $10^{22}$ FLOPs, well within practical pretraining budgets. (3) Without a visual encoder, the language model learns to take over its role via vision-specific adaptation: bidirectional interactions among visual tokens become increasingly beneficial as training compute grows, visual processing shifts toward earlier layers, and expert routing for visual tokens becomes more concentrated. Overall, our results indicate that the advantage of the visual prior provided by a pretrained encoder diminishes with scale, positioning encoder-free architectures as a promising direction for multimodal pretraining. --- ### AutoBCI: Forecast-Guided Agentic Neural Architecture Discovery for EEG-Based Brain--Computer Interfaces Authors: Muyun Jiang, Yi Ding, Wei Zhang, Jinbo Chen, Chenyu Liu, Zhenjie Yang, Yuxin Li, Jingyuan Chen, Yuhao Lu, Yong Li, Shuailei Zhang, Cuntai Guan Published: 2026-09-28 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.35456v1 EEG-based brain-computer interfaces support a broad range of applications, yet designing decoding architectures that perform well across diverse tasks remains challenging. We introduce AutoBCI, an agentic framework in which a Designer Agent and a Forecaster Agent support the discovery and selection of EEG decoding architectures across tasks. The Designer Agent performs Pool-Guided Architecture Discovery (PGAD), generating and refining architectures through training and validation across multiple EEG tasks, such as emotion recognition, motor imagery, and sleep staging. The Forecaster Agent performs Performance Estimation from Early Knowledge (PEEK), using architecture code, the training protocol, and early learning curves to predict full-budget validation performance and select promising candidates for continued training. Across 14 EEG datasets spanning motor imagery, emotion recognition, and sleep staging, we evaluate AutoBCI with six LLMs, including Opus 5.5 and GPT 5.6 Sol, and compare the architectures selected by the search procedure against ten baselines: six conventional EEG models and four foundation models. The architecture discovered by AutoBCI with Claude Opus 5.5 achieves 64.16% average test balanced accuracy (bAcc), compared with 63.87% for REVE, the strongest baseline on this metric. Using ten observed epochs, PEEK reduces mean absolute error in predicting average validation bAcc from 2.20 to 1.36 percentage points, a 38.1% reduction relative to the best-observed-score baseline. --- ### Manifold-Stable Flow Matching Authors: Amirhossein Nazerian, Ali Pezeshki, Jianguo Zhao Published: 2026-09-28 Categories: cs.LG, cs.RO, eess.SY arXiv: https://arxiv.org/abs/2609.35454v1 Flow matching (FM) learns generative dynamics through velocity regression. Geometric FM variants commonly assume a prior supported on the data manifold, requiring geometric knowledge that is often unavailable. Without such knowledge, low regression error alone does not guarantee manifold adherence. Adherence keeps generated samples within valid configurations and is empirically associated with better task performance. We introduce manifold-stable flow matching (MSFM), which can start from an arbitrary ambient prior, not necessarily supported on the manifold. Using tools from nonlinear dynamics, namely contraction theory, MSFM combines learned tangential transport with prescribed normal contraction. The construction uses analytical projectors for known manifolds and local affine proxies estimated by principal component analysis for unknown data geometry. By implementing contraction theory in both cases of known and unknown manifolds, we guarantee manifold invariance and transverse convergence to the manifold within a desired time window (e.g., one second). We derive a family of compatible probability paths and decompose the training loss into a learnable tangential term and a normal residual. An ellipse experiment attains a mean terminal off-manifold error of order $10^{-6}$. In Push-T robotic experiments, MSFM raises success from $74\%$ to $82\%$. In the Robomimic Square task, success increases from $60\%$ to $72\%$, while rotation-manifold deviation decreases from order $10^{-2}$ to $10^{-7}$. The MSFM terminal geometric errors are controlled by the chosen numerical tolerance. These results demonstrate stronger geometric adherence and higher observed task performance, supporting prescribed normal contraction as a complement to learned generative transport. --- ### From internal representations to model improvement through prediction errors Authors: Yushi Nakaya, Kenichi Higuchi, Shuichi Ishida Published: 2026-09-28 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2609.35449v1 With limited annotation budgets, choosing which images to label determines how much a model improves. Data-selection methods that use features from a separately trained model, or scene descriptions written by vision-language models, have been successful, but those signals do not directly capture changes in the model being improved. The target model's own internal features reflect what it has learned so far and change with retraining, making them a natural cue for choosing the next training data. However, feature rarity alone does not reveal the errors that matter for performance. Here we link internal features to prediction errors and their expected impact on performance and select images for labeling and retraining without using labels for candidate images. We evaluated the method with an object detector on two datasets and two pairs of random seeds. Adding internal features improved the identification of prediction errors in 15 of 16 conditions. When performance was averaged over successive labeling rounds, the method outperformed selection based only on feature rarity in all four evaluation settings and ranked among the top two of six methods. With other conditions held fixed, performance after retraining was again higher than with rarity-based selection, even though the latter collected more errors. With longer retraining, the proposed method ranked first among six methods. These results suggest that linking a model's internal features to its errors and their effects on performance may help select training images that improve performance, thereby allowing the model's current state to guide which images are labeled next. --- ### NeuronSifter: Intervention Planning in CNS Microenvironments Authors: Haowei Xu, Wanyi Fu, Hongbin Han, Zhaoheng Xie Published: 2026-09-28 Categories: cs.LG, q-bio.NC arXiv: https://arxiv.org/abs/2609.35445v2 Prioritizing central nervous system (CNS) interventions requires predicting how a dose, route, and schedule act on a partially observed microenvironment, then choosing the measurement that would change the decision. Action-conditioned predictors reduce a regimen to an identity token or a scalar exposure, discarding where and when the target is engaged; handing a point estimate to a separate planner then discards the joint uncertainty that makes a measurement worth running. We therefore treat decision quality as a property of the intervention interface, not of controller placement. NeuronSifter compiles regimens into state-conditional target-occupancy fields with support masks, propagates them through microenvironment dynamics with an occupancy-conditioned diffusion operator, and selects measurements by their expected reduction in intervention loss, assimilating typed outcomes into the same posterior. In a declared synthetic Alzheimer's disease (AD) evaluation over 64 paired scenario blocks, occupancy conditioning lowers trajectory continuous ranked probability score from 0.165 to 0.110 and raises intervention ordering accuracy from 0.760 to 0.880, and every paired benchmark contrast remains separated after Holm correction. Decision-directed acquisition attains terminal risk 0.160 against 0.166 for a matched numerical Bayesian experimental design planner, and reaches the target risk at 0.796 $(0.732,0.873)$ of an earlier design control's cost, while the corresponding ratio against the matched planner, 0.963 $(0.907,1.025)$, is not separated from equality; point-state and dependence-ablated interfaces instead raise risk to 0.220 and 0.199, and a full-posterior external controller ties exactly. Published AD trials supply a separate retrospective endpoint bridge. --- ### DiMoP: Diffusion-Driven Motion Representation Learning With Frame-Level Pseudo-Classification for Skeleton-Based Action Recognition Authors: Shanaka Ramesh Gunasekara, Wanqing Li, Nikalal Kaldera, Philip Ogunbona, Jack Yang Published: 2026-09-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.35444v1 Robust skeleton-based action recognition requires representations that capture a wide spectrum of motions, from subtle to moderate and strong ones. Existing methods often focus on strong motions. This paper introduces DiMoP, a masking- and diffusion-driven motion representation learning method with frame-level pseudo-classification to explicitly learn the distribution of joint motions rather than regressing deterministic coordinates, as existing methods often do. By diffusing masked joints with progressive noise and denoising them conditioned on visible joints, DiMoP learns through controllable noising and denoising processes, enabling uniform learning of weak, moderate, and strong dynamics. To enable the masking-based generative diffusion learning with a discriminative capability, a pseudo-frame classifier is proposed that enforces the learning towards sequence-consistent and temporally coherent pseudo-labels without manual annotations. Together, these strategies provide a principled mechanism for joint generative and discriminative motion modeling. DiMoP achieves state-of-the-art performance across NTU RGB+D 60/120, and PKUMMD, including a 1.1 percentage point gain over prior works on NTU RGB+D 120 with the cross-subject protocol. --- ### Just Initialize: A Training-Free Initialization Component for Large-Scale Routing Optimization Authors: Jiale Zhao, Sirui Mao, Zimu Chen, Wentao Yang, Zihan Wang, Xuefeng Huang, Junji Cheng, Liyuanjun Lai Published: 2026-09-28 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.35443v2 Large-scale routing problems are difficult to solve efficiently as their search spaces grow rapidly with problem size. Existing approaches primarily improve the optimization procedure itself, often at increasing computational cost. We instead shift the focus to a useful initialization that can be refined into a high-quality solution with limited downstream refinement. We propose Just Initialize, a training-free and solver-agnostic initialization component for large-scale routing optimization. Just Initialize compresses a large routing instance into a compact surrogate space, optimizes its global routing structure, and recovers the resulting solution as an optimization-friendly starting point in the original space. Extensive experiments on Traveling Salesman Problems (TSPs), Capacitated Vehicle Routing Problems (CVRPs), Vehicle Routing Problems with Time Windows (VRPTWs), and Prize-Collecting Traveling Salesman Problems (PCTSPs) demonstrate that Just Initialize achieves high-quality solutions comparable to or better than state-of-the-art methods while substantially reducing computational cost across instances ranging from 1K to 100K nodes, including an average speedup of approximately 70$\times$, sub-second runtimes on 10K-node instances, and runtimes within tens of seconds on 100K-node instances. --- ### Riccati State Space Models: Non-iterative Parallelization for Nonlinear Sequence Modeling Authors: Mónika Farsang, Ramin Hasani, Daniela Rus, Radu Grosu Published: 2026-09-28 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.35441v1 State space models (SSMs) achieve efficient sequence processing because their affine state updates are closed under composition and can therefore be evaluated with an associative parallel scan. Nonlinear recurrent models can provide richer, state-dependent dynamics, but generally lose this compositional structure: parallel evaluation then requires iterative methods that repeatedly linearize and scan the recurrence. We ask, what state-dependent nonlinear dynamics can be designed to remain exactly composable? We answer by introducing RiccatiSSM, a nonlinear SSM, in which each state dimension follows an input-conditioned Riccati differential equation. Its quadratic state dependence makes the local Jacobian explicitly state-dependent, while its exact per-step flow under piecewise-constant inputs is a Möbius transformation. Since Möbius maps are closed under composition and compose through $2\times 2$ matrix multiplication, the complete nonlinear state trajectory can be evaluated exactly with a single associative parallel scan, without iterative linearization. We further derive a constrained parameterization that ensures bounded, contractive dynamics, and avoids poles in the fractional-linear state update. Across long-sequence classification, regression, and forecasting tasks, RiccatiSSM achieves competitive predictive performance while reducing runtime by $22{-}33\%$ compared to the nonlinear LrcSSM under matched architectures. These results demonstrate that state-dependent nonlinear dynamics can retain exact composability and be evaluated efficiently within a single parallel scan. --- ### SOLO: Pretraining Billion-Parameter Language Models with Shared-Output Local Learning Authors: Bojian Yin, Shurong Wang, Yuqi Pan, Guoqi Li Published: 2026-09-28 Categories: cs.LG, cs.DC arXiv: https://arxiv.org/abs/2609.35440v1 Large language models are trained with backpropagation, whose global gradient coordinates all layers but forces each to hold its activations and wait for the gradient to pass back through every deeper layer. Conventional local learning removes this update locking by training each module to predict the target through its own readout, but has not scaled to billion-parameter pretraining. We identify these private readouts as a key weakness, since they leave each module without information from deeper modules. We propose Shared-Output LOcal learning (SOLO), which replaces them with a shared, read-only copy of the final module's readout, the only one trained on the output of the whole network. Taken from the previous step, the copy transmits information from the final module without passing gradients between modules or reintroducing update locking. SOLO approaches backpropagation on Transformers of 340M to 2B parameters pretrained on 15B tokens, staying within one point in average zero-shot accuracy with a perplexity gap that narrows with scale. Readout ablations attribute SOLO's improvement over private readouts to sharing. Without update locking, each of p pipeline stages holds activations for O(1) micro-batches instead of O(p). The freed memory permits larger micro-batches, which reach up to 1.44x the best measured throughput of pipeline backpropagation on the same partition. To our knowledge, SOLO is the first local learning method to show such memory and throughput gains in billion-parameter language-model pretraining. Local learning thus becomes a practical alternative to backpropagation for large-scale pretraining. --- ### Revision, Not Restart: Revisable Visual Plans for Closed-Loop World-Action Models Authors: Pengyiang Liu, Junbo Niu, Wenhao Zheng, Xinchen Chen, Canyu Li, Zhongyue Shi, Jiahao Xie, Si Liu Published: 2026-09-28 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2609.35439v1 World-action models use predicted visual futures to condition robot actions, yet execution feedback can invalidate parts of a prediction while leaving its task structure useful. We propose Revisable Temporal Planning (RTP), which maintains the visual future as a persistent action condition and revises it after feedback. Its central mechanism is a learned revision bridge: it resumes an intermediate state saved during visual generation and adapts its continuation to current observations. Visual and action supervision connect this revision to subsequent control. Time-aware history supplies observed evidence, and an adaptive policy selects retention, bridge revision, or fresh replanning from new noise before decoding the next action. On RoboMME and RMBench, RTP achieves task-averaged success rates of 48.6% and 84.8%, respectively. Matched comparisons support learned continuation; estimated checkpoint-source and action-prefix effects are positive but less precisely resolved. These results connect feedback-driven visual-plan revision to closed-loop task performance. Project Page: https://PLACEHOLDER.github.io/RTP/ --- ### An integrated geometric quantification and shape analysis framework for axillary lymph node metastasis in breast cancer patients Authors: Zixi Yi, Limeng Qu, Gary P. T. Choi Published: 2026-09-28 Categories: q-bio.QM, cs.CV arXiv: https://arxiv.org/abs/2609.35437v1 Quantitative characterization of lymph node morphology is important for assessing axillary lymph node metastasis in breast cancer. However, surfaces reconstructed from computed tomography (CT) segmentation may contain geometric and topological defects that compromise subsequent analysis, while conventional shape descriptors predominantly characterize global morphology. To address these issues, we developed an integrated framework combining topology-aware surface processing with multi-resolution spherical harmonic (SH) analysis of CT-derived axillary lymph nodes. The processing pipeline produced topology-valid genus-0 surfaces with improved mesh quality, which were then represented at multiple SH degrees and characterized using 20 predefined geometric feature families. Geometric fidelity increased with SH degree, whereas predictive performance peaked at intermediate resolutions. Preferred SH degree also differed across feature families. A family-specific mixed-resolution model achieved an AUC of 0.918, compared with 0.884 for the conventional PyRadiomics Shape14 baseline, corresponding to an improvement of 0.0344. Controlled perturbation experiments showed that higher SH degrees transmitted more fine-scale geometric variation and yielded lower stability of curvature-based predictions. Representative geometric descriptors provided interpretable characterization of metastasis-associated surface morphology. Independent validation further supported the framework's transportability: label-free replication in a multicenter lymph node cohort reproduced the family-specific resolution effects, while a labeled LIDC-IDRI lung-nodule experiment reproduced the resolution-dependent relationship between SH degree and predictive performance. Altogether, the framework provides a topology-valid basis for quantitative characterization of lymph node morphology and metastasis-associated imaging phenotypes. --- ### Building Transformation Layers for Riemannian Neural Networks Authors: Ziheng Chen Published: 2026-09-28 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.35436v2 Recently, deep neural networks on manifold-valued representations have garnered significant attention across various machine learning applications. One recent focus is the generalization of Euclidean fully connected (FC) and convolutional layers to non-Euclidean geometries. However, previous approaches typically focus on a few selected manifolds and rely on specific properties of the target manifold. In contrast, this work proposes a framework for constructing FC and convolutional layers over computationally tractable Riemannian spaces. This framework incorporates several previous FC layers across different geometries as special cases and is instantiated on ten representative manifolds, including three hyperbolic models, five geometries of the symmetric positive definite (SPD) manifold, and two Grassmannian perspectives. Experiments on different manifolds demonstrate the effectiveness and applicability of our approach. Code can be found at https://github.com/GitZH-Chen/RieTrans. --- ### ReSPO: Reshaped Sequence Policy Optimization for Gradient Starvation in Off-Policy Learning Authors: Yihang Chen, Yuanhao Ban, Cho-Jui Hsieh Published: 2026-09-28 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.35433v1 Reinforcement learning from verifiable rewards (RLVR) frequently reuses rollouts across multiple policy updates, increasing the mismatch between the current policy and the data-generating policy. We identify a sign-dependent gradient starvation problem in clipped policy optimization: clipping suppresses under-generated positive responses at the low-importance-weight tail while permitting severely over-generated negative responses to dominate the high-weight tail. To address this, we propose ReSPO (Reshaped Sequence Policy Optimization), which replaces clipping with a smooth, two-branch sequence-level kernel derived from an $α$-divergence variational objective and an exponential variance-control tilt. The positive branch preserves a nonzero gradient weight for under-generated positive responses, while the negative branch suppresses heavily over-generated negative responses. We demonstrate that ReSPO effectively learns from long positive reasoning trajectories during early training, even when accumulated policy drift relegates them to the low-importance-weight tail. On dense and MoE Qwen3 models, ReSPO accelerates early optimization, improves final training scores, and achieves higher held-out benchmark performance under a rollout reuse, validating our approach on importance-weight tail control in off-policy learning. --- ### Multi-Task Learning of Conditional Mean Operators: applications to dynamical systems and uncertainty quantification Authors: Sami Chemlal, Thibaut Germain, Rémi Flamary, Vladimir R. Kostic, Karim Lounici Published: 2026-09-28 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2609.35429v1 Estimating conditional statistics and learning representations of a population of conditional distributions are central problems in many data-driven applications, including uncertainty quantification and dynamical systems analysis. Conditional mean operators (CMOs), a class of linear operators between function spaces, resolve these objectives by providing access to a broad class of conditional statistics. However, existing methods typically estimate each CMO independently or constrain it to prespecified function spaces, thereby preventing the exploitation of shared structure across related distributions. In this work, we posit that related CMOs share finite-dimensional input and output function spaces, and are specialized for each task with a linear operator mapping these spaces. Based on this hypothesis, we introduce MTL-CMO, a multi-task framework that jointly learns shared function spaces and task-specific operators across multiple datasets. We further introduce T-CMO, a transfer learning method that reuses the shared spaces to estimate, in closed form, the operator of a new conditional distribution. We establish statistical guarantees quantifying the benefits of jointly learning the shared function spaces. Our experiments demonstrate that learning shared function spaces improves uncertainty quantification across a broad range of conditional distributions and, when applied to Langevin and plasma dynamics, yields compact representations of complex dynamics that retain physically meaningful information and enable parameter identification. --- ### LLMs are General Asynchronous Agents Authors: George Yakushev, Denis Mazur, Vladimir Bartenev, Vyacheslav Zhdanovskiy, Timofey Byzov, Vladimir Kaurkin, Vadim Pastushenko Published: 2026-09-28 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2609.35427v1 Modern LLMs are increasingly capable as autonomous agents, but they follow sequential interaction cycles: read, think, reply or call tools, repeat. Many real-world use cases are not sequential: voice assistants, embodied agents, and monitoring systems receive new inputs while they think or perform another task. Modern LLMs address this with specialized architectures for voice interaction and video streams, VLAs for robot control, asynchronous tool calling for API usage, and others. In this work, we generalize from different asynchronous tasks to general asynchronous agents that can adapt to different types of concurrency. To achieve this, we develop an asynchronous LLM framework that lets users (or the agents themselves) define inference coroutines with overlapping memory states. We showcase that Qwen 3.x models are capable of asynchronous operation for streaming video understanding, videogames, and monitoring, without task-specific training. --- ### Frontier Learning: Training LLM Reasoners at the Edge of Capability Authors: Robin Faro, Shyam Sundhar Ramesh, Ilija Bogunovic, Aurelien Lucchi Published: 2026-09-28 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2609.35426v1 Reinforcement Learning-based post-training of Large Language Models (LLM) has been successfully applied to improve their reasoning capabilities. Existing pipelines primarily finetune LLMs on a fixed pool of problems specified prior to training using the GRPO loss. This is fundamentally limiting, as learning signal arises only when policy rollouts mix successes and failures, causing the useful portion of any fixed pool to quickly become stale as the model improves. To address this, we propose frontier learning, an open-ended post-training approach in which procedural generators are used online to continually produce informative training problems. It treats the generator's task-specific parameters as a search space and uses a regret signal to prioritize and explore frontier difficulty levels in order to focus training at the edge of the model's evolving reasoning capabilities. Across several reasoning tasks and model families, our approach consistently achieves higher relative gains over fixed-pool baselines, demonstrating that effective post-training requires not only selecting useful problems, but continually generating them at the edge of capability. --- ### Semantic Prefix Oracles for LLM Decoding: Contracts and Differential Validation Authors: Paul Kronlund-Drouault Published: 2026-09-28 Categories: cs.PL, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2609.35425v1 Constrained decoding can enforce regular or context-free output formats, but many program-generation failures are semantic: scope, typing, and declaration effects depend on context. We present semantic grammar specifications, a declarative formalism that attaches such constraints to a context-free surface and executes them during Earley descent. Our implementation enforces \emph{safe pruning}: it rejects only prefixes whose semantic contradictions cannot be repaired by any continuation. A separate, grammar-dependent, \emph{dead-end freedom} property guarantees the existence of a realizable witness for each remaining branch. We give simple sufficient conditions based on surface productivity, type coverage, and left-to-right constraint flow. Our finite-lambda, core ML, and C-like fragments satisfy them, while the STLC instance used in our experiments does not: plain STLC can violate type coverage, and we show how restricting its type universe recovers it. A tokenizer-lifting lemma carries character-level witnesses to token sequences under an explicit vocabulary-coverage hypothesis. We validate the implementation differentially against production compilers (\texttt{ocamlc}, \texttt{cc}). Across every prefix of 65 compiler-valid programs we observe zero false prunes. The semantic oracle localizes 25/30 invalid programs mid-stream, against 0/30 for a syntax-only oracle, and agrees on 42/42 recursion probes. A twelve-model generation study, including a matched semantic-versus-syntactic ablation for nine models, finds nonnegative observed semantic-minus-syntactic point estimates for every model-language pair, with maxima of $+15.2$ points on STLC task correctness and $+14.3$ points on ML validity. --- ### Automated Species Identification in Camera Trap Images for Wildlife Conservation Authors: Nowshin Amin, Nafisa Tabassum Oyshi, Tahmid Abrar Zidan, Miftaun Noor, Md. Abrar Rahman Shafin Published: 2026-09-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.35420v1 Wildlife conservation involves protecting, preserving, and managing wildlife species and their habitats. With today's rapid pace of human development, climate change, and other unsustainable practices, the need for wildlife conservation has heightened. Despite significant progress in species identification using deep-learning models, significant challenges still remain in effectively detecting small animals in low-contrast trap images due to limited feature extraction capabilities. This thesis presents a novel end-to-end framework integrating a self-attention mechanism to address these limitations. The proposed architecture involves a Swin-BiFPN backbone integrated in a Faster RCNN detection network, coupled with a visual semantic extraction module driven by the LLaVA v1.5 (13B) multimodal large language model. The detection framework, capable of extracting crucial features in challenging trap images, demonstrates consistently high results and robust generalization capabilities. Furthermore, the visual semantic extraction module provides zero-shot detection capability, as well as providing valuable insights and emergent cues of the animal's behavior, further supporting the conservation effort. The MLLM evaluation was conducted using both traditional NLP metrics (precision, recall, F1, and SBERT similarity) and subjective scoring by LLM-based judges (GPT-4.1 and GROK 3.0), across five MLLMs, demonstrating the model's strong performance in visual description generation. The proposed framework improves detection accuracy across low-contrast trap images and small animals while also demonstrating zero-shot detection capability leveraging the MLLM. --- ### Convex Optimization Is Free When Accuracy Is Expensive Authors: Arthur Paing, Arthur Jacot Published: 2026-09-28 Categories: math.OC, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2609.35418v1 This paper studies convex optimization when the gradient cannot be evaluated exactly, but only approximated by a hierarchy of algorithms whose compute grows like $δ^{-γ}$ in the accuracy $δ$. When $γ>2$, falling into the Harder-Than-Monte-Carlo (HTMC) regime, the price of accuracy outruns the variance reduction that Monte Carlo would buy and we show that minimizing a loss function costs no more, up to a factor depending only on $γ$, than a single evaluation of its gradient at the accuracy the problem demands. A randomized multilevel oracle replaces the deterministic approximation of accuracy $δ$ by an unbiased estimator of it, whose variance $σ^2$ becomes a second, independently priced dial: the cost of one call drops from $δ^{-γ}$ to $δ^{2-γ}σ^{-2}$. Plain inexact gradient descent driven by that oracle reaches loss $\varepsilon$ at expected compute $Θ(\varepsilon^{-γ})$ in the convex case, against $Θ(\varepsilon^{-(γ+1)})$ for the same method run at a fixed accuracy: randomization buys a full power of $\varepsilon$. Under $μ$-strong convexity the exponent halves, to $\varepsilon^{-γ/2}$, because the iterates settle at a noise floor and the bias budget relaxes accordingly. Both bounds are independent of the step size, and hence of the smoothness constant, and we show that the cost is a functional of the underlying gradient flow rather than of any discretization of it. --- ### When Should the Count Change? Learning State Maintenance for Causal Video Counting Authors: Pengyiang Liu, Dongyue Lyu, Junbo Niu, Zhongyue Shi, Jiahao Xie, Si Liu Published: 2026-09-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.35416v1 Continuous video counting requires distinguishing new observations from new objects or completed events. We introduce StaMina (State Maintenance), which learns to maintain counting state through state-conditioned updates. Recurrent visual context supports recognition; learned transitions maintain visibility, persistent identities, and completed-event records. A differentiable recurrence trains event transitions over legal paths constrained by count endpoints; visibility and association objectives train the object branch. A multi-source pipeline organizes 39.8K spatial queries and complementary event annotations into counting trajectories. On SVCBench, we evaluate counting adaptation with partial video overlap and held-out groups of linked annotations. Under prefix replay (Full) and persistent streaming (Stream), 4B and 8B models reach 41.9/36.4 and 44.9/38.2 Gaussian Precision Accuracy, respectively. The 8B model gains 10.9/3.2 points over Counting-SFT on the same queries. Matched-graph comparisons isolate phase conditioning and trajectory supervision, assessing training objectives alongside hard decisions. Online video benchmarks and count-conditioned decisions assess online understanding and task eligibility. Project Page: https://PLACEHOLDER.github.io/StaMina/ --- ### Adaptive Safety Filtering for Frozen ACC Policies via Conformal Residual Calibration Authors: Zhiruo Zhou, Rigaudiere Z. Li, Chen Xiwen, Yucheng Chen, Xiaojun Zhu, Houde Liu Published: 2026-09-28 Categories: cs.RO, cs.CV, eess.SY arXiv: https://arxiv.org/abs/2609.35415v1 Frozen adaptive cruise control (ACC) policies can violate constraints when deployment dynamics differ from their training conditions. We propose residual-aware conformal action filtering (RACF), which calibrates residuals of a fixed nominal predictor and converts their quantile into an operating margin for finite-model action projection. Completed transitions update margins and candidate selection without retraining the policy. In a registered comparison over 2,400 controller-trial units, Adaptive RACF achieves 94.3% episode safety, improving by 19.9 percentage points over the evaluated nominal CBF-QP baseline while reducing projection frequency from 8.11% to 6.63%. A controlled study isolates a 4.54-point improvement from residual-margin injection. In a separate matched-hardware evaluation, Adaptive reduces mean amortized rollout time by 21.2% relative to Robust CBF-QP, with 161/180 versus 170/180 safe episodes. We characterize conditions linking one-step residual coverage to constraint satisfaction and quantify the observed safety-computation trade-offs. ---