# Research Papers — 2026-09 · bundle page 12 of 266 > Full-text markdown of papers #551–600 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/12 [← Previous bundle](https://aipod.dev/papers/archive/2026-09/page/11.md) [Next bundle →](https://aipod.dev/papers/archive/2026-09/page/13.md) ### PrivCert: Certifying Statement Support under Differential Privacy Authors: Tsubasa Takahashi, Takumi Hiraoka Published: 2026-09-30 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2609.38934v1 Differentially private (DP) text generation can protect individual records, but privacy alone does not specify what evidence a released statement carries about the underlying data. We identify this as an evidence gap: a private report may contain plausible claims without indicating whether they are strongly supported by the private dataset. We introduce PrivCert, a framework for privacy-preserving reporting that makes statement support explicit through privacy-preserving certificates and emit-or-abstain decisions. As a canonical instantiation, PrivCert-PF (Proposal-and-Filter) separates data-independent candidate discovery from private support certification, emitting only statements whose support passes a private evidence test. We provide theoretical grounding for this framework by characterizing the limits of implicit evidence under DP, deriving a sharp privacy--honesty frontier for single-statement certification, and establishing a worst-case cost for fine-grained multi-statement certification. Experiments on synthetic tasks and TAB, WildChat, and Yelp show that explicit certification maintains low unsupported emission, while free-text DP baselines frequently produce low-support claims under the same declared support semantics. We further show that the PrivCert contract can be realized with histogram, sparse-vector, and Gaussian mechanisms, and use DP synthetic data to illustrate an important boundary: support in a private proxy does not automatically certify support in the original data. Together, these results position privacy-preserving reporting as an evidence-design problem: not only how to generate private text, but what a private report can substantiate about its underlying data. --- ### EFormer: Temporally Aligned Local Correction for Continuous sEMG-Based Hand Pose Tracking Authors: JiaCheng Ge, SiYu Zhang Published: 2026-09-30 Categories: cs.LG, cs.HC arXiv: https://arxiv.org/abs/2609.38932v1 Surface electromyography (sEMG) provides a wearable, camera-free signal for continuous hand-motion inference. Mapping muscle activity to joint kinematics remains challenging because the recorded waveforms are indirect measurements, their relationship with motion changes over time, and individual anatomy and sensor placement alter the signal distribution. This paper presents EFormer, a residual feature-correction network built on a frozen tracking backbone. EFormer combines a high-rate event branch, temporally aligned local cross-attention, two causal rotary position embedding (RoPE) temporal layers, and a bounded, dynamically gated residual. EFormer receives 16-channel sEMG sampled at 2 kHz and fuses a 64-channel tracking representation at 25 Hz with a 128-channel event representation at 200 Hz. Cross-attention uses a nominal delay of 100 ms, a 300 ms history parameter, and a 50 ms tolerance; its causal mask restricts each query to events occurring 50-400 ms earlier. The correction scale is 0.15. The evaluated continuation-training configuration contains 585,376 trainable parameters and 5,974,508 frozen parameters. On the test set, EFormer achieves an MAE of 0.1546634 rad, an RMSE of 0.24063 rad, and an R^2 of 0.74801, compared with 0.1745326 rad, 0.2715448 rad, and 0.6791103 for the official tracking baseline. EFormer reduces MAE by 11.38% relative to the baseline. The results show that temporally aligned event-feature correction can reduce continuous hand-pose tracking error. --- ### Adaptive Self-Consistency: From Black-Box Sampling to Distribution-Valued Feedback Authors: Jingkai Huang, Yunfan Zhang, Will Ma, Weihua Zhou, Zhengyuan Zhou Published: 2026-09-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.38931v1 Self-consistency samples many reasoning trajectories and aggregates their final answers, treating the LLM as a black box that returns one answer per trajectory. Yet the final answer of each trajectory is sampled from a softmax vector that is available from the model's log-probabilities. We refer to this as the grey-box setting in which each trajectory reveals this answer distribution rather than a single draw from it. We formulate efficient inference in this setting as sequential mode identification with distribution-valued observations: sample trajectories one at a time and stop as soon as the LLM's modal answer is identified at a prescribed confidence level. We characterize the asymptotic stopping rate of mode identification with distribution-valued observations exactly and show that it is never worse than the black-box rate. We then propose the ASC-D algorithm, a betting stopping rule that attains this asymptotic stopping rate. On MMLU-Redux, ASC-D uses $46.4$--$95.6\%$ fewer trajectories than answer-only adaptive self-consistency baselines and achieves the highest fixed-budget correct-certification rate across three open-source models. --- ### On the Relaxation of Conditional Independence Assumption for Image Segmentation Authors: Zixun Wang, Ben Dai Published: 2026-09-30 Categories: cs.CV, cs.AI, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2609.38930v1 In semantic segmentation, a recent line of RankSEG methods directly optimizes Dice/IoU scores at inference time, improving alignment with evaluation metrics without modifying model training. Despite its theoretical and empirical success, RankSEG relies on the restrictive Conditional Independence Assumption (CIA), which ignores crucial label correlations and therefore degrades performance in ambiguous or low-contrast scenarios. However, accounting for full label dependence is computationally prohibitive, requiring $\mathcal{O}(d^3)$ time. To address this, we replace the CIA with a Spatially Localized Dependence (SLD) structure that captures local label correlations while keeping the dependence model tractable. We further overcome the remaining computational bottleneck via a Reciprocal Moment Approximation coupled with a novel fixed-point optimization strategy that eliminates exhaustive search. The proposed algorithm achieves a highly practical $\mathcal{O}(d \log d)$ complexity and consistently outperforms conventional argmax and CIA-based RankSEG across diverse segmentation benchmarks. Improvements are significant in low-contrast or small-object scenarios, where label dependence offers valuable signals complementary to image information for accurate segmentation. The code of experiments is available at https://github.com/ZixunWang/RankSEG-DEP. --- ### Learning What to Forget: Distributional Unlearning for LLM Representation Spaces Authors: Pinaki Mohanty, Haoran Tang, Maggie Makar, Rajiv Khanna Published: 2026-09-30 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.38929v1 Machine learning systems increasingly face the need to remove the influence of entire data domains, such as toxic language, harmful behavior, or topical content, rather than isolated records. Recent work formalizes this problem as \emph{distributional unlearning}: selecting a subset of a forget domain whose removal moves the training distribution away from an unwanted population while preserving proximity to the desired one. However, existing analyses often impose parametric assumptions to obtain tractable selection rules. These assumptions may be poorly suited to high-dimensional language-model representations. We introduce \textsc{Mamushi}, a framework for non-parametric distributional unlearning that ranks forget examples using a probabilistic classifier whose Bayes-optimal logit equals the forget-to-retain log-density ratio (up to an additive class-prior constant). We show that thresholding the population log-density ratio yields the optimal fixed-budget selection rule for our removal--preservation objective and establish a non-asymptotic transfer guarantee relating score-estimation and threshold-calibration errors to degradation from the population-optimal selection rule. Our empirical evaluation spans real-world datasets on toxic-language removal and topical-domain removal regimes using different representations, with \textsc{Mamushi} achieving a more favorable removal--preservation trade-off than other baselines. Our work shows that \textsc{Mamushi} can serve as an efficient selection approach for downstream machine unlearning procedures, reducing the number of forget examples required to reach a fixed forgetting target. --- ### World-as-Graph: Relational World Modeling Through Latent Space Graphs Authors: Yaqi Yang, Shuo Huang, Yujin Huang, Fucai Ke, Jiatong Han, Xin Zheng Published: 2026-09-30 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2609.38927v1 World models aim to learn representations of real-world environments and predict their future evolution. Recent object-centric world models have made expressive progress by representing visual scenes as sets of object-level latent states, but object-object relations are often captured only implicitly, which limits explicit relational and temporal structure modeling and object-centric dynamic memory modeling. To address such challenges, we propose World-As-Graph (WAG), a graph-based object-centric world model that introduces relational inductive bias into JEPA-style predictive representation learning. The proposed WAG contains two main modules: (1) Relation-aware structure induction, which constructs time-varying latent graphs from object-centric slots and designs relation-aware object masking policies to guide relational object representation learning in latent space; (2) Object-centric memory transition, which maintains and updates object-level dynamic states by combining relational information from neighboring objects with historical memory, enabling effective autoregressive future prediction. Extensive experiments on both visual reasoning and robotic manipulation tasks could demonstrate the superior performance of our proposed WAG. --- ### PrecipJEPA: JEPA-Regularized Future-State Prediction with Motion-Source Rendering for Precipitation Nowcasting Authors: Yufeng Zhu, Dan Niu, Qiliang Wu, Weiwei Huang, Yixiao Liang, Yongchao Feng, Chunlei Shi Published: 2026-09-30 Categories: cs.MM, cs.LG arXiv: https://arxiv.org/abs/2609.38926v1 Long-term precipitation nowcasting requires modeling radar-echo evolution while preserving localized high-intensity structures. Recent radar-specific studies motivate location-aware prediction and separating echo displacement from intensity change. However existing encoders learn historical representations mainly from final forecast errors. We propose PrecipJEPA, which couples a structured forecasting path with an auxiliary path that enriches its encoder from observed radar history. In the forecasting path, an online encoder first converts the observations into spatiotemporal tokens. The Task-Driven Future-State Predictor (TFP) combines these tokens with a recent-dynamics summary and spatiotemporal queries to construct future radar states. The Parallel Motion-Source Renderer (PMSR) decodes these states into motion and source-sink fields that transform the latest observation into future frames. During joint training, the History-Masked JEPA (H-JEPA) operates on the auxiliary path to predict masked historical features from visible context, directly supervising the same online encoder from the observed sequence. Experiments on SEVIR and MeteoNet show that PrecipJEPA improves highest-threshold CSI by 118.6% and 35.1%, respectively, over the strongest baselines, while maintaining the highest mean CSI throughout the 3-hour forecast. --- ### Prototype-guided Bilateral Alignment Multimodal Federated Learning Authors: Tianchi Liao Tianchi_Liao, Lele Fu, Sheng Huang, Qing Hu, Hong-Ning Dai, Chuan Chen Published: 2026-09-30 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.38925v1 Multimodal federated learning (MFL) has emerged as a pivotal paradigm for leveraging distributed data to enhance model performance. However, existing methods predominantly rely on idealized assumptions of model homogeneity and balanced modality distributions, rendering them ill-suited for practical scenarios characterized by heterogeneous client architectures and severe modality imbalance. To address these challenges, we propose a \textbf{M}ultimodal \textbf{Fed}erated learning Prototype-guided Bilateral Alignment (MFedPBA) framework. MFedPBA facilitates robust knowledge synergy through a dual alignment mechanism: (i) at the feature level, it aligns heterogeneous feature spaces via a projection encoder optimized by contrastive learning and the Gromov-Wasserstein distance; (ii) at the decision level, it employs an entropy-weighted aggregation of naturally aligned logit prototypes. This novel design achieves robust MFL by jointly tackling heterogeneous feature spaces and collectively aggregating decisions. Extensive experiments demonstrate that our method significantly outperforms state-of-the-art baselines under conditions of model heterogeneity and modality imbalance. --- ### From Image Interpretation to Clinical Reasoning: Upstream Physician-Context-Aware Multimodal Learning with Causal Reinforcement Learning Authors: Jialu Pi, Yanan Ma, Weijie Chen, Owen Crystal, Shubham Trivedi, Stephen Xie, Anna Silverman, Matthew Stib, Chadi Ayoub, Reza Arsanjani, Imon Banerjee Published: 2026-09-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.38924v1 Major adverse cardiovascular events (MACE) remain the leading cause of mortality worldwide. Opportunistic screening using routinely acquired clinical data offers a scalable approach for identifying high-risk individuals before acute events occur. Although chest X-rays (CXRs) capture latent cardiovascular biomarkers and clinical histories provide complementary patient context, existing medical vision-language models are primarily optimized for radiology interpretation rather than prognostic reasoning. We propose a causal reinforcement learning framework for multimodal clinical reasoning that integrates CXRs and physician-authored clinical histories for opportunistic MACE prediction. The framework introduces (1) a role-decoupled dual-LLM architecture that separates reasoning from risk prediction, (2) a dual-action causal reinforcement learning policy for evidence selection and reasoning optimization, and (3) causal token pruning to learn compact multimodal representations. Evaluated on an internal cohort, an emergency department cohort, and the external MIMIC dataset, the proposed framework consistently outperformed unimodal baselines and state-of-the-art medical vision-language models, achieving AUROCs of 0.720, 0.760, and 0.845, respectively. It also substantially improved reasoning quality, achieving higher GREEN scores and higher expert preference while maintaining robust predictive performance across diverse patient populations. --- ### GraphForge: Training Working Agents with Graph-Anchored Workspace Synthesis Authors: Qisheng Su, Hanchen Wang, Guanru Zhu, Huicheng Jiang, Qiuyinzhe Zhang, Kou Shi, Zhen Fang, Ziao Zhang, Qingnan Ren, Zehui Chen, Tao Gui, Feng Zhao Published: 2026-09-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.38923v1 Working agents need to read diverse files, coordinate tools, and produce deliverables. Training such agents requires tasks built on many real files with verifiable results, but few pipelines exist to synthesize this kind of data. Existing pipelines either generate files with models, which lack realism and diversity, or build tasks on real files without task-specific verifiers, leaving result quality unchecked. We introduce GraphForge, an evidence-graph based framework that grounds both the task and its verification in real files. Starting from occupation-grounded seeds for controlled diversity, GraphForge assembles a workspace of real files for each seed and builds an evidence graph over their relations. Since the task statement and rubrics are both derived from this graph, task requirements are backed by the workspace files and each criterion is anchored to the files needed to verify it. An initial rollout further tests executability, and a revision agent repairs the task and rubrics against the original files before trajectories are collected. Fine-tuning Qwen3.6-27B on 2,169 GraphForge trajectories brings GDPVal to 1445.7 (+65.7) under OpenHands, and Workspace-Bench-Lite and SpreadsheetBench II to 63.7 (+7.7) and 24.0 (+13.7) under Claude Code. Rejection fine-tuning on the SFT model's own rollouts, with candidates selected by the evidence-anchored rubrics, yields further improvements on all three benchmarks, suggesting that the rubrics provide a useful selection signal. The data and models are available. --- ### Learning Where to Steer: Noise-Space Geometry for Efficient Offline Multi-Objective Optimization with Generative Models Authors: Yuan Lu, Esha Singh, Yi-An Ma, Yusu Wang Published: 2026-09-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.38920v1 Offline multi-objective optimization (MOO) seeks solutions with better objective trade-offs using only a fixed dataset, without querying the objectives. Diffusion models trained on such data have emerged as a promising approach, but their samples are not inherently better than the data and must be steered toward the Pareto front. Existing methods guide or condition every sampling step. We instead act on the initial noise and leave the sampling process unchanged. Across Off-MOO-Bench, we observe that the objectives, as functions of the noise, are sensitive to only a few directions. We estimate these directions once per task via a Recursive Feature Machine using function values alone, and a small cache serves every trade-off, so each candidate costs one noise displacement and one ODE solve. We prove that this displacement increases the learned scalarized objective in expectation, and that sweeping trade-offs recovers the flow's attainable front up to proxy and steering errors. With additional guidance, for which we introduce novel data-adaptive and Pareto-aware operators, our method attains the best average hypervolume rank among generative methods on 47 tasks, at comparable or lower sampling cost. Steering alone outranks the best prior generative method at a fraction of its sampling cost. --- ### Flow Matching under Noisy Latent Structure: Beyond Exact Low-Dimensional Support Authors: Lifeng Hao, Shaolin Ji Published: 2026-09-30 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2609.38918v1 Flow Matching (FM) learns a velocity field whose ODE transports a simple source distribution to a target law. Existing finite-sample theory largely treats ambient-space regularity or data supported exactly on low-dimensional sets. We study linear FM under a noisy latent-generator model, where a low-dimensional Hölder map is perturbed by nondegenerate ambient Gaussian noise, so the target law is full-dimensional despite its latent structure. We construct a spatially regular ReLU velocity class and establish non-asymptotic high-probability approximation and estimation bounds whose leading sample-size exponent is governed by the latent dimension rather than the ambient dimension, with ambient and noise dependence kept explicit. Fixed positive target noise keeps the interpolation nondegenerate over the full time interval. The same spatial regularity propagates the learned velocity error through the transport ODE, yielding a corresponding Wasserstein convergence guarantee. These results show that exact low-dimensional support is not necessary for Flow Matching to retain latent-dimensional statistical behavior. --- ### How Much Can Reliability Drift Under a Fixed Confidence Distribution? Authors: Wenhao Liang, Lin Yue, Wei Emma Zhang, Mingyu Guo, Olaf Maennel, Weitong Chen Published: 2026-09-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.38917v1 A classifier's conditional accuracy can change while its confidence distribution stays exactly the same. We study the worst-case movement of the reliability relation under covariate shifts that preserve the distribution of the confidence score, constraining the reweighting within each confidence level by a $χ^2$ budget; the resulting worst case, as a function of the budget, is a fragility profile. On an interval of budgets that can be computed from the source distribution, the profile equals exactly the square root of the budget times the within-level variance of the correctness propensity -- the grouping-loss term of calibration-refinement decompositions. Beyond this interval the profile is governed by the tails of the propensity law, and the entire upward profile determines the centred within-level law; consequently, calibration residual and grouping variance do not determine fragility in general, though they do when labels and predictions are deterministic. Since the propensity is not observed, we restrict reweightings to a learned finite readout within confidence bins, bound the part the restriction misses by the grouping variance remaining inside readout cells, estimate the restricted profile with role-separated labels, and provide a separate split-sample lower confidence bound. On ImageNet this bound is positive in both splits for four of six primary classifiers and nine of twelve additional ones as released, and for three of eighteen after temperature scaling. Held-out drift under optimised reweightings fitted without evaluation labels tracks the estimated profile; an exploratory label-permutation diagnostic yields near-zero agreement for this statistic while largely reproducing the correlation observed for unsigned random reweightings. --- ### Warm-starting PDE solvers with any-dimensional machine learning Authors: Wilson G. Gregory, George A. Kevrekidis, Ben Blum-Smith, Soledad Villar Published: 2026-09-30 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2609.38916v1 Any-dimensional machine learning models, such as graph neural networks (GNNs), can be naturally trained and evaluated on inputs of different sizes and dimensions. Inspired by the GNN transferability literature, we show mathematical conditions under which a partial differential equation (PDE) learning-based solver can be trained in small dimensions and directly applied to solve a higher dimensional PDE in a zero-shot fashion. These conditions are based on symmetries in both the partial differential equation and the initial data. When the equations satisfy the symmetries but the data does not, which is the case for many PDEs arising from physics, we show that our theory gives a principled way of warm-starting low-dimensional PDE solvers for higher dimensional PDEs. We apply this method on the heat equation, Burgers' equation, and the compressible Navier--Stokes equations, improving the performance in both zero-shot and typical training regimes on high dimensional data. For example, we train a surrogate model on 2D Navier--Stokes data and achieve better results on 3D test data than a baseline surrogate model trained on 3D data, while only using 12$\%$ of the flops and 20$\%$ of the total data size. --- ### Risk-Aware Adaptive Evaluation: Finding High-Impact Failures Under Limited Budgets Authors: Priyanath Maji, Spandan Ghose Chowdhury Published: 2026-09-30 Categories: cs.AI, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2609.38914v1 Evaluating interactive agents is expensive. Agent behavior is stochastic, so reliability must be measured over repeated trials, but failures are rare and differ widely in how much they matter. Standard benchmarks spend this budget uniformly: a read-only lookup is sampled as often as an irreversible payment action. We instead formulate evaluation as a sequential allocation problem. Given a fixed trial budget and a set of scenarios whose failure behavior is unknown, which scenarios should be run, and run again? We propose a risk-aware contextual Thompson Sampling policy that combines a pre-execution scenario context vector and a fixed impact score with the failure outcomes observed during evaluation, and we test it by offline replay over 70 $τ$-bench airline scenarios and 824 recorded trials. Our main result is at the smallest budget: with only 50 trials ($6\%$ of the corpus), the policy recovers $86\%$ of the impact-weighted failures an oracle could find, compared to $25\%$ for uniform allocation. It discovers $3.5\times$ more impact-weighted failures (215.4 vs. 62.2) with the same number of trials, delivers $5\times$ the discovery per dollar, and cuts the budget wasted on scenarios that never fail from $34\%$ to $2.8\%$. The rest of our analysis demonstrates and qualifies this result: a budget sweep shows the advantage shrinks as the budget approaches the corpus size, and paired significance tests show that scenario context helps mainly at small budgets while posterior-based exploration helps at moderate ones. Risk-aware adaptive allocation therefore helps most exactly where evaluation budget is scarcest. --- ### FLOW: Feature-Level Optimal Warping for Generalized Remote Physiological Measurement Authors: Bo Zhao, Junzhe Cao, Dan Guo, Dongmin Huang, Wenjin Wang, Tao Tan, Yue Sun, Zitong YU Published: 2026-09-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.38913v1 Remote photoplethysmography (rPPG) enables non-contact physiological measurement but remains vulnerable to domain shifts from illumination, motion, and sensors. We propose \textbf{FLOW (Feature-Level Optimal Warping)}, an \emph{optimal transport--driven} framework for domain-generalized rPPG. FLOW integrates a \textbf{Temporal Refinement Module (TRM)} to stabilize temporal dynamics and a \textbf{Prototype-based Cross-Temporal Optimal Transport (PCOT)} module to achieve domain-invariant alignment via learnable prototypes.Beyond feature alignment, FLOW employs soft cross-temporal correspondence modeling that aligns temporal features in a flexible manner, allowing the model to respect and preserve the intrinsic rhythmic patterns of physiological signals. Moreover, the lightweight design of our modules allows seamless integration into existing end-to-end rPPG architectures without additional preprocessing. Two regularization terms further enforce source consistency and identity preservation. Theoretically, we derive a generalization bound under conditional optimal transport. Extensive experiments across four rPPG benchmarks show that FLOW achieves state-of-the-art cross-domain performance with lightweight design and strong physiological fidelity. --- ### Composing Task-specific Agent Harnesses at Test Time with Reusable Primitives Authors: Peng Kuang, Haibo Jin, Dehao Wu, Feiyang Deng, Xiaopeng Yuan, Jerry Wang, Haohan Wang Published: 2026-09-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.38912v1 Agent harnesses govern how large language models (LLMs) gather context, invoke tools, verify results, preserve state, and terminate, largely affecting agent performance. However, the value of each harness mechanism can differ across heterogeneous tasks: a mechanism that improves one task may impose overhead or context distraction on another, leading to the suboptimality of a global harness. We characterize this suboptimality as a mismatch induced by fixed mechanism choices, motivating task-specific harness construction. Nonetheless, generating harness code for each task introduces generation and debugging costs, with execution risks that can compound as more mechanisms are generated. To address those challenges, we introduce Harness Primitives, reusable harness mechanisms with clear application scope and composition contract mined from failed task trajectories. Based on Harness Primitives, we propose STITCH, a framework that Selects suitable primitives given Task Information and compiles them into Task-speCific Harnesses at test time. This separation enables task-specific harnesses without generating or repairing mechanism code at test time. Extensive experiments demonstrate that STITCH not only improves harness adaptability and robustness, but also scales with the primitive library size, boosting task success rates by up to 12 points over fixed harness baselines, surpassing human-designed harnesses like Codex CLI while maintaining a minimal test-time harness composition overhead of only 2.7%, 638 times more efficient than generating task-specific harnesses from scratch. Ultimately, our work demonstrates that building task-adaptive harnesses can be beneficial for completing diverse tasks and that building reusable primitives can be a promising path towards this goal. --- ### Generalized Residual Closure: General Learning Dynamics for Stability-Plasticity Compatibility Authors: Dongxu Li, Yinuo Zhang, Hongyu Zhang, Feng Tian Published: 2026-09-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.38911v1 Learning must acquire new capabilities while preserving both prior responsibilities and the capacity to learn again. We introduce Generalized Residual Closure (GRC), a framework for learning as recursive closure of future-relevant discrepancies: closing a residual establishes the conditions for subsequent prediction, interaction, and learning. Under a complete representation-relation description at a fixed learner-world boundary, persistent internal learning has two primitive modes: Transformation within a representation and revision of the Representation itself. We establish a local tangent decomposition under regularity assumptions and a criterion for when representation revision is necessary. In an affine model, we derive a necessary-and-sufficient condition for stability-plasticity compatibility and the unique solution of a constrained quadratic update problem, which preserves registered old responsibilities while reducing residuals with an effective safe response. We prove that reconstructive semantic protection weakly enlarges the safe-response operator relative to preserving an exact historical realization. Dynamic sufficiency and future-closure viability extend representation adequacy from current prediction to lawful future updating and continued learning. Growth Learning expands the lawful closure domain or lowers optimal closure cost without regression of the registered capability-cost frontier; a conditional commit rule maintains this order. Restricted-sector recoveries and a conditional representation theorem connect the framework to optimization, machine learning, and control. Together, these results organize adaptation, representation revision, and reusable capability within a common account of continued learning. --- ### Unlearning Deceptive Behaviors in LLMs with Contrastive Forget Sets Authors: Haoran Tang, Rajiv Khanna Published: 2026-09-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.38909v1 Large language models often know the truth and say otherwise: a model that answers correctly when asked neutrally will affirm a user's mistaken belief, or misstate a fact its system prompt wants hidden, once the context rewards it. Such deception is a behavior conditioned on context, not knowledge, yet machine unlearning, the natural tool for removing a behavior from the weights, is built to forget facts that a deceptive model still needs. We propose to unlearn when a model deceives rather than what it knows, with a contrastive forget unit built from the model's own realized deceptions: the same question under a deception-triggering and a neutral context, admitted only where belief holds and behavior flips. Standard objectives on this unit face a dilemma. Suppression objectives such as NPO leave much of the deception in place. Target-based objectives, which distill the model's neutral behavior into the pressured context, remove it but induce context blindness: a target generated without the context teaches the model to stop reading it, eroding benign system-prompt instructions, secret-keeping and the reasoning a monitor inspects, a failure invisible to deception rates and capability benchmarks. We introduce PACT, which trains toward pressure-aware counterfactual targets (the model's own honest response, with a trace that registers the pressure and resists it) while retaining the benign uses of the triggering context. On two 32B reasoning models, PACT reduces held-out deception from over 50% to under 3% while system-prompt adherence, secret-keeping and the reasoning trace stay at the base model's level. On a tug-of-war score of removal against retention, PACT reaches 0.94 and 0.86, against at most 0.77 and 0.60 for any baseline. Like removed knowledge, removed deception is shallow under relearning, and terms that simulate the attacker hold it only at a cost in context use. --- ### CellMSA: Context Modeling for Single-Cell Representation Learning Authors: Suyuan Zhao, Minghao Liu, Yizhen Luo, Zaiqing Nie Published: 2026-09-30 Categories: q-bio.GN, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.38908v1 Single-cell transcriptomics enables profiling of cellular states at unprecedented resolution, but its high dimensionality, sparsity, and technical batch effects pose significant challenges for representation learning. Existing single-cell foundation models typically encode each cell independently or only model cells from the same batch for denoising, thereby underutilizing the rich relational information across batches and cell types to model gene expression patterns. We argue that single-cell models can benefit from more informative cell-context modeling. By comparing consistency and variation across cells, models can capture fine-grained gene-gene dependencies associated with cell states, which are essential for learning high-quality representations. Inspired by the use of multiple sequence alignment (MSA) context in protein modeling, we propose CellMSA, a single-cell representation learning framework that introduces an MSA-inspired inductive bias into transcriptomic modeling. For each target cell, CellMSA retrieves relevant cells from different batches and biologically related cell types as context, and summarizes cross-cell patterns into a context-dependent gene-pair representation. This representation is then injected into a pair-aware target-cell encoder for fine-grained representation learning. We pretrain CellMSA on a large-scale human single-cell corpus of approximately 109 million cell observations, including 65.6 million primary observations. Experiments show that our framework consistently outperforms existing methods across multiple benchmarks. Code is available at the following repository: https://github.com/PharMolix/CellMSA. --- ### Characterizing Questioning Patterns and Student Engagement Through Contextual Analysis of Real-Time Classroom Interactions Authors: Rohit Sharma, Pavani Ayinampudi, Aditya B. M. V., Jinal Gupta, Prakash Hegade, Sakshi Sharma, Meenakshi V, SRS Iyengar Published: 2026-09-30 Categories: cs.HC, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2609.38907v1 Real-time classroom polling is now routine, yet the data it produces is usually read narrowly, as a correctness score or a headcount. Such readings say little about what a poll is doing within a lecture or how it shapes engagement. This is particularly relevant for short-response formats such as True/False, where the same question format can be used to test recall, check comprehension, or direct students' attention to a deliberately misleading statement. This study asks whether a poll's answer and instructional function can be determined by reading it against its lecture transcript, what cognitive levels of Bloom's taxonomy and instructional-function clusters the corpus contains, and how student engagement relates to answering correctly. We analyse a naturalistic corpus of 47 live sessions over 39 days, comprising 604 poll questions and 340,668 responses from 2,807 learners, most items True/False, read against time-aligned lecture transcripts and attendance. Reading each poll in context proves essential: the answer to 89% of polls is locatable in the lecture, and a recurring attention-checking device is visible only through context. Questioning is overwhelmingly lower-order and falls into seven instructional functions, and a poll's response follows its function rather than its wording. Engagement is broad but concentrated, and the class majority answers correctly 88.5% of the time, though a small set of high-consensus yet incorrect answers cannot be detected by agreement alone. An independent survey of 579 students agrees on what the polls are and on their participation, but reveals a gap between perception and reality: students cannot judge their own correctness, and the polls they find hardest are not those they answer worst. --- ### DAMPER: Return-Prioritized Gradient Control for Smooth Policies Authors: Seokmin Ko, Taewon Goo, Kihyuk Hong Published: 2026-09-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.38903v1 Actor-critic methods achieve strong performance in continuous control, but their policies can produce highly oscillatory actions. A common remedy is to add auxiliary smoothness losses. However, their contribution can be negligible when their gradients are small relative to the native actor gradient. Moreover, existing methods often combine multiple auxiliary losses, complicating loss balancing without necessarily improving the return-smoothness trade-off. We introduce DAMPER (Direction-Aware Magnitude-Controlled Projection with Explicit Return Priority), which combines the native actor gradient with a temporal-consistency gradient through conflict-conditioned projection and adaptive magnitude control. It removes the auxiliary component opposing the actor gradient and scales the retained temporal direction relative to the actor gradient norm, preserving positive alignment with the native actor gradient. Experiments with TD3 and SAC on six continuous-control tasks show reduced action oscillation relative to the native agents in all 12 task-backbone pairs and the best oscillation score among the compared methods in eight, with task-dependent return trade-offs. --- ### Amortized Data Borrowing with Exchangeability-Aware Neural Posterior Estimation Authors: Chin-Hung Huang, JooChul Lee, Huan He Published: 2026-09-30 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2609.38902v1 Augmenting small concurrent studies with external or historical cohorts is attractive in drug development, where enrollment is slow, follow-up is expensive, and closely related trial or real-world data are often already available. Bayesian dynamic borrowing (BDB) provides a principled framework for adaptively controlling the influence of external data, but classical implementations often depend on hand-specified priors and MCMC-based inference, which can be computationally expensive and not generalizable. In this work, we study amortized neural posterior estimation (NPE) as a flexible alternative. A single network is pretrained on simulated current/external dataset pairs spanning covariate shift, outcome drift, and joint non-exchangeability, and then returns an approximate posterior for a scalar current-study target in a single forward pass. Through simulation studies, we find that NPE is most useful under outcome drift and joint mismatch: in the harder outcome-drift regimes, it gives up to about five-fold lower absolute bias than the best classical baseline and keeps Type I error close to nominal. After pretraining, posterior summaries are obtained in about 8 ms per dataset, roughly $10^3\times$ faster than MCMC-based borrowing baselines in our timing experiment. We further analyze Alzheimer's Disease Neuroimaging Initiative (ADNI) data and show that, when mild cognitive impairment outcomes differ across cohorts, the NPE formulation recovers the later-cohort risk level in this example without claiming greater precision. Code is available at https://github.com/ChinHungScott/NPE-for-Bayesian-Dynamic-Borrowing-MLHC-. --- ### Certified Approximation for Interpretable Representer Landmarks Authors: Jayanta Mukherjee, Shourya Verma, Mengbo Wang, Jasorsi Ghosh, Ananth Grama Published: 2026-09-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.38901v1 Representer explanations rank the training landmarks that most influence a self-supervised representation. At scale, this ranking rests on up to four stacked approximations of the empirical neural tangent kernel (eNTK). These are random output heads, a parameter sketch, landmark sampling and a coefficient fit. Existing analyses bound each approximation separately, but none certifies the top-$K$ set against their combined error. We introduce CAIRN (Certified Approximation for Interpretable Representer laNdmarks), a framework that carries this error through to the ranking. We derive the exact variance of the sketched multi-head eNTK, which matches measurement within $4\%$ where Johnson-Lindenstrauss bounds err by up to $2.5\times$. This yields a high-probability top-$K$ certificate for a fixed coefficient fit, alongside exact residual-trace certificates for discarded spectral mass. An exact product-variance identity separates kernel error from fit variability and identifies when a larger kernel budget can still sharpen a ranking. Stochastic Lanczos Quadrature (SLQ) estimates the effective dimension within $0.72\%$ and guides the landmark budget without dense eigendecomposition. We show that residual mass does not control class coverage, and residual-greedy selection cuts the worst coverage excess of $k$-means++ from $8.5\times$ to $1.55\times$ ($4\times$ on the sketched eNTK). Cross-view initializers outperform principal-component initialization in five (AUI) to all six (CSI) settings. Against the KREPES Gauss-Newton solver, CAIRN converges $2.5$ to $11.3\times$ faster, trails by at most $0.31$ points and gains up to $3.14$ points on MNIST. Together, these results make the reliability of representer explanations measurable and show where approximation budgets are best spent. --- ### MEMO: Multi-Level Entity-Aware Memory for Streaming Video Understanding Authors: Yinying Li, Yuqian Fu, Yulin Dai, Jingyu Gong, Tianwen Qian, Xiaoling Wang Published: 2026-09-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.38900v1 Streaming video understanding requires models to process unbounded visual streams while preserving rich visual semantics across vast temporal horizons, posing a fundamental challenge for memory modeling. Existing approaches primarily focus on increasing memory capacity, either by compressing historical information into fixed-size representations or by extending storage beyond GPU memory. However, these methods largely rely on global or coarse-grained representations, inevitably losing fine-grained visual information. In this work, we argue that streaming video memory should explicitly encode structured and semantically meaningful representations, particularly at the entity level. To this end, we propose MEMO, a novel framework that models streaming video through multi-level, entity-aware structured memory. MEMO performs multi-level perception to jointly capture global semantics, entity dynamics, and spatial structures, partitioning streaming video into semantically coherent chunks. Each chunk is organized into a structured memory, where lightweight global and entity-level representations serve as retrieval indices, while the corresponding high-resolution visual content is retained separately for on-demand access. At inference time, MEMO performs query-specific retrieval over the structured memory and selectively recalls relevant visual evidence for downstream reasoning. Notably, MEMO is training-free and plug-and-play with existing multimodal large language models. Extensive experiments on StreamingBench and OVO-Bench demonstrate that MEMO consistently improves multiple base models and achieves state-of-the-art performance. --- ### SceneJail: Exploiting Video Scenario Context to Jailbreak Multimodal LLMs Authors: Wenyu Chen, Li Wang, Chuanchao Zang, Xiangtao Meng, Xinyu Gao, Jianing Wang, Zheng Li, Shanqing Guo Published: 2026-09-30 Categories: cs.CR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.38899v1 Video Multimodal Large Language Models (Video-MLLMs) support reasoning over video inputs, yet remain vulnerable to jailbreak attacks that elicit policy-violating responses. Existing video jailbreaks primarily manipulate how harmful queries are visually presented, thereby treating video merely as a carrier. Consequently, the surrounding video scenario remains unexplored as a contextual attack surface. In this paper, we show that the same harmful query can elicit different safety responses when placed in different video scenarios. To systematically exploit this vulnerability, we propose SceneJail, an adaptive black-box jailbreak framework with two coordinated components. Adaptive Scenario Construction dynamically searches for a surrounding scenario that is contextually compatible with the harmful query. Scenario-aware Prompt Search uses black-box response feedback to search for textual guidance tailored to the selected scenario. Extensive evaluations on the HADES and SafeBench datasets across eight Video-MLLMs, including two proprietary models, GPT-4.1 and Gemini3.5-Flash, demonstrate the effectiveness of SceneJail. SceneJail-F, which presents the complete query persistently, achieves average attack success rates (ASR) up to 91.5%, outperforming the strongest baselines by 29.1 percentage points. Furthermore, SceneJail-S, which distributes the query across successive frames, remains highly robust against current defenses, retaining a 72.3% ASR even under strict image filtering. --- ### K2P: Label-Free Knowledge to Prompt Distillation Authors: Yingchuan Zhang, Haoran Lu, Wenxuan Zhong, Ping Ma Published: 2026-09-30 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2609.38898v1 Knowledge distillation can transfer reasoning from stronger teachers to frozen students through reusable prompts, but avoiding weight updates does not eliminate supervision. Without ground-truth answers, teacher solutions are unverified, and agreement with the teacher can reward shared mistakes. We introduce Knowledge-to-Prompt (K2P) for label-free knowledge distillation to prompts. K2P synthesizes reusable instructions from teacher solutions, refines them using paired teacher and student responses, and guides search and selection with answer agreement. It retains candidates that adaptive search may undervalue and selects on reserved questions. Deployment uses only the frozen student and selected prompt. Our theory separates generation and selection gaps and gives conditions under which agreement-guided construction yields accuracy guarantees despite imperfect teacher references. Across reasoning tasks and students, K2P outperforms label-free alternatives overall and remains competitive with supervised prompt optimization. Ablations and archive diagnostics assess the contributions of teacher solutions and refinement, while revealing the limits of agreement-guided selection. --- ### FFASR: Benchmarking Far-Field Automatic Speech Recognition using High-Fidelity Simulated RIRs Authors: Shivam Saini, Eric Bezzam, Georg Götz, Alessia Milo, Steinar Guðjónsson, Konstantinos Gkanos, Finnur Pind, Daniel Gert Nielsen Published: 2026-09-30 Categories: cs.SD, cs.AI, cs.PF arXiv: https://arxiv.org/abs/2609.38897v1 Far-field automatic speech recognition(ASR) degrades under reverberation, noise, and talker motion, yet the benchmarks that drive model selection emphasize close-microphone speech. We present FFASR, a held-out corpus of 15,637 utterances and an open leaderboard spanning nine conditions, each varying a single acoustic factor: anechoic near-field speech, a measured-versus-simulated office-lab pair, static far-field mixtures at high/mid/low signal-to-noise ratio(SNR), and moving-talker variants at matched SNR. Dry speech from 15 talkers is convolved with hybrid wave/geometrical-acoustics room impulse responses from 14 furnished rooms; because the speech is newly recorded and the test waveforms are never released, the corpus resists training-data contamination. Across contemporary systems, mean word error rate (WER) rises from 4.4% near-field to 41.3% in the static low-SNR condition; a moving talker adds a small but consistent penalty at matched SNR; and on the office-lab pair, measured and simulated WER agree to within about 1.7 pp on average. These results support high-fidelity simulation as a scalable proxy for measured far-field evaluation under the conditions we test. --- ### Unmerge: Efficient Machine Unlearning via Task Arithmetic Authors: Haoran Tang, Andrew Tan, Rajiv Khanna Published: 2026-09-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.38895v1 Approximate machine unlearning seeks to remove the influence of a forget set from a trained model without full retraining. Existing gradient-based methods require data-dependent hyperparameter search, struggle when forget and retain knowledge are entangled, and offer little insight into where unlearning actually happens inside the network. We recast unlearning through the lens of task arithmetic: if finetuning produces a merged task vector $τ_m$ that combines learning on forget and retain sets, unlearning is the inverse operation that subtracts a learned forget component $τ_F$ to recover the retain task vector $τ_R$. The forget signal is concentrated: at every layer, forget activations lie in a subspace spanned by a handful of dominant directions, so we factorize $τ_F$ in a low-rank forget basis, which is faithful up to a small tail-eigenvalue residual and limits how far the correction can perturb retain. We then optimize three intuitive goals (match the merged vector inside the forget span, suppress leakage into the retain span, and bound the correction size) that provably bound forget leakage and retain damage in activation space. The resulting algorithm, Unmerge, is fast and powerful: on class-level unlearning with ResNet-50 on CIFAR-100 and Tiny ImageNet, it improves Tug-of-War by up to ~24% over a baseline of comparable runtime and by up to ~18% over stronger baselines that run ~5x slower, keeps membership-inference exposure at the level of retraining, and shrinks the feature-distribution gap to the retrained model, where relabeling methods leave forget features cleanly separable. Further studies show that Unmerge also applies to ViT-S/16 and scales to Llama-3.2-3B. The per-layer basis geometry that drives the algorithm also serves as a layerwise diagnostic for when and where unlearning becomes structurally hard. --- ### Learning Continuous Neural Representation of Stochastic Hybrid Systems Authors: Sangli Teng, Hang Liu, Koushil Sreenath Published: 2026-09-30 Categories: cs.LG, cs.AI, eess.SY arXiv: https://arxiv.org/abs/2609.38893v1 A stochastic hybrid system (SHS) is governed by a stochastic differential equation (SDE) describing the continuous dynamics and a Markov reset kernel triggered on the guard surface. Its probability evolution can be described by a hybrid Fokker-Planck (HFP) equation with a partial differential term corresponding to the SDE and an integral term arising from the reset kernel. This work shows that such an SHS can be approximated by an SDE in a higher-dimensional latent space where the sample paths are continuous. The key to this result is to encode different branches of the reset kernel using auxiliary variables, transforming the resets into deterministic ones that enable topological gluing. By the embedding theorem, the glued manifold can then be embedded into a higher-dimensional Euclidean space. We show that the probability evolution on the embedded image no longer requires explicit reset terms in the HFP equation. Building on this theorem, we design a loss that matches the evolving state distributions, enabling a single latent SDE to recover the probability evolution of the SHS without mode labeling, trajectory segmentation, or event-based simulations. --- ### Consistent Plan-Act for Long-Horizon Agentic Tasks Authors: Heng-Zhuang Li, Yi-Kai Zhang, Yu Wang, Yueqing Sun, Jiayuan Zhang, Qi Gu, Han-Jia Ye Published: 2026-09-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.38891v1 Long-horizon agentic tasks demand strong reasoning and efficient execution across successive interactions with dynamic environments. A common approach decouples high-level planning from low-level execution through separate planner and actor roles. To investigate coordination failures in these tasks, we prompt both agents for structured state assertions and compare their reports programmatically to detect explicit contradictions. Our analyses reveal systematic disagreement about the same task-relevant state facts, a phenomenon we term planner-actor state mismatch. We further find that providing agents with task-relevant state information reduces mismatch and improves coordination and task performance. Based on the systematic analysis of the state mismatch, we propose Consistent Plan-Act (ConPAct), which feeds detected contradictions back to both agents to form consistent state interpretations and fine-tunes them on curated consistent interactions for better coordination. ConPAct improves performance across various environments and model configurations, e.g., increasing MiniGrid success rate from 38.6% to 54.4% with GPT-5.6-sol/terra as planner and actor respectively, demonstrating that state consistency can guide both inference-time correction and coordination training. --- ### VERA: Verifiable Feasibility Representations with Counterfactual Credit for Constrained Multi-Agent Control Authors: Bo Yin, Dongbo Li, Hongkai Chen, Jie Liu, Guoliang Xing Published: 2026-09-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.38889v1 Constrained multi-agent control requires more than predicting rewarding actions: an action can cease to be executable as contact windows, shared capacity, and deadlines change. We introduce VERA, a centralized-training, decentralized-execution framework that separates feasibility estimation from credit assignment. Each actor predicts a five-dimensional verifiable feasibility representation (VFR). After an action is proposed, exact action-conditioned margins available only during training supervise that representation, while a counterfactual group-relative advantage (CGRA) ranks candidate representation-action pairs. Execution uses one actor pass and no privileged state. In a dynamic space-air-ground integrated network (SAGIN), VERA obtains 55.33% +/- 3.60% success with 0.45% +/- 0.81% coverage violation, within 1.33 percentage points of a privileged-mask reference. With rewards matched over ten paired seeds, VERA improves success over the strongest baseline by 8.74 percentage points (p=0.023) and reduces violation by 52.19 percentage points (p=5.7e-8). A ten-seed 4-by-2 factorial attributes a 14.16-16.48 percentage-point gain to CGRA across handcrafted, learned, random, and latent representations; evaluation on seven unseen topologies preserves a 24.33-30.02 percentage-point advantage over multi-agent proximal policy optimization. From 10 to 40 users, success remains 50.1-53.8%, and VFR adds only 0.026 ms to a central processing unit (CPU) actor step. Cross-domain tests further identify the governing condition: counterfactual credit succeeds when candidate scores respect shared constraints and fails under incompatible reward geometries. These results establish action-conditioned feasibility as an auditable training interface and counterfactual credit as a geometry-dependent optimization mechanism. --- ### VOSSA: Voiceprint Optimization for Streaming Speech Architectures Authors: Mu-Ruei Tseng, Waris Quamer, Ghady Nasrallah, Ricardo Gutierrez-Osuna Published: 2026-09-30 Categories: eess.AS, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2609.38887v1 Real-time voice conversion (VC) systems commonly rely on pretrained speaker embeddings from automatic speaker verification (ASV) models. While effective for speaker discrimination, these embeddings are trained to remain stable across phonetic and prosodic variations within-speaker, which may conflict with frame-level acoustic generation in streaming constraints. To address this issue, we propose VOSSA (Voiceprint Optimization for Streaming Speech Architectures), a speaker representation framework that extracts speaker information from intermediate content encoder layers and aggregates using attentive statistics pooling. The embedding is trained jointly with VC objectives, removing the need for a separate speaker encoder. Across six datasets, VOSSA improves F0 dynamics and vowel-discriminative acoustic cues while maintaining comparable NISQA-MOS, WER, and speaker similarity. Perceptual tests further indicate improvements in naturalness, speaker similarity, intelligibility, and vibrancy. --- ### Right Answers, Costly Models: The Efficiency Gap in LLM-based Optimization Modeling Authors: Zhong Li, Xin Huang, Jinhui Wan, Xiangyi Wang, Shenkai Zhang, Ruiqi Chen, Wenyu Liu, Zaiwen Wen, Ziyan Luo Published: 2026-09-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.38884v1 Optimization modeling formulates real-world decision problems as mathematical programs that solvers can use to find optimal decisions. Large language models (LLMs) can automate this process, but the resulting correct formulations can require substantial time and memory to construct and solve, limiting practical scalability. Therefore, we systematically investigate whether LLMs can identify problem structure from natural-language descriptions and apply suitable optimization modeling techniques to generate mathematical models and solver code that solve the problems correctly and efficiently. To this end, we first curate OptTips, a knowledge base of 50 expert modeling techniques in eight families. Using this knowledge, we develop OptDachshund, a multi-agent framework that transforms problems from existing optimization benchmarks into new tasks for evaluating LLMs' use of modeling techniques. It constructs conventional and expert mathematical models with solver code for the same task and data, providing baselines for correctness and computational cost. The resulting EfficientOpt benchmark contains 561 expert-reviewed tasks with paired reference implementations. Evaluation of 11 representative LLMs reveals an efficiency gap on correctly solved tasks with comparable measurements: for every LLM, most generated programs take longer to solve than their expert counterparts. Within the comparable reference-size subset, 57\% of programs with correct objective values and fewer variables and linear constraints have longer recorded solver times. Case studies show that different modeling techniques can achieve the same optimal value at similar recorded cost. Faster solving may not reduce execution time if the code takes longer to prepare data and build the model. LLM optimization modeling should therefore be evaluated for both correctness and computational efficiency. --- ### STRATA: Self-Learning Through Role-Aligned Tiered Agents for Real-Time Strategy Games Authors: Xinhe Tian, Xiaoyue Zhang, Ziyou Zhang, Jiacheng Li, Xiaoqiang Jin, Qianchuan Zhao, Gaochen Cui Published: 2026-09-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.38881v1 Real-time strategy (RTS) games require agents to coordinate economic development, production and construction, base defense, unit organization, and attack timing over long matches. Existing studies have applied large language models to command decision-making in RTS games, enabling agents to read textual game states and generate high-level plans. However, long inference latency can cause them to miss critical tactical events. The complexity and tactical diversity of full RTS matches also leave existing systems heavily dependent on manually written experience-based prompts, with limited ability to learn continuously from past games. We present STRATA, a role-aligned hierarchical system with cross-game self-learning for Red Alert. STRATA assigns in-game strategic, logistical, and tactical decisions to a Strategic Agent (SA), Logistics Agent (LA), and Tactical Agent (TA), respectively. The SA generates high-level directives based on the global game state and relevant experience cards, while the LA and TA handle logistics and tactical execution. After each match, a Review Agent (RA) derives candidate experience from game traces, validates and revises it using evidence from subsequent matches, and compresses strategic experience supported across multiple games into concise experience cards for SA retrieval. We evaluate STRATA through the formation of experience cards, full-match comparisons before and after learning, and experience learning against AI opponents with different play styles. Under a fixed scenario, using the learned experience cards increases the observed win rate from 30% to 100%. Sequential learning against AI opponents with different play styles also produces distinct long-term strategic experience. --- ### Sharp Statistical Rates for Asynchronous TD Learning with Markovian Data Authors: Yang Peng Published: 2026-09-30 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2609.38880v1 We study the last iterate of standard tabular temporal-difference (TD) learning from a single trajectory of a finite Markov reward process. For discount factor $γ$, write $H=(1-γ)^{-1}$, and let $μ_{\min}$ and $t_{\operatorname{mix}}$ denote the minimum stationary probability and total-variation mixing time. We prove that last-iterate TD achieves sup-norm error at most $\varepsilon$ with high probability using$\widetilde O\left( \frac{H^3}{μ_{\min}\varepsilon^2} +\frac{t_{\operatorname{mix}}}{μ_{\min}} \right)$ transitions, for $0<\varepsilon\leq1$. This rate holds both for a constant step size selected for the target accuracy and for a decreasing schedule independent of the target accuracy and terminal time. The latter gives a simultaneous guarantee over all times beyond an explicit transient threshold. The statistical term retains the cubic effective-horizon dependence of synchronous TD, and the additive mixing transient has no extra horizon factor. The result allows non-reversible chains, arbitrary initial state distributions, and bounded rewards that may depend on the next state. The proof uses an anchored local Poisson equation in reverse time to control stochastic fluctuations without a mixing-time factor, and a hitting-time compensation identity to bound initialization error. The latter also yields a finer transient in terms of the worst expected reverse hitting time. A bound on the expected cumulative propagation mass extends this argument to decreasing step sizes. A three-state construction with known deterministic rewards gives matching minimax lower bounds for the statistical and mixing terms, up to logarithms, over specified model classes in a slow-mixing parameter regime. --- ### Does Learning Protein Folding Generalize to Broader Reasoning? Authors: Yong Liu, Zhanpeng Shi, Yizhou Dang, Zhongyue Zhang, Xiaoliang Shi, Zhijian Wei, Shuangjia Zheng Published: 2026-09-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.38879v1 Large language models rely heavily on human text, which often conveys surface answers rather than the spatial and structural logic behind them. Protein folding is a natural testbed, because one solved structure yields thousands of exactly checkable spatial and topological statements. We ask: can learning to fold proteins teach general models reusable reasoning capabilities? To answer this, we build FoldingCorpus, a protein-derived question-answer dataset, and Fold2Reason, a recipe that post-trains on it through two complementary signals: discrete structural answers predicted via the model's native language head, and continuous 3D geometry decoded from the same shared representations. On FoldBench, Fold2Reason achieves structure prediction scores 2.7 to 3.5 times those of Qwen3.5-9B. Beyond protein structure prediction, it improves performance on all 10 benchmarks spanning spatial, graph, scientific, and general reasoning, raising macro-average accuracy from 45.09% to 48.33% (+3.23 pp), with positive gains on all 10 benchmarks, while matched controls built from random, synthetic, and shuffled structure yield substantially smaller or negative gains. Our work shows that non-linguistic, structure-dense scientific data can systematically improve broad reasoning in language models, making a solved scientific problem a practical source of post-training supervision. --- ### Audio Token Attention Is Predictable Before the Language Model Runs Authors: Kyoungjun Park, Yunzhe Li, Lili Qiu Published: 2026-09-30 Categories: cs.SD, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2609.38878v1 A large audio language model (LALM) turns a minute of speech into 750-1,500 tokens and prefills every one. Image-token pruning often cuts after the language model's first layers, where image tokens draw little attention. Audio tokens draw much more attention there, and their ranking is still far from final, so audio needs a ranking before the language model runs. Surprisingly, the attention an audio token will receive across the language model is already linearly predictable from its encoder output, before the language model runs. A linear map, fitted in closed form without labels, predicts this all-layer attention ranking at $ρ\geq .69$ on eleven of thirteen LALMs. Our method, Triage, cuts audio tokens by this prediction and, on multiple choice, cuts again at layer 2, correcting the prediction with the attention observed there. Triage sets its compression without labels, under two budgets that limit how far its output may differ from the model's own full-audio output. At the conservative budget, its word error rate and accuracy stay within .04 of full audio. At the aggressive budget, Triage beats every baseline in all twelve transcription cases. On multiple choice, at 2.2-5x compression, it outperforms DART, the strongest baseline on average, by .043 in mean accuracy. Because it cuts before the language model, it raises the audio that fits in Qwen2.5-Omni-3B's context window from 21.8 to about 62 minutes. At its most compressive point, Triage lets one GPU serve 4x as many concurrent 5-minute streams of that model. Project page: https://audio-triage.github.io --- ### On Parameters of Nonlinear Scalar Dynamics from Video: Invariants, Calibration, and Identifiability Authors: Wenjie Wang, Yuanyuan Wang, Zixiang Jiang, Shaoan Xie, Mingming Gong Published: 2026-09-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.38877v1 Physical parameter estimation from video aims to recover the parameters of a known family of governing dynamical equations from pixel observations. Existing identifiability theory for this setting has focused on linear time-invariant (LTI) second-order systems, leaving open what can be identified for nonlinear scalar dynamics. We develop an identifiability theory for nonlinear scalar second-order ODEs, organized by how their velocity dependence interacts with changes of the learned state coordinate. Under a shared non-collapsed state map and explicit same-state velocity-coverage conditions, we show that parameter identifiability depends on the ODE family: some parameters are uniquely identifiable, while in other families only invariant parameter combinations are identifiable or external physical calibration is required. For laws that are at most linear in velocity, compatibility forces affine coordinate alignment, yielding explicit parameter relations, invariants, and calibration conditions. This affine conclusion extends to broader finite velocity-feature families when coordinate curvature can be separated from the declared velocity dependence. For families admitting a squared-velocity term, nonlinear coordinate ambiguity can remain; a law-derived normalization instead enables affine comparison between canonical laws. Experiments on synthetic systems and real pendulum and free-fall videos support the predicted parameter relations, coverage effects, and calibration requirements. --- ### Optimal Allocation and Volume under Surface Authors: Kai Feng, Han Hong, Jessie Li, Wenshi Wei Published: 2026-09-30 Categories: econ.EM, stat.ME, stat.ML arXiv: https://arxiv.org/abs/2609.38875v1 This paper develops a framework for estimation and inference on the volumes of sets that are projections of critical function sets, focusing particularly on the convex body beneath the optimal receiver operating characteristic (ROC) surface. Specifically, we propose a volume calculation method that first uses an Aumann expectation representation and then applies Minkowski mixed volumes. Using this framework, we show that the population volume under the ROC surface (VUS) is proportional to the expectation of a symmetric U-statistic kernel. We then propose a double/debiased machine learning estimator of the VUS, derive its asymptotic properties, and develop an inference procedure. Further applications of this framework include an analysis of the feasible error set across pre-defined groups and a natural generalization of the Gini coefficient for measuring inequality. --- ### Reasoning Externalization for Faithful Large Language Model Narratives of Stock Return Predictions Authors: Sujung Kim, Seung Hwan Cho, Sangjin Park, Young-Min Kim Published: 2026-09-30 Categories: cs.AI, cs.CE arXiv: https://arxiv.org/abs/2609.38869v1 In finance, interpreting machine learning predictions is essential, yet the numerical outputs of explainable AI can be difficult for non-experts to understand. While large language models (LLMs) can translate these outputs into natural language, they may produce errors when inferring numerical changes and feature relations. We propose an LLM narrative framework for cross-sectional stock return prediction that combines temporal Shapley additive explanations (SHAP) evidence with historical regime analogs. Temporal evidence tracks changes in the normalized global SHAP importance of an XGBoost model over six months. Historical analogs are past periods with similar changes in SHAP importance, their model performance and subsequent market returns are provided as comparative context. Using this framework, we conduct a controlled study of progressive reasoning externalization, sequentially providing raw SHAP sequences, deterministic temporal descriptors, and feature relations. Each generated claim is verified against provenance-linked evidence. Across Qwen3, externalizing numerical and relational reasoning improved evidence faithfulness as well as temporal and relational accuracy. Evidence faithfulness increased from 0.696 to 0.996 for Qwen3-32B-Instruct. While historical analogs did not improve structured automatic faithfulness, they received higher human-rated usefulness scores. These results suggest that externalizing verifiable reasoning enhances narrative faithfulness and that historical context adds interpretive value. --- ### Talk2Agent: Benchmarking Voice Interfaces for Text Agents Authors: Terumi Chiba, Guangzhi Sun, Zheqi Yuan, Chao Zhang Published: 2026-09-30 Categories: cs.AI, eess.AS arXiv: https://arxiv.org/abs/2609.38867v1 Large language model (LLM) computer-use agents are typically evaluated with clean written instructions, despite speech being an increasingly popular interface for interacting with such systems. Speech input introduces an additional failure point: transcription errors can alter task-critical entities, constraints, or targets before the agent begins reasoning, while conventional ASR metrics do not directly measure whether the information required for successful execution has been preserved. We introduce Talk2Agent, a benchmark for evaluating how effectively voice interfaces convey human-spoken instructions to LLM-based computer-use agents. Talk2Agent builds human-spoken versions of tasks from WildClawBench and OSWorld and evaluates a range of voice interfaces, including dedicated ASR models, audio-capable LLMs, contextual biasing, and LLM-based ontology repair. Because repeatedly executing long-horizon computer-use tasks is costly and stochastic, we further propose an execution-free, task-conditioned evaluation framework that projects the original task grader onto prompt-addressable intentions and measures how much task-relevant information is retained after the voice interface. On WildClawBench, Talk2Agent's execution-free native projection provides a practical, execution-grounded measure of voice-interface quality, correlating with downstream task completion and improving Pearson correlation by 0.246 over WER/CER on 32 hours of real human speech. --- ### When Context Changes: Understanding Update Failures in LLMs Authors: Junyu Guo, Yuchen Fang, Shangding Gu, Costas Spanos, James Demmel, Javad Lavaei Published: 2026-09-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.38866v1 As preferences, goals, and facts change, LLM agents must use the current state while earlier versions remain in context. Yet they can answer with an old value of the same variable, a failure that we call stale binding. To study when models use outdated information and why, we introduce Controlled In-Context Memory (CICM), a benchmark for tracking and using updated information in conversations and agent logs. We observe that even frontier reasoning models can fail to recover the current state. We find that in open-source models probes can still recover the updated value when the model answers with an old one, pointing to a failure to select information that remains available. Component tests in Qwen and Pythia identify a mechanism for this selection failure: attention drift, where attention favors old values over the current one when producing an answer. We study a one-layer transformer to mathematically understand how this phenomenon happens: when attention scores are similar, several old values can together receive more attention than the current value. Guided by this explanation, we redirect attention toward the current value without further training. When the current value is requested directly, adjusting this intervention for each input corrects most old-value errors across various model families while preserving nearly all initially correct answers. Reliable context management therefore requires more than remembering updated information: models must use it to guide their answers. --- ### AdaOcc: Adaptive 3D Occupancy Prediction for Embodied Tasks Authors: Jinglong Wang, Yunjie Wang, Zhiyang Zhang, Jiawei He, Ye Yuan, Bo Qiu, Jing Zhang Published: 2026-09-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.38864v1 Embodied tasks demand accurate, flexible, and semantically rich 3D scene representations. 3D semantic occupancy is well suited to this requirement, as it can model holistic 3D spaces by encoding geometric occupancy along with semantic categories. However, existing occupancy prediction methods struggle to meet practical deployment requirements, such as adapting to varying computing budgets, sensor setups, and observation views. In this paper, we propose a point-based Adaptive 3D Occupancy Prediction method, called AdaOcc, tailored for embodied scenarios. To accommodate heterogeneous sensor inputs, AdaOcc uses an adaptive geometry-guided dual-branch encoder that can support RGB images in various numbers of views with (estimated) depth maps or LiDAR scans. AdaOcc represents occupied regions via sparse semantic points trained with a progressive query learning strategy, allowing the prediction computational budget to be flexibly adjusted through query point numbers and decoder layers. To facilitate high-fidelity geometric modeling for lightweight point-based occupancy learning, we further propose a novel containment loss that regularizes predicted points to reside within valid occupied regions. Extensive experiments show that our method achieves a new state-of-the-art on Occ-ScanNet with considerable performance improvements over previous methods. Moreover, our framework demonstrates strong practical applicability as an adaptive 3D perception module in real-world embodied systems. --- ### GeoNest: Learning to Select Failure-Aware Neighborhoods for the Irregular Knapsack Problem in a Circular Container Authors: Zhongman Du, Huiming Zhang, Linlin Yang, Sheng Xu, Baochang Zhang Published: 2026-09-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.38863v1 The two-dimensional irregular knapsack problem in a fixed circular container is an important combinatorial optimization problem for maximizing material utilization in manufacturing. Conventional geometric packing solvers can produce tightly packed layouts, yet they often partition the residual space into isolated small pockets that cannot fit valuable unplaced polygons. To overcome this late-stage packing bottleneck, we propose a failure-aware large neighborhood search framework named GeoNest, driven by a graph policy trained via reinforcement learning. Specifically, we first construct neighborhoods by pairing failed target polygons with residual pockets. We then use explanatory poses to identify the placed polygons that block candidate insertions. These diagnosed blocking relations define bounded, fixed-item repair subproblems for the underlying geometric solver. Finally, the graph policy selects the most promising subproblem for execution. For evaluation, we introduce CircleNest-Bench, a benchmark comprising 2,391 load-controlled instances from four contour sources, including a held-out industrial CAD source. Experimental results demonstrate that, under the same total time budget, GeoNest improves mean utilization over a state-of-the-art standalone packing solver by about 0.9% on average across the three main test sets and by about 0.6% on the held-out industrial set. --- ### Efficient Multi-Modal Planning with Reward-Guided Preference Optimization for Autonomous Driving Authors: Chenglin Chen, Lujia Wang, Xinhu Zheng, Jun Ma, Haoang Li Published: 2026-09-30 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2609.38862v1 Safe and efficient trajectory planning is essential in autonomous driving. However, existing end-to-end approaches often fall short in both computational efficiency and safety guarantees. Methods based on imitation learning suffer from causal confusion, while rule-based scoring approaches often incur heavy computational overhead and suffer from objective misalignment. Additionally, preference-based methods rely on strict pairwise annotations, limiting data utilization. To overcome these limitations, we propose EMPlan, an efficient multi-modal trajectory planning method powered by reward-guided fine-tuning. We design a hybrid architecture that combines sparse anchors with an offset refinement module for efficient multi-modal trajectory prediction. Sparse anchors provide coarse trajectory candidates with low latency, which are subsequently refined by the offset module for higher prediction accuracy. To enhance safety without incurring additional inference costs, we adopt a two-stage training paradigm consisting of pretraining and reward-guided fine-tuning. During fine-tuning, we leverage rule-based reward signals and unpaired preference supervision to refine the pretrained policy toward safer trajectory selection. We evaluate EMPlan on the non-reactive NAVSIM benchmark, where it strikes a favorable balance between planning accuracy and efficiency, demonstrating superior performance under real-time constraints. --- ### TRACE: Target-Aware Retrieval, Attributed Evidence, and Contract-Constrained Extraction for LitTraceQA Authors: Sachin Gupta, Divya Godara Published: 2026-09-30 Categories: cs.CL, cs.DL, cs.IR arXiv: https://arxiv.org/abs/2609.38861v1 Finding a relevant paper is not the same as producing a verifiable answer from it. LitTraceQA requires canonical paper identifiers, exact evidence at the page or object level, and typed answers that match the evaluator. We call the separation between source access and scorer-visible correctness the grounding contract gap. TRACE - Target-Aware Retrieval, Attributed Evidence, and Contract-Constrained Extraction - addresses this gap with target-grouped retrieval, independent typed evidence localization, multimodal table extraction, schema-driven table construction, and fail-closed validation. It indexes 27,487 papers through passage, object, alias, citation, and dense representations while retaining the question target behind each signal. For tables, TRACE predicts the observation unit before extracting values and assembles rows with evaluator-compatible key normalization. Our audited selected clean-track artifact scores 0.760613 on the official 71-question test set, including 0.9728 paper F1, 0.6847 evidence F1, 0.9800 multiple-choice accuracy, 0.5423 table-row F1, and 0.3508 macro cell accuracy. On 11 public-development table records, a clean baseline and coordinate-aware visual fill obtain row F1 of 0.291 and 0.411, respectively; this diagnostic comparison includes fallback outputs and is not an official-test claim. Remaining errors chiefly concern locator, observation-unit, row-key, and source-value identity. --- ### Optimal Design for Active Preference Learning with Biased LLM Judges Authors: Zhongman Du, Huiming Zhang, Haodong Zhu, Baochang Zhang Published: 2026-09-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.38860v1 Learning from human preferences is central to large language model (LLM) alignment, but human preference annotation is costly. Active preference learning reduces this cost by selecting informative comparisons, and LLM judges can provide additional scalable feedback. However, the preferences of the judges may deviate from those of the target human population. Even after calibration on trusted reference data, active acquisition can shift the comparison distribution and expose residual judge bias. We therefore incorporate judge deviations into the acquisition design rather than relying on a separate calibration stage. Under joint estimation, comparisons that appear highly informative about the reward may also reflect judge bias and therefore provide less information about human preferences. To address this issue, we propose Nuisance-Adjusted Optimal Design (NAOD), a comparison-selection strategy that prioritizes policy-relevant target information after nuisance adjustment and uses the Frank-Wolfe algorithm for optimization. Theoretically, we establish a sharp conditional local asymptotic minimax lower bound on policy risk and construct an estimator that attains it. We further characterize the finite-sample cost of learning the nuisance representation and show that representation error can reverse an oracle design advantage. Finally, we validate these predictions experimentally and evaluate NAOD on Chatbot Arena data across 17 judges, 15 budget configurations, and 15 random cluster-level splits. NAOD reduces the mean regret of proxy policy by 29.1% relative to a matched target-information design, outperforms existing methods, and improves human-preference prediction on held-out data. --- ### Decoupling Spherical Reasoning from Dense Prediction for 360 Depth Estimation Authors: Zhijie Shen, Chunyu Lin, Shuai Zheng, Feng Li, Runmin Cong, Huihui Bai, Yao Zhao Published: 2026-09-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.38856v1 The equirectangular projection (ERP) is widely used for panoramic depth estimation, but its spatially varying distortion makes geometry-consistent feature modeling challenging. We revisit panoramic depth estimation by decoupling contextual modeling in native spherical space from dense ERP prediction. To this end, we propose a Fibonacci Spherical Graph (FSG) as an intermediate reasoning space to lift ERP features onto quasi-uniform Fibonacci nodes on the sphere and capture local and long-range dependencies through complementary spherical neighborhoods. The resulting spherical discretization distributes graph nodes approximately uniformly over the spherical surface, reducing the over-representation of highly stretched regions during relational modeling. Operating on a compact set of Fibonacci nodes also avoids the computational burden of constructing and processing a graph at full ERP resolution. To bridge spherical reasoning and dense prediction, we propose a Spherical Context Conditioning (SCC) module that adaptively modulates dense ERP features with the enhanced spherical representation, allowing spherical context to guide pixel-aligned depth prediction. Extensive experiments on three benchmarks demonstrate that the proposed method consistently achieves superior depth accuracy over existing approaches. --- ### Online Evolution Strategy for Flow-Matching VLA Policies via Self-Supervised Trajectory Distribution Optimization Authors: Gongxin Yao, Yongsheng Zhao, Jiayin Deng, Deng Liang, Han Gao, Lei Zhao, Baoping Cheng Published: 2026-09-30 Categories: cs.RO, cs.AI, eess.SY arXiv: https://arxiv.org/abs/2609.38855v1 Vision-Language-Action (VLA) models based on generative frameworks, such as Flow Matching, have recently achieved impressive performance in robotic manipulation. Unlike deterministic policies, Flow Matching enables VLA models to learn conditional action trajectory distributions, where latent noise vectors induce different actions under the same task scenario. However, we observe that these distributions are often ill-formed, with successful and failed behaviors coexisting while considerable probability mass remains in unfavorable regions. To this end, we propose Online-ES, an online adaptation framework for Flow Matching VLAs based on Evolution Strategy (ES), which refines the learned action trajectory distribution through interaction feedback. Instead of pruning the latent noise space, our method performs evolutionary exploration directly in the action trajectory space, where diverse trajectories generated by Flow Matching provide candidate solutions for adaptation. By perturbing sampled trajectories and evaluating their execution outcomes, we derive a self-supervised MSE objective that transfers the evolution direction from trajectory space into model parameter space. Mathematically, we prove that the proposed objective provides an unbiased estimator of the optimal evolution direction. Moreover, we also incorporate failure experiences as negative feedback to regularize the evolution direction, steering the policy away from previously explored failure regions. Experiments in both simulation and real-world environments demonstrate that Online-ES achieves policy improvement comparable to reinforcement fine-tuning, without learning a value model or computing advantages. ---