# Research Papers — 2026-09 · bundle page 7 of 266 > Full-text markdown of papers #301–350 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/7 [← Previous bundle](https://aipod.dev/papers/archive/2026-09/page/6.md) [Next bundle →](https://aipod.dev/papers/archive/2026-09/page/8.md) ### Towards Robust Time Series Learning via Capacity-Centric Modulation Authors: Siru Zhong, Senzhang Wang, James T. Kwok, Yuxuan Liang Published: 2026-09-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.39489v1 Sample-level reliability heterogeneity is common in deep time series learning. Standard training pipelines apply a uniform regularization setting to all samples, which can under-regularize corrupted samples and over-restrict clean samples. Common robustness approaches filter observations in data space or impose priors on latent representations. We propose Capacity-Centric Modulation (CCM) as a complementary, sample-adaptive regularization principle. Under this principle, we introduce SACM (Sample-Adaptive Capacity Modulation), a task-agnostic framework that exploits spectral sparsity to assign sample-wise dropout probabilities along internal activation paths. SACM integrates into existing backbones without architectural redesign and preserves the deterministic inference pipeline. Across 301 real-world dataset-backbone pairs covering 9 forecasting, 32 classification, and 4 anomaly-detection datasets, SACM reduces forecasting MSE by 6.7% on average and improves classification accuracy and point-adjusted F1 by 3.04% and 17.05%, respectively, relative to unmodified backbones, with zero test-time overhead. --- ### Correcting CondOT: Exact Finite-Step Sampling in Gaussian Flow Matching Authors: Ron Levy, Michael Elad Published: 2026-09-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.39488v1 Flow matching generates samples by gradually transforming noise into data. In practice, using a finite number of sampling steps introduces a numerical error that depends on the chosen schedule. We study this dependence for Gaussian targets and the explicit midpoint sampling method, using the exact flow field. We measure sampling error by the squared Wasserstein distance between the target distribution and the final distribution produced by the midpoint sampler. We show that the standard conditional optimal transport (CondOT) schedule cancels the leading midpoint error and improves the general convergence bound, even when the sampling steps are unequally spaced. On a uniform grid of $S$ sampling steps, we fix the signal schedule at $α_t=t$ and prove the existence of scalar noise schedules $β_t$ that approach the CondOT noise schedule $1-t$ at rate $1/S$ and yield exact Gaussian sampling for every sufficiently large $S$. Controlled Gaussian experiments illustrate the convergence rates and exact calibration. --- ### From Wrecks to Wisdom: Recovering Crash Mechanics from Real-World Multi-View Photos Authors: Ondřej Valach, Václav Diviš, Ivan Gruber Published: 2026-09-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.39486v1 Estimating accident mechanics from real-world crashes is important for vehicle-safety analysis, injury modeling, crash-severity prediction, and operational workflows such as insurance claim triage. In standard crash records, key metadata such as impact configuration, principal direction of force, and change in velocity ($ΔV$) may be missing, delayed, or corrupted, while post-crash photographs are widely available and contain rich visual evidence of deformation. We study how much crash-mechanics information can be recovered directly from vehicle photos when structured signals are absent. We formulate crash understanding as supervised prediction from per-case multi-view photo sets. Targets include six Collision Deformation Classification (CDC) descriptors and the longitudinal and lateral components of reconstructed $ΔV$. Each photo is encoded by a shared visual backbone, and the resulting view-level features are fused into a case-level representation from which target-specific heads predict crash descriptors. Using 15.2k training cases from the Crash Investigation Sampling System, drawn from about 1.5M photos before filtering, together with 1.15k validation and 1.15k test cases, we define an evaluation protocol for vision-based crash descriptor estimation from incomplete multi-view evidence. Post-crash imagery alone provides usable signal for several non-trivial crash-mechanics descriptors, while weakly observable and long-tailed targets remain challenging. Within the compared training regimes, the selected joint-training recipe reduces mean absolute angular error for principal direction of force from 20.1 to 14.05 degrees and longitudinal $ΔV$ MAE from 8.04 to 7.45 km/h. Our work provides a reference point for future multimodal fusion with structured crash metadata. --- ### CAMOS: Coupled Oscillatory State-Space Model for Multimodal Clinical Time-Series Authors: Maxx Richard Rahman, Mostafa Hammouda, Wolfgang Maass Published: 2026-09-30 Categories: stat.ML, cs.AI arXiv: https://arxiv.org/abs/2609.39484v1 Longitudinal clinical cohorts are multimodal, irregularly sampled and pervasively incomplete: in ADNI, positron emission tomography and cerebrospinal fluid assays are absent from roughly half of all visits. Linear state-space models handle irregular sampling gracefully but treat a missing modality by masking the input, leaving the transition operator untouched. We prove that this is a representational limitation: the latent state of any linear state-space layer whose transition operator does not depend on the availability pattern is an additive function of the availability indicators, so no such layer can represent an interaction between two modalities being jointly present or jointly absent. We propose CAMOS, which gives each modality a bank of second-order oscillators coupled through a matrix that sits inside the differential equation and is gated by availability, so the transition operator itself becomes a function of which measurements were taken. Coupling invalidates the analysis of uncoupled oscillatory models, and we restore it: a per-channel Gershgorin budget makes the effective stiffness positive definite uniformly over all $2^M$ availability patterns and all gaps, an energy argument charges amplification to availability transitions rather than sequence length, and a channel factorization preserves exact associative parallel scans. On ADNI, CAMOS outperforms uncoupled oscillatory state-space models and clinical fusion models on same-visit staging, landmark prediction and longitudinal forecasting, and under zero-shot transfer to OASIS-3 it is the only model that avoids collapse to the majority class. --- ### Who Owns That? Evaluating Ownership Intuitions in Large Language Models Authors: Xizhi Xiao, Yue Wu, Shan Xu, Jia Liu Published: 2026-09-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.39483v1 Ownership establishes rights over the use, control, and transfer of objects. Understanding these relations is essential for AI systems to interact appropriately with people and their resources. Yet how large language models (LLMs) attribute ownership under competing claims remains unclear. We introduce the Competing Ownership Attribution Task (COAT), comprising 42 scenarios, and compare ownership allocations from 24 LLM configurations with those of 108 human participants. Overall, human-model similarity is close to human-human similarity, but models show greater homogeneity in their ownership judgments. Within individual answers, models also divide ownership more evenly among claimants than humans do. Pooling responses across model configurations reveals more scenarios with a shared judgment and fewer with distinct viewpoint groups than in humans. When humans form distinct groups, models may converge on one viewpoint or between competing viewpoints. Further comparisons reveal different contextual sensitivities. As material value increases across scenarios, allocations to creators decline less sharply in models than in humans. Across scenarios differing in public recognition of later holders as owners, allocations to these holders increase in models but decrease slightly in humans. Together, these findings suggest that the evaluated LLM responses do not fully capture the diversity of participants' ownership judgments or how those judgments vary across situations. Developing socially capable AI therefore requires moving beyond overall similarity to capture the diversity and context dependence of human judgments. --- ### About the Influence of Workflow Topology on Task Intensity Prediction through Graph Learning Authors: Max Otto, Haci Ismail Aslan, Joel Witzke, Jonathan Bader, Odej Kao Published: 2026-09-30 Categories: cs.DC, cs.LG arXiv: https://arxiv.org/abs/2609.39481v1 Efficient resource provisioning for large-scale workflows on cloud infrastructures is a critical performance engineering challenge. These workflows are often structured as directed acyclic graphs (DAGs), where under-provisioning can cause critical bottlenecks and over-provisioning leads to unnecessary costs. Accurate, task-level prediction of resource intensity (e.g., CPU load and memory usage) is essential for mitigating these issues. While task-level features are commonly used for prediction, the performance impact of the workflow's overall topological structure is often overlooked or assumed. The central question of our work is: To what extent does what part of the DAG topology influence task-level resource intensity, and what is the most effective way to model this influence? This paper presents a comprehensive benchmark to systematically quantify the impact of graph topology on task intensity prediction. We evaluate and compare a spectrum of modeling approaches. Our findings demonstrate that topology is a critical feature for accurate prediction. Models incorporating important topological information, even through simple handcrafted features, significantly outperform baseline models. We show that graph-native models provide the highest accuracy, achieving low mean absolute errors for both CPU and memory predictions, and can still be combined with simple topological features that they do not learn for better performance. --- ### Also Small Models Can Reasonably Self-Evaluate Their Confidence Authors: Idil Kapikiran, Thomas Decker, Thomas Runkler Published: 2026-09-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.39478v1 This study systematically evaluates self-evaluation-based uncertainty quantification across different language models of varying sizes on question-answering tasks spanning general to specialized knowledge domains. Using various self-evaluation methods where models judge their own predictions, we examine how model scale and domain specificity affect the quality of self-assessed confidence signals. Our results reveal that while accuracy predictably declines with smaller models and more specialized domains, the reliability of self-evaluated confidence remains largely stable across both dimensions. This independence means the most capable model is not necessarily the best at self-assessing prediction reliability. These findings suggest that smaller models can achieve reasonable self-assessed confidence despite lower accuracy, making them viable for resource-constrained deployments. --- ### Beyond the Shadows of Plato's Cave: Evaluating False Memory in Autonomous Agents via Counterfactual Reasoning Authors: Quan M. Tran, Zhuo Huang, Zhen Fang, Jing Zhang, Mingming Gong, Tongliang Liu Published: 2026-09-30 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.39473v1 Autonomous agents increasingly rely on memory to generalize beyond their training environments. However, agents are bounded by what they have seen and believed, and leveraging such memories in unseen environments can introduce biases into their internal beliefs. We formalize this phenomenon as \textit{false memory}, which can arise from spurious correlations, environment shifts, and knowledge conflicts. Despite its importance, false memory is difficult to evaluate because it stems from agent internal beliefs and is easily confounded with ordinary generalization failures. Therefore, we propose FAME, a training-free framework that evaluates false memory through the evolution of agent beliefs under counterfactual reasoning. Specifically, counterfactual scenarios reveal how beliefs change as the latent concept of memory shifts under hypothetical interventions; thus, measuring the resulting concept drift provides a signal for distinguishing faithful versus false memory. Such concepts can be estimated from agent hidden states before answer generation, avoiding the need for reward design or answer sampling. Empirical experiments reveal that simply monitoring answers often fails to detect false memory, while FAME achieves AUROCs of 76.2% - 96.7% across false-memory settings, and outperforms the best baseline by 3.4% - 23.3% across realistic benchmarks, spanning math reasoning (GSM-Symbolic), code generation (GitChameleon), and complex reasoning (BigBench-Hard). We further release corresponding counterfactual templates and facilitate future research on false memory. --- ### DensePed-Lite: Quality-Aware Adaptive Detection for Dense Pedestrians under Occlusion Authors: ZiAn Wang, MingZhe Liu, Chaoyi Guo, ChangChun Li, Fangming Gu Published: 2026-09-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.39467v1 Pedestrian detection plays a crucial role in computer vision with applications in autonomous driving, surveillance, and public safety. However, real-world dense scenes bring severe challenges, including heavy occlusion, drastic scale variations, and strict real-time requirements. Existing lightweight detectors struggle to balance accuracy and efficiency while often neglecting quality-aware feature modeling and consistency between classification and localization, leading to unstable performance under crowded conditions. To address these issues, we propose DensePed-Lite, a unified framework built on a single principle: under occlusion the network should adapt its behavior to the quality of what it observes rather than assume complete information. This principle is realized at three points where occlusion does the most damage: unreliable confidence scoring (UQE), fragmented spatial coverage (MPSC), and incoherent multi-scale fusion (CTDM). The three mechanisms reinforce one another instead of acting in isolation, all without significantly increasing complexity. Experiments on CityPersons and CrowdHuman validate that DensePed-Lite achieves a superior accuracy-efficiency trade-off compared with recent state-of-the-art lightweight methods, making it suitable for real-time deployment in dense pedestrian scenarios. --- ### T-ARC: Topology-Aware Randomized Clustering via Distributionally Robust Stochastic Block Models Authors: Serena Grazia De Benedictis, Andersen Ang, Nicoletta Del Buono, Flavia Esposito, Laura Selicato Published: 2026-09-30 Categories: cs.LG, math.AT, math.OC arXiv: https://arxiv.org/abs/2609.39466v1 In this work, we introduce a new clustering method, namely T-ARC (Topology-Aware Randomized Clustering), that corrects the geometric bias of K-means by embedding topological information directly into the optimization objective. Building on the assumption that the data admits an underlying hidden structure modeled via a latent graph, the idea is to uncover this information through the interplay between the standard K-means data-fidelity term and a graph-cut penalty, which discourages cluster assignments inconsistent with the connectivity structure of the data. To render this coupling tractable, the latent graph is modeled as a random realization from a Stochastic Block Model (SBM), whose scalar parameter is optimized within a Distributionally Robust Optimization (DRO) framework, yielding a closed-form proximal update. Both SBM and DRO are informed by a persistence-based similarity matrix derived from zero-dimensional persistent homology ($H_0$), which translates the multiscale connectivity structure of the data into a pairwise topological prior. The overall optimization proceeds via Block Coordinate Descent; convergence is established through a global Lyapunov functional: the deterministic blocks satisfy monotonic descent, while the stochastic graph update satisfies descent in expectation, so that the expected energy converges. Experiments on synthetic datasets with non-convex geometries and on random subsets of Fashion-MNIST show that T-ARC recovers latent topological structures where K-means fails, achieving the highest accuracy on curved and interleaved clusters while remaining competitive, and markedly more stable than K-means, on real data. --- ### Understanding Head Geometry and Dynamics in Federated Regression through a Natural Solution Selection Rule: An Unconstrained Feature Model Analysis Authors: Chuang Ma, Tomoyuki Obuchi Published: 2026-09-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.39464v1 In federated averaging, local objectives can admit multiple optimal heads, making the aggregate depend on which heads clients return. We study this ambiguity in federated multivariate regression with private backbones and a shared linear head, using an unconstrained feature model (UFM) that treats training-sample features as free variables. We introduce a natural selection rule: each client returns the optimal head closest to the broadcast head. We show that global minimization with a vanishing proximal penalty on the head realizes this rule. When the clients' optimal Gram matrices and the initial shared Gram matrix are positive definite, the shared Gram matrix follows a closed recursion and converges to the unique Bures-Wasserstein barycenter of the clients' optimal Gram matrices. Even with this alignment, the limit generally differs from the centralized optimal Gram matrix. We decompose this gap into three positive-semidefinite terms arising from differences in client target means, covariance heterogeneity, and averaging the aligned heads. A correction based on a one-time exchange of target means and covariances recovers the centralized optimal Gram matrix in one round under exact local optimization and the same selection rule. We verify these results numerically in the UFM and test its predictions on five tabular and five image regression datasets using deep networks with feature regularization and long local training. In these experiments, ordinary training approaches the predicted barycenter, while a weak proximal penalty improves endpoint agreement and yields trajectories that closely follow the predicted Gram dynamics. The correction moves the final Gram matrices close to the centralized UFM prediction. --- ### Right-Wing Rock or Just Rock? A Computational Linguistic Analysis of Frei.Wild Authors: Carlotta Schneeberger, Kevin Tang Published: 2026-09-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.39460v1 Rechtsrock is a subgenre of rock music that spreads right-wing ideology, often instrumentalized to recruit adolescents into the radical scene. Monitoring institutions counteract this by manually examining and, in some cases, banning extremist content; however, there are border cases that evade regulation. We present a study aimed at determining whether such a case, the band Frei.Wild, should be classified as politically right-leaning or as part of the general German rock genre. We sampled a German rock dataset and created a corpus for right-wing rock to use as reference in this analysis and found that we can confirm the intuitions from previous investigations that Frei.Wild successfully maintains an ambiguity with regard to their political affiliation. However, the tendency is towards the right-wing spectrum. Lexical analyses reveal nationalistic narratives and two high-performing classifiers (up to 97% ROC-AUC score) label more than half of their songs as right-wing extremist. Our analysis provides insight into how computational methods can improve the process of identifying right-wing extremist tendencies in music, especially in borderline cases like Frei.Wild. The code and data are made available for future research. --- ### Mutual Equilibrium: Multimodal Representation Learning through Reciprocal Feedback Authors: Ho-min Park, Byungkon Kang Published: 2026-09-30 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2609.39456v1 This work proposes a mutual feedback architecture, MEQ, that refines the two inputs, of possibly different modalities, into a pair of coupled embeddings such that each embedding reflects the information of the other. The core idea is to incorporate continuous interchange of information between the two inputs. This idea leads to a mutual feedback architecture consisting of two components whose outputs are fed back into the other. The final output of this model is defined as the fixed point of this interaction. We provide theoretical analysis that offers interpretation of this model as well as design choices to prevent failure cases. We show the benefits of MEQ through classification and visual grounding tasks spanning various datasets. Quantitatively, our model outperforms or shows competitive performance on concatenation-based multimodal classification problems. Qualitatively, the proposed interactive mechanism allows the model to progressively refine the visual grounding when paired with complementary modality, thus demonstrating the power of mutual feedback under such settings. --- ### From Speech to Editable Concepts: Probing Emotion Recognition with Concept Bottleneck Models Authors: Hezhao Zhang, Thomas Hain Published: 2026-09-30 Categories: cs.SD, cs.AI, cs.CL, eess.AS arXiv: https://arxiv.org/abs/2609.39453v1 Speech emotion recognition (SER) is the task of assigning emotion labels to utterances. Early systems relied on acoustic features, whereas recent approaches combine multiple modalities, most commonly speech and text. Still, performance remains poor on many datasets. Large language models (LLMs) have therefore attracted interest for SER, as they can process diverse inputs jointly with instructions. However, direct audio input raises questions of explainability. To address similar questions in image classification, concept bottleneck models were introduced. This work adapts concept bottlenecks to SER to examine how individual predictions depend on transcripts, acoustic descriptions and speaker attributes. Experiments test three LLMs on CREMA-D, IEMOCAP and MELD, with concepts extracted by separate tools. On scripted corpora, LLMs are strongly biased towards the transcript in the zero-shot setting, which lowers Macro-F1 from 27.8 to 5.8 on CREMA-D. Fine-tuning removes this bias, and the transcript raises Macro-F1 from 41.8 to 45.1. Removing speech rate changes 48% of Neutral predictions to Disgust on CREMA-D; removing intensity level on MELD changes predictions despite little change in Macro-F1. These findings show that aggregate performance changes alone do not capture the effects of concept removal on individual predictions. --- ### ResARC: Residual-Aware AutoRegressive Coding for Ultra-Low Bitrate Image Compression Authors: Qin Yan, Ruixiao Dong, Yutao Xie, Li Li, Ying Chen, Kai Li, Daowen Li, Houqiang Li Published: 2026-09-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.39451v1 Progressive autoregressive image codecs provide an appealing paradigm for generative compression by quantizing continuous latents into discrete tokens, transmitting coarse-to-fine prefix tokens and generating the remaining suffix tokens at the decoder. However, their reconstruction quality is fundamentally limited by two residuals introduced along this pipeline: the quantization residual, arising from information loss during discrete tokenization, and the generation residual, resulting from imperfect autoregressive generation of the suffix tokens. To address these limitations, we introduce ResARC, a residual-aware autoregressive codec that explicitly compensates for both residuals at the decoder. Specifically, we generate the quantization residual with a diffusion transformer conditioned on the autoregressive decoding context, while requiring no additional side information. In parallel, we compute the generation residual at the encoder and employ a learned Generation Residual Codec to efficiently compress and transmit it for decoder-side correction. The recovered residuals are then integrated with the reconstructed latent representation and decoded through an adapted VAE decoder. Extensive experiments demonstrate that ResARC achieves competitive perceptual similarity while substantially improving distributional fidelity over leading generative codecs across the ultra-low bitrate regime. Code and models will be released soon. --- ### ActionGuard: Tool Call Authorization under Poisoned Skills Authors: Jihun Han, Yejin Jang, Byung Il Kwak, Mee Lan Han Published: 2026-09-30 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2609.39450v1 LLM-based agents extend their capabilities through third-party skills that provide task-specific instructions, scripts, and tool-use procedures. However, malicious instructions inserted into an otherwise benign skill can cause a benign user request to trigger dangerous Tool Calls, including data exfiltration, file deletion, or unauthorized code execution. This paper presents ActionGuard, which inspects skill-influenced Tool Calls immediately before execution. ActionGuard separates the target agent's action-generation context from the safeguard's authorization context. The target agent may use the original skill for planning, but the Reviewer does not receive the potentially poisoned raw skill text. Instead, it determines whether each action is justified by the trusted user request using a balanced skill profile, current and recent Tool Calls, and local script contents. ActionGuard intercepts each Tool Call at OpenClaw's before-tool-call stage and enforces the Reviewer's ALLOW or DENY decision under a fail-closed policy. We evaluate ActionGuard on 139 contextual and 180 obvious injections in a SKILL-INJECT-based setting against Dynamic Guardian and SkillGuard, using three open-source and two commercial Reviewer models. Each condition is repeated three times and evaluated using Attack Success Rate (ASR) and Task Success Rate (TSR). Overall, ActionGuard reduced ASR by 35.54 to 46.11 percent relative to existing safeguards and by 70.44 percent relative to No Safeguard, while maintaining high benign-task completion. These results show that execution-boundary authorization grounded in trusted user intent and runtime evidence can restrict unauthorized Tool Calls induced by skill injection. --- ### Distributionally robust linear regression through the lens of adversarial training Authors: Elis Stefansson, David Vävinggren, Antônio H. Ribeiro Published: 2026-09-30 Categories: stat.ML, cs.LG, math.OC arXiv: https://arxiv.org/abs/2609.39449v1 Distributionally robust optimization (DRO) studies parameter estimation under uncertainty in the underlying probability distribution and has emerged as a principled framework for analyzing robustness and generalization. In particular, Wasserstein DRO, with distributional uncertainty induced by the Wasserstein distance, generalizes several popular regularizers. This paper studies Wasserstein DRO linear regression, unifying square-root Lasso and adversarial linear regression as important special cases. We prove that many properties of these two special cases carry over to this general method. In particular, we show (i) deterministic and non-asymptotic in-sample error bounds $O(n^{-1/2})$ in general and $O(n^{-1})$ under design matrix and sparsity conditions; (ii) insensitivity to the noise level, also known as the pivotal property; and (iii) solution equivalences for small and large ambiguity sets. The key proof step is to recast the method into a quadratic form, mimicking adversarial linear regression. We also show that the method can be solved efficiently, and we validate our findings through numerical simulations. --- ### Synthetic Data Characterization via Training Dynamics Authors: Irene Lago, Ana Ezquerro, David Vilares Published: 2026-09-30 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2609.39447v1 Interpreting properties of LLM-generated data is important for understanding its utility and limitations across learning tasks. In this work, we characterize synthetic data through sample-level learnability, studying variation among LLM families and scales, alongside human-written data as a reference. We first generate synthetic datasets spanning single- and multi-label classification, labeling, and tree prediction tasks. We then derive empirical data distributions from encoder training dynamics for both machine and organic data, and estimate the robustness of these distributions across encoders. Finally, we evaluate how data selection strategies based on these learnability signals affect both data sources differently. --- ### DuplexAct-Bench: Broadening Full-Duplex Speech Evaluation toward Proactive Interaction across Diverse Behavioral Requirements Authors: Keyue Xing, Wentao Ding, Mengmeng Wang, Wenming Tu, Zilong Zheng, Yipeng Kang Published: 2026-09-30 Categories: cs.CL, cs.HC arXiv: https://arxiv.org/abs/2609.39446v1 Existing full-duplex speech benchmarks cover only subsets of real-time interaction behaviors, often under limited contextual conditions. We introduce DuplexAct-Bench, a bilingual benchmark that systematically covers six complementary behaviors, from interruption and yielding to proactive initiation, active silence, and backchanneling, across Pre-session, In-session, and No-explicit conditions. Across 1,290 English and Chinese streaming trials, we evaluate 12 full-duplex speech systems on both Timing and Content. Results reveal substantial variation across behaviors, conditions, and systems, as well as frequent mismatches between semantic quality and behavioral timing. These findings show that current systems remain far from robustly managing when, whether, and how to participate as real-time interaction unfolds. Project page: https://alitaxky.icu/DuplexAct-Bench/ --- ### Raw-Routed Mixture of Adapters: A Causal Intervention for Routing Collapse in Time Series Foundation Models Authors: Hung Phan, Thuy T. Nguyen, Minh Ngoc Dinh, Nhat-Quang Tran Published: 2026-09-30 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2609.39445v1 Time series foundation models (TSFMs) commonly adapt to new data by attaching a single trainable head to a frozen backbone, a one-size-fits-all setup that underfits heterogeneous regimes. Replacing the head with a mixture of experts is the standard upgrade, but on instance-normalized backbones (the dominant TSFM design class) it fails: routing entropy collapses to zero and one expert absorbs every input, a failure we call normalization-induced routing collapse. Standard MoE rescue mechanisms do not repair it, because the cause is in the router's input, not its optimization. Pre-encoder normalization strips the statistics a router would need to tell regimes apart. A mutual-information decomposition makes this precise and yields a signal-ratio that, computed before training, predicts dataset vulnerability (Spearman $ρ= -0.88$). Eight causal controls, including a vision-modality replication, isolate instance normalization as the cause. The prescription is a minimal causal intervention: Raw-Routed Mixture of Adapters (RR-MoA), which routes on the raw, pre-normalization input. Under a strictly frozen backbone, RR-MoA wins 54/54 comparisons against the strongest fixed adapter and significantly outperforms LoRA, TRACE, AdaMix, and full fine-tuning. The effect generalizes across six backbones and an imputation task. Frozen RR-MoA also beats full fine-tuning by 12-79% (the Frozen Paradox); two architecturally distinct variants confirm the principle generalizes beyond this specific router. --- ### CAST: Causal Advantage-Structured Training with Spatially Grounded Compositional Rewards for Diffusion Models Authors: Shu Yu, Chaochao Lu Published: 2026-09-30 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.39441v1 Online reinforcement learning has been extended to flow matching for diffusion model (DM) image generation. However, this paradigm faces three limitations: (1) Window selection. Existing methods manually set the stochastic differential equation (SDE) sampling window, i.e., the denoising steps where exploration noise is injected. We instead determine it from each model's denoising trajectory. (2) Reward saturation. Current methods rely on scoring models trained on human annotations; we find that such scores are extremely high and nearly indistinguishable on the latest SOTA open-source DMs, making advantage estimation largely ineffective. (3) Sample inefficiency. A single scalar reward collapses different failure modes into almost identical scores, leaving minimal gradient guidance for targeted improvement. To address these issues, we propose CAST (Causal Advantage-Structured Training), an RL fine-tuning method for pretrained DMs, which (1) identifies the denoising step at which each model fixes the objects and their spatial arrangement in the image and uses that timing to set the SDE window, (2) decomposes each prompt via Causal Scene Graphs (CSG) into verifiable-atoms, i.e., minimal semantic units such as an object, count, attribute, or spatial relation that can each be checked independently, and rewards each atom separately, and (3) projects the signed atom-level advantages into pixel space through teacher-forced attention and uses them to spatially weight the SDE policy objective. We fine-tune two of the strongest open-source DMs, FLUX.2-dev and Qwen-Image-2512, with CAST, and evaluate them on GenEval 2, a compositional benchmark, and on Qwen-Image-Bench for overall quality. Within almost the same training budget, CAST's improvement over the base model on the most challenging GenEval 2 prompts is up to 3.07x that of Flow-GRPO, while overall generation quality also improves. --- ### Principal Component Regression Dominates all Monotone Spectral Filters for Linear Regression Authors: Juno Kim, Hengyu Fu, Peter Bartlett, Jason D. Lee, Jingfeng Wu Published: 2026-09-30 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2609.39440v1 We compare the instance-wise, finite-sample risks of monotone spectral filters for linear regression, a broad class of estimators including principal component regression (PCR), gradient descent (GD), and ridge regression. We show that PCR dominates all monotone spectral filters: compared to any such filter, the risk of optimally tuned PCR is no bigger by a constant factor for all problems. Furthermore, the dominance is strong if the filter is separated from step functions (e.g., GD and ridge): there exist problem instances for which the risk of PCR is smaller by a polynomial factor in sample size dependence. Our comparison results show that PCR is optimal and thus admissible among monotone filters, significantly extending Wu et al. (2026)'s result that GD strongly dominates ridge. From a technical perspective, we establish new upper and lower bounds for general spectral filters, which are instance-wise sharp when specialized to ridge or GD, recovering or improving the best-known bounds. --- ### Network-based Spatial Context Retrieval for Open-weight LLMs: A Faithfulness Benchmark for Grounded Geographic Reasoning Authors: Joan Perez Published: 2026-09-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.39437v1 Large language models (LLMs) encode substantial latent geographic knowledge, yet they reason poorly over space and are unreliable when queried from coordinates alone. Useful behaviour emerges only when structured spatial context is supplied in the prompt. This raises a question geographic evaluation has left unexamined: once the right context is supplied, does the model reason from it, or override it with its own parametric recall? We take up this question with an open pipeline for network-based spatial context retriev-al. In it, the surroundings of a selected point are defined by the pedestrian street network, the area actually reachable on foot. Using only open data and open-weight models, the pipeline retrieves features from OpenStreetMap and the GHS-POP population grid, computes indicators over the network catchment in code, and injects them as a compact spatial brief. On this basis we build a faithfulness benchmark. It labels every claim a model makes by its source (grounded in the brief, or drawn from training knowledge) and its correctness, and it probes each case with a planted false premise that the brief refutes. We evaluate sixteen open-weight model configurations across three families (Qwen, Gemma and Llama, with Gemma in two generations), four size classes and, where available, both thinking and non-thinking modes, on three con-trasting cities, resampling every case over ten seeds. The results show that resistance to the planted premise varies more strongly by model family and generation than by scale, while brief-reading competence forms a partly separate dimension. These behaviours are not captured by conventional world-correctness scores or single-shot evaluation. We release the implementation, spatial briefs, model outputs, and claim-level labels as a reproducible workflow at github.com/perezjoan/NSCR-LLM. --- ### From Imitation to Reward Discovery: On-Policy Warmup for Agentic RL Authors: Yitong Qiao, Tiantian He, Lei Liu, Yue Shen, Jian Wang, Jinjie Gu, Zhixuan Chu Published: 2026-09-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.39436v1 Reinforcement learning with a verifiable reward (RLVR) offers a scalable approach to training language-model agents, yet sparse outcome rewards can leave early training with little signal for policy improvement. We identify an On-Policy Acceleration Phenomenon: in our main comparisons, RLVR initialized with on-policy distillation reaches high performance earlier in training and achieves both higher average performance during subsequent RLVR and higher final performance than the alternative baselines. Motivated by this observation, we study On-Policy Warmup (OPW), a teacher-guided stage in which the student trains with teacher supervision on its own interaction trajectories before transitioning to RLVR. Unlike imitation on fixed teacher-generated trajectories, OPW targets states induced by the student's own decisions, including imperfect actions and recovery situations. We provide a theoretical explanation by connecting on-policy reverse-KL distillation to trajectory-level distribution matching. Under a competent teacher and sufficiently small population distillation loss, this connection yields a lower bound on initial verifier success and a corresponding bound on reward-discovery complexity. For group-relative RLVR, we further characterize when increased success probability produces more reward-informative groups. Together, our findings support on-policy distillation as an effective warmup for agentic RLVR and identify initial reward discovery as a mechanism that can contribute to the observed acceleration. --- ### Towards Trustworthy AI for Glioma Diagnosis: A Task-Aware Evaluation of Uncertainty Quantification Authors: Gonzalo Esteban Mosquera Rojas, Sebastian R. van der Voort, Carolin M. Pirkl, Sandeep Kaushik, Marion Smits, Stefan Klein Published: 2026-09-30 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.39429v1 Uncertainty Quantification (UQ) is a key requirement for trustworthy AI in high-stakes medical image analysis. In this work, we evaluate UQ in a multi-task Deep Learning framework for MRI-based glioma diagnosis that performs tumor segmentation and predicts IDH mutation status, 1p/19q co-deletion status, and tumor grade. Monte Carlo Dropout (MCD) is used for a detailed task-aware analysis of predictive, aleatoric, and epistemic uncertainty. We assess MC sample convergence, calibration, error detection, selective prediction, associations with segmentation performance, and the effect of voxel-wise uncertainty aggregation on case-level reliability. We also compare MCD with Deep Ensembles (DE) and Monte Carlo Deep Ensembles (MCDE), examine interactions between segmentation quality and classification, and evaluate a composite trust score integrating segmentation and classification uncertainty. Across tasks, uncertainty estimates supported meaningful error detection, while calibration depended on the dropout rate, with moderate rates yielding the most reliable probabilities. Uncertainty decomposition provided task-dependent interpretability but did not consistently improve error detection over predictive uncertainty alone. DE and MCDE showed comparable operational utility, with no method consistently dominating across tasks and metrics. The composite trust score did not consistently outperform classification uncertainty for selective prediction. Overall, our results provide a task-aware evaluation strategy and practical guidance for the development of trustworthy AI for glioma diagnosis. --- ### PCB-MC: Missing Component Analysis in Printed Circuit Boards Authors: Betsy Villa Brochero, Ian Gibson, Estefania Talavera Published: 2026-09-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.39427v1 Detecting missing components on printed circuit boards (PCBs) differs fundamentally from conventional object detection, as the model must localize components that are not present. We introduce PCB-MC, a curated dataset for missing component detection with footprint level annotations built on top of the RF100 dataset. The dataset contains 197 distinct board types, each corresponding to a unique PCB design, with multiple augmented samples per type. We also provide benchmark results on PCB-MC by evaluating a diverse set of supervised and unsupervised methods. To ensure fair evaluation, we propose board type aware cross validation splits that prevent layout leakage between training and test sets. Supervised models showcase high false negative rates on unseen board designs, and unsupervised anomaly detection methods fail entirely due to the lack of spatial alignment with a board specific reference. These results confirm that missing component detection on diverse PCB layouts remains an open challenge. We release PCB-MC and all training protocols to support reproducible research on structural absence detection in industrial inspection. --- ### QuantCode Model: Specializing Language Models for Executable Algorithmic Trading Code Authors: Alexey Chernysh, Orkhan Ekhtibarov, Dmitry Zmitrovich Published: 2026-09-30 Categories: cs.CL, cs.LG, q-fin.TR arXiv: https://arxiv.org/abs/2609.39420v1 Large language models are strong general-purpose code generators, but executable algorithmic trading remains a demanding specialization target: a model must translate a natural-language strategy specification into correct program logic for a specialized trading framework, execute on historical data, produce trades, and remain semantically faithful to the request. We study two complementary mechanisms for specializing language models for this setting: continued pretraining on algorithmic-trading framework code and supervised fine-tuning (SFT) on agent-validated request-to-code pairs. Evaluation is centered on QuantCode-Bench, our 400-task benchmark for Backtrader strategy generation, together with a repository-level SWE-bench-like track. Continued pretraining improves single-turn Judge Pass from 41.5% to 47.5% for Qwen3.5-397B-A17B and from 27.8% to 33.0% for Qwen3.6-35B-A3B. SFT applied after continued pretraining yields a larger gain for Qwen3.6-35B-A3B, reaching 58.2% Judge Pass and 83.5% successful backtests; in agentic evaluation it raises first-turn success from 22.3% to 58.3% and final success after up to 10 turns from 47.5% to 79.5%. Continued pretraining alone improves first-turn agentic success but lowers final success after repair from 47.5% to 32.5%, consistent with degraded instruction following, whereas SFT improves both. We also identify a capability-retention failure: domain specialization degrades parser-conformant structured tool calling, and targeted recovery SFT restores tool-call formatting but not the base checkpoint's repository-level agent performance. The results show that framework-oriented pretraining, validated SFT, and explicit capability-retention evaluation address distinct failure modes in domain-specific executable code generation. --- ### Awakening of the Buddha: Subspace Learning During Population-Loss Plateaus Authors: Akash Kumar Published: 2026-09-30 Categories: cs.LG, math.OC, stat.ML arXiv: https://arxiv.org/abs/2609.39408v1 Population loss can remain nearly constant while a neural network learns a substantially more predictive representation. We establish this separation for two-layer ReLU and leaky-ReLU networks trained on Gaussian inputs by simultaneous fixed-step population gradient descent on all parameters. For structured additive teachers whose links are positive mixtures of Gaussian-damped cubics in $H^1(γ)$, we give explicit conditions under which small IID Gaussian initialization yields a high-probability guarantee: at a checkpoint during a high-loss plateau, minimum alignment between the rank-$r$ teacher subspace and the leading $r$-dimensional eigenspace of the predictor's average gradient outer product (AGOP) increases by at least $1/2$, and the minimum refit MSE under unchanged coefficient budgets decreases by more than $0.399$, both relative to initialization. The same trajectory subsequently attains a trained loss below every value in the plateau window. A complementary result treats unequal-weight cubic teachers and small additive Sobolev perturbations using projected-feature refits. For SwiGLU networks with an exactly fitted intercept, we prove leading-AGOP alignment during a loss plateau at fixed width and dimension as Gaussian initialization vanishes, for square-integrable teachers with nonzero Hermite content of degree one, two, or three. A rank-one cubic specialization also gives simultaneous unrestricted-refit gains at a prescribed width. An approximation lower bound further shows that certain interaction targets retain nonzero error when ridge neurons are restricted to shared orthogonal axes within the teacher subspace. Population-moment experiments with ReLU students across 21 teachers and 50 initializations per teacher complement the analysis. --- ### Inferring Causal Relations between Two Sequences of Events with Language Models Authors: Nishchal Prasad, Eric Gaussier, Emilie Devijver, Alexander Obeid Guzman, Armen Aghasaryan, Gregor Gössler Published: 2026-09-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.39406v1 Causal AI is a branch of Artificial Intelligence which helps understand and reason about cause and effect relationships, not just patterns or correlations. Causal discovery aims to infer elements of the underlying causal structure--often represented as a directed graph--from observational and, when available, interventional data. While causal discovery is the fundamental step for moving beyond mere associations toward genuine understanding, and thus the basic building block of causal AI, it becomes intrinsically difficult when causal relations must be inferred from single observations. In such situations, standard causal discovery methods cannot be used and one has to identify causal relations from limited amount of information. This is typically the case for, e.g., sequences of events produced by different alarms which need to be analyzed on the fly to detect abnormal phenomena, which are usually rare. We show in this study that it is possible to leverage the predictive power of Large Language Models (LLMs) to infer causal relations between only two sequences of events. This approach, which is validated on both synthetic and real data, provides better results than standard causal discovery algorithms on several time series data, even though these data were converted into smaller, single observed sequences. --- ### No Task Vector Is an Island: A Comprehensive Study on the Composability of Task Vectors from On-Policy Distillation Authors: Jingang Zhou, Feiyu Han, Han Zhu, Yuyi Zhou, Ruiyang Zhang, Jian Xu, Sirui Gao, Qingpei Guo, Xu-Yao Zhang Published: 2026-09-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.39405v1 Task vectors provide a simple mechanism for composing learned capabilities through model merging. However, the composability of task vectors produced by on-policy distillation (OPD) remains largely unexplored. OPD trains a student using teacher feedback on student-generated trajectories, yielding parameter updates that differ from those produced by the teacher model, usually by reinforcement learning (RL). We therefore ask whether OPD task vectors can complement their RL teacher updates and compose effectively across tasks. Across five domains and two model architectures, we find evidence for both forms of composability. Within a task, merging OPD and RL task vectors can outperform both constituent models, even when the OPD student is weaker than its RL teacher. Across tasks, OPD task-vector compositions achieve higher average scores than corresponding RL compositions in seven of eight backbone-merging-rule comparisons. Parameter-space analyses reveal substantial non-collinearity between OPD and RL updates. Experiment in CODE domain on SMOLLM3-3B shows that the combined direction outperforms either constituent direction at the tested global update norm, supporting directional complementarity in this configuration. Across tasks, OPD updates also show lower overlap among the top-10% feed-forward channels ranked by update energy. Together, these results show that weaker standalone performance does not imply weaker task-vector composability. OPD task vectors can complement stronger RL teacher updates and combine effectively across tasks, highlighting composability as a distinct property for understanding and evaluating post-training updates. --- ### Advancing Entropy-Level Credit Assignment in RLVR via Proximal Entropy Policy Optimization Authors: Yun Kim, Nojun Kwak Published: 2026-09-30 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.39402v1 Value-model-free RLVR methods such as GRPO assign uniform advantages to all tokens in a rollout, ignoring that tokens contribute unequally. Recent methods use token entropy as an importance proxy but compute it globally across the batch, conflating importance with prompt difficulty and positional trends. We argue that importance should instead be measured relative to the local context of each token. We introduce proximal entropy, a local measure of token importance relative to neighboring tokens, and prove it is invariant to both confounders. Proximal Entropy Policy Optimization (PEPO) uses it to weight per-token advantages and outperforms GRPO and entropy-based baselines on mathematical reasoning across Qwen3-1.7B, Qwen3-4B, and Llama-3.2-3B-Instruct. We also show the formulation generalizes to other algorithms where substituting proximal entropy into existing methods improves, and applying it to single-stream RL succeeds where global entropy fails. --- ### Towards Optimal Inventory Control under Censored Demand: A Biased Sample-Average Approximation Approach Authors: Yuxuan Han, Xiaoyu Fan, Jiawei Zhang, Zhengyuan Zhou Published: 2026-09-30 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2609.39397v1 We study data-driven multi-period lost-sales inventory control under censored demand, where a stockout reveals only that demand exceeded the stocking level. We develop a unified, model-based framework for policy learning from censored data, built on a new cost decomposition for base-stock policies and a biased sample-average approximation (SAA) approach. The cost decomposition allows us to propose a new coverage condition under which censored observations are informative enough for sample-efficient policy learning. Guided by this coverage condition, we design two biased SAA algorithms: an upper-biased one that achieves near-optimal sample complexity under the offline coverage condition, and a lower-biased one that actively generates the required coverage and achieves near-optimal regret online. More broadly, this biased SAA approach provides a general principle for implementing pessimism and optimism under censored feedback, which may be of independent interest. --- ### Can Computation from Earlier Problems Help LLMs Solve New Ones? Authors: Jipei He, Wenhui Tan, Xiaoyi Yu, Enver Sangineto, Fiorenzo Parascandolo, Rita Cucchiara, Ruihua Song Published: 2026-09-30 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2609.39394v1 Large language models often solve independent problems in the same conversation. Can computation from earlier problems help them solve new ones? To answer this question, we first conduct preliminary experiments showing that retained history can raise or lower later-turn accuracy, even within the same domain. To understand these effects, we use controlled replay to isolate internal state changes specific to each problem-history pairing. Across different histories, these changes preserve similar relationships among current problems. To improve reasoning under retained history, we introduce STAIR (Stale-Token Attention for Inter-query Reuse). STAIR captures keys and values from earlier response generation in a fixed bank. It learns to redirect current queries when they read this bank during prompt processing. The base model remains frozen; only 12,288 parameters are trained. Across three Qwen models and four benchmarks, STAIR improves average later-turn accuracy by up to 11.67 percentage points over the unmodified model with history. --- ### Experimental Experience Modeling for Autonomous Research Authors: Wenda Wei, Yingchen Zhang, Ruqing Zhang, Jiafeng Guo, Daiting Shi, Xueqi Cheng Published: 2026-09-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.39392v1 Autonomous research agents can generate hypotheses and conduct experiments, but experimentation remains a major source of computational cost. A fundamental challenge is deciding which experiments are worth running, particularly when prior evidence is insufficient to resolve uncertainty. Yet current research agents lack a systematic way to leverage experimental experience when making such decisions. We introduce Experimental Experience Modeling (EEM), a framework for making informed experimental decisions by acquiring, reusing, and accumulating experimental experience. EEM extracts decision-relevant records from earlier experimental trajectories, distills them into reusable experience, and organizes them in an experience library. For a new experimental decision, EEM retrieves relevant historical experience and assesses whether it provides sufficient support for deciding whether a candidate direction warrants further investment. When historical experience is insufficient, EEM conducts a targeted, low-cost pilot experiment to acquire the missing decision-relevant experience on demand. It then combines this newly acquired experience with retrieved historical experience to determine whether the direction warrants full-scale evaluation, which requires substantial resources. The resulting experimental outcomes are further distilled into reusable experience, allowing the library to continually grow through iterative accumulation. Experiments on autonomous research benchmarks show that EEM improves research performance while reducing model interaction overhead, demonstrating the value of reusing accumulated experience and acquiring additional experience only when needed. --- ### Decoupled and Distilled: Task-Adaptive LoRA-Teachers with Ensemble Knowledge Transfer for Few-Shot Class-Incremental Learning Authors: Hongwei Zhao, Rui Liu, Yansong Liu, Zhiyuan Zou, Yong Chen Published: 2026-09-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.39390v1 Few-Shot Class-Incremental Learning (FSCIL) addresses the challenge of learning new classes from very limited samples while retaining knowledge of previously learned ones. Although parameter-efficient fine-tuning methods with pre-trained models show promise for class-incremental learning, strict gradient-based constraints can be unreliable under severe data scarcity, while multi-expert approaches can impose substantial inference-time costs. We propose TALON (Task-Adaptive LoRA-Teachers with Ensemble Knowledge Transfer), an inference-efficient FSCIL framework. TALON dynamically allocates an independent LoRA-Teacher to each incremental task for task-specific representation learning, then distills multiple frozen teachers into a unified LoRA-Student through Ensemble Knowledge Transfer, eliminating runtime module selection or generation. A semantic-guided distillation strategy weights teacher contributions by feature-space similarity to mitigate catastrophic forgetting and overfitting. Across three class-order runs, TALON achieves comparable or better mean average accuracy across four FSCIL benchmarks, obtaining 86.68 +/- 1.22% on CUB200, 90.39 +/- 0.27% on CIFAR100, 78.38 +/- 0.94% on ImageNet-R, and 96.34 +/- 0.33% on miniImageNet. TALON uses up to 33x fewer deployment parameters and reduces average inference time per task to 26.7 s, a 41.70% reduction relative to ASP. --- ### UniWAM Technical Report: Unified Mobile Manipulation via Mixed-Stream World-Action Modeling and Manipulation Anchor Pose Supervision Authors: Wei Xue, Keliang Liu, Mingzhang Cui, Jinhua Xie, Jinjie Wei, Jianan Hou, Jingcheng Lu, Lintao Wang, Kaixiang Qiu, Yizhou Liu, Xinghai Ye, Jinghang Han et al. Published: 2026-09-30 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2609.39388v1 Mobile manipulation requires precise navigation to a manipulation-ready pose followed by reliable object interaction. These two stages differ in action spaces and visual requirements, which complicates unified policy learning. In addition, collecting diverse real-world navigation data with explicit manipulation-ready pose supervision remains costly and difficult to scale. We introduce UniWAM, a unified mixed-stream world-action model with separate action encoders and output heads for navigation and manipulation, sharing a common backbone. This design supports joint representation learning on independently sampled navigation and manipulation data. UniWAM supports independent inference for either stream and batch-parallel inference for both. We further introduce Manipulation Anchor Pose (MAP) supervision for where to stop and how to orient for manipulation. An automated pipeline constructs MAP-Data from large-scale 3D scenes, yielding over 1.5 million episodes and 7,500 hours. MAP-Data provides per-frame target-object bounding boxes and image-plane MAP coordinates as auxiliary navigation supervision. Together with projected end-effector trajectories for manipulation, these prediction targets provide stream-specific image-plane supervision for action learning from egocentric observations. With large-scale MAP-Data, UniWAM outperforms the strongest external baselines on our MAP-Bench by 30.1\% in position error and 44.0\% in heading error. Across 24 real-robot tasks, UniWAM achieves leading results in MAP navigation and mobile manipulation, with competitive manipulation performance. We have released code, data, and benchmark. --- ### Beyond Simulation: Retain-and-Repair Neural Operators for Real-World Adaptation Authors: Woojin Cho, Junghwan Park Published: 2026-09-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.39387v1 Neural operators increasingly benefit from pretraining on numerical simulations, yet adapting them for real-world prediction remains challenging. We introduce the Retain-and-Repair Neural Operator (R$^2$NO), a framework for adapting simulation-pretrained operators to real-world data while retaining useful pretrained structure. The pretrained operator is first finetuned on real data and then frozen to provide a source prediction, and a shared repair module learns a sequence of refinements from the same observations. Using orthogonal Fourier projections, a spectral ensemble fits a small ridge regression within each cell of the Fourier domain and combines the refinements by weights fitted on a held-out split of the real data. The cells are defined jointly by radial ranges, angular sectors, and measured channels, allowing refinement depth to vary with frequency magnitude, with orientation, and across channels. Including the source prediction as a candidate makes retention available in every cell, and independently trained repair modules enter the same combination as additional candidates. On all RealPDEBench systems and six backbones, R$^2$NO consistently outperforms full finetuning and iterative refinement. The framework treats adaptation depth as a cell-specific choice learned from real data. --- ### When, Not How Much: Evaluating Time-Series Foundation Models on Sparse Events Authors: Daniel Schoess, Florian von Wangenheim Published: 2026-09-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.39386v1 Pretrained time-series foundation models (TSFMs) are evaluated as forecasters of future values, yet for sparse series many decisions depend only on which future periods contain activity. Standard benchmarks do not assess this. On five sparse datasets, we rank positions within forecast windows that contain both events and zeros. The released point forecasts of 12 TSFMs improve chance-corrected average precision over training-free references by at most 0.031, and in chance-corrected AUC the median TSFM falls below them on every dataset. With event supervision, linear probes of six frozen backbones improve on their backbone's point forecast in 29 of 30 backbone--dataset pairs. Averaging the predicted quantiles instead of taking their median improves the ranking of most TSFMs that forecast the median, and on two datasets the strongest such outputs rival the probes. The probes' advantage over raw-context learners depends on the dataset, and under the same probe, pretrained features outperform randomly initialized ones for five of six backbones. For sparse-event ranking, released point forecasts thus add little over simple references, whereas lightweight event heads on frozen TSFMs rank events better than these forecasts, and the best of them exceed gradient-boosted trees trained on the raw context on three of the five datasets. More broadly, assessing pretrained forecasters on tasks beyond value forecasting requires reporting their outputs, supervised probes of their representations, and raw-context and randomized controls side by side, since each supports a different conclusion. --- ### TTLab at Daleel 2026: STAR-Ar, Sequence Tagging for Argument Recognition in Arabic Authors: Bhuvanesh Verma, Ali Abusaleh, Alexander Mehler Published: 2026-09-30 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.39385v1 Argument Mining (AM) is a critical NLP task that remains significantly under-resourced in Arabic. This paper presents $\testtt{STAR-Ar}$, a BERT-BiLSTM-CRF architecture for argument discourse detection and classification, as our system for Daleel 2026, the inaugural Arabic argument mining shared task. The task requires the identification and classification of argumentative discourse units (ADUs) in debate and editorial texts.We jointly model these two objectives as a token-level sequence labeling task using a BERT-BiLSTM-CRF architecture that combines contextual transformer embeddings with structural transition constraints to support accurate span detection. $\testtt{STAR-Ar}$ achieves an F1-score of 72.69 on validation and 73.7 on test data. Our domain-specific analysis shows that models trained exclusively on editorials underperform those trained on debates, a disparity we primarily attribute to the smaller size of the editorial dataset. The code for $\testtt{STAR-Ar}$ is available at ${\href{https://github.com/ENTAILab/daleel_2026_Arabic-Argumentative-Discourse-Mining}{\faGithub~TTLab at Daleel 2026}}$ --- ### From Search to Signal: Online Post-Training in Automatic Heuristic Design Authors: Yilun Yuan, Tianyu Zhou, Zhenzhou Tang Published: 2026-09-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.39383v1 Large language model (LLM)-based automatic heuristic design (AHD) iteratively proposes and refines heuristics, pairing design rationales with executable code. Task-specific evaluators assess programs; execution outcomes and performance scores guide search. Many AHD systems keep the generator frozen; EvoTune and Co-Evolution of Algorithms and Language Model (CALM) instead update it from evaluated candidates. When such outcomes drive reinforcement learning with verifiable rewards (RLVR), they create a search-coupled loop: the evaluated candidate stream supplies both search-state updates and training signals for the model that generates future candidates. Yet validity and performance do not uniquely determine useful model updates; converting them into learning signals must account for the prompt and evolving search state that produced each candidate. We formulate online post-training of small open-weight LLMs in AHD as context-dependent signal construction and develop alternative mappings from program validity, task performance, and generation context to update signals. Using shared evaluated rollouts and matched update budgets, controlled experiments across AHD tasks and model families compare these mappings with online post-training baselines, testing their effects on validity, performance among valid proposals, and the yield of valid proposals that improve under contextual comparisons. Complementary checkpoint, frozen-search, and live-system evaluations assess whether proposal-level gains appear in updated checkpoint behavior and subsequent search, rather than arising solely from accumulated search state. A resource-matched comparison under pre-specified cost accounting tests whether online updating adds value beyond additional search with a frozen generator. Together, this design avoids treating end-to-end search gains alone as evidence of stronger heuristic-design capabilities. --- ### SkillFM: Generating Skills for LLM Agents via Latent Flow Matching Authors: Zuming Zhang, Jie He, Yizhe Zhang, Jeff Z. Pan Published: 2026-09-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.39382v1 Textual skills provide reusable guidance for large language model agents, but existing approaches often rely on manually curated skill banks or reinforcement learning with indirect and delayed feedback. We introduce SkillFM (Skill Flow Matching), a generative framework that synthesizes task-conditioned textual skills directly without test-time skill retrieval. Our framework combines a codec for encoding and reconstructing textual skills in a continuous latent space with a conditional flow model trained using improved MeanFlow. At inference time, the learned velocity field enables single-step latent sampling, and an LLM-based decoder converts the sampled representation into textual guidance for a frozen downstream agent. We evaluate the framework on embodied tasks, question answering, and web shopping. On ALFWorld and Search-QA, our method achieves the best overall performance among the compared vector-based skill approaches. Our analyses further demonstrate that latent skill generation is an effective alternative to retrieval-based skill augmentation. Our code and training skill libraries are available at https://github.com/lulushang999/SkillFM. --- ### InfoAgent: Traceable Generation and Repair of Evidence-Grounded Infographics Authors: Yifan Li, Tong Li, Qi Zeng, Lishuai Gao, Ruwei Pan, Cong Wei, Shaohua Kevin Zhou, Zhuoliang Kang, Xiaoming Wei Published: 2026-09-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.39380v1 Reliable infographic generation requires facts, symbols, and visual relations to remain consistent through rendering and revision. Correcting one element also requires tracking its supporting evidence and the dependencies affected by the change. We present \textbf{InfoAgent}, a training-free framework for \emph{evidence-bound visual-symbolic program synthesis}. Its Infographic Visual Description (IVD) records factual payloads, evidence provenance, execution routes, and verification obligations in a typed dependency graph. Retrieved design priors guide compilation, and layered execution combines raster synthesis with editable symbolic and binding objects while retaining their traces. Dependency-aware repair localizes corrections, rechecks affected dependencies, and requires protected obligations to remain satisfied under the declared checkers. Unresolved obligations remain explicit. On IGenBench, InfoAgent achieves 93.0 Q-ACC and 59.0 I-ACC. We also introduce InfoGraphicBench-Evidence, where complete-checklist pass rates on 200 test requests increase from 21.5\% for Same-IVD Prompt to 23.5\% for the initial layered output and 28.5\% after repair, using the same evidence and initial IVD. On 120 audited repair cases, localized repair edits 12.4\% of the canvas on average, compared with 67.3\% for global regeneration. --- ### EgoTools: Towards Tool-Centric Reasoning in Real-World Egocentric Videos Authors: Shulin Tian, Junsu Kim, Shuai Liu, Hao Li, Yujiao Shen, Sihan Li, Zhe Yang, Yeongon Kim, Feiyu Li, Jialin Wu, Yichi Zhang, Wenhui Wang et al. Published: 2026-09-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.39378v1 Real-world embodied tasks, from everyday activities to professional procedures, require agents to act under physical constraints while tracking evolving object and task states. Tool use sits at the heart of such tasks, as many everyday and professional activities are tool-mediated. Understanding them requires reasoning about affordances, hand-tool-object geometry, procedural progress, and causal effects on target objects. Yet despite strong performance on perception-oriented video tasks such as captioning and general video QA, current multimodal video models remain limited in this form of tool-centric embodied reasoning. Progress in this direction has been limited by the lack of real-world egocentric data and diagnostic benchmarks. To address this gap, we introduce EgoTools, the first comprehensive suite for egocentric tool-use understanding. It consists of two complementary components: EgoTools-Data, a large-scale corpus of 100 hours of tool-centric egocentric recordings with synchronized audio, dense captions, reasoning-heavy narrations, and supplementary 3D information; and EgoTools-Bench, a diagnostic benchmark of 1,000 QA pairs across four tracks that cover tool-use understanding from perception and geometry to procedure and causal reasoning. Experimental results show that current models still struggle to ground tool use in visual evidence: Gemini-3.1-Pro achieves 66.9% overall accuracy but only 51.7% on Perception & Grounding. Beyond evaluation, we validate EgoTools-Data as a training resource. On the full 1,000-question benchmark, full supervised fine-tuning improves Qwen3-VL-8B-Instruct from 50.0% to 60.9%, under strict source-video separation. Together, these results establish EgoTools as a unified resource for both training and diagnostic evaluation of real-world egocentric tool-use understanding. --- ### Beyond the Current Scene: Event-Referential Grasping with Active View Selection Authors: Hyunjoon Lee, Haebeom Jung, Eunsung Cha, Daeun Lee, Yu-Chiang Frank Wang, Jaesung Choe, Jaesik Park Published: 2026-09-30 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2609.39375v1 A robot that observes people interacting with objects should be able to carry out later requests that refer back to those interactions. Such requests may specify a grasp target by the role it played in a past event rather than by its name or appearance. Moreover, the target may no longer be visible when the robot is asked to act. We present BeyondSCe, a zero-shot robotic grasping system for this event-referential setting. Given the event history and the current scene, the system identifies the requested object or part and localizes it for grasping. If the target is occluded, it combines an event prior recovered from the history with current scene geometry to select camera viewpoints likely to reveal the target. The system uses pretrained models without additional task-specific training. In real-robot experiments with a single wrist-mounted RGB-D camera, it achieves grasp success rates of 76% and 77% for initially visible and occluded targets, respectively, compared with 40% and 55% for the strongest baseline in each condition. On four additional scenes with heavy occlusion, it increases grasp success rates from 75% to 95% while reducing the mean number of views from 3.35 to 2.20, compared with an active-perception baseline given the target's ground-truth 3D bounding box. --- ### Wavelet Flow Matching for Time Series Authors: Lucas Poinsignon, Jorge da Silva Gonçalves, Samuel Ruipérez-Campillo, Julia E. Vogt Published: 2026-09-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.39374v1 Synthetic time series are increasingly used for data augmentation, privacy-preserving data sharing, and downstream model development, yet faithfully reproducing both multi-scale temporal structure and cross-channel dependencies remains challenging. We study multivariate time-series generation through flow matching in the wavelet domain. By operating on multilevel discrete wavelet coefficients rather than directly in the time domain, the model represents coarse structure and progressively finer details at separate scales. Their naturally different variances further induce an implicit coarse-to-fine generative process without requiring an explicit multi-scale schedule. Since the transform acts independently on each channel, we pair it with a channel-token transformer whose attention directly models cross-channel dependencies. Across seven benchmark datasets and four sequence lengths, our method is best or tied on a majority of dataset-metric combinations, with the largest and most consistent improvements in Context-FID and discriminative score. --- ### EHR-RobustGym: Benchmarking and Training Agents for Robust Clinical Reasoning Authors: Yitong Qiao, Yancheng Jin, Lei Liu, Yue Shen, Jian Wang, Jinjie Gu, Zhixuan Chu Published: 2026-09-30 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.39371v1 In hospital workflows, electronic health records (EHRs) are often noisy, and may not contain the evidence needed to confirm events or measurements referenced in a clinical query. Even when database retrieval succeeds, clinical agents can overlook such discrepancies and return plausible but unsupported answers. We introduce EHR-RobustGym, a scalable and interactive environment for evaluating and training robust clinical agents grounded in noisy EHRs. Built on MIMIC-IV hospital records (365K patients, 31 tables, and over 500M records), EHR-RobustGym comprises 5,486 Clean-Noise pairs spanning six clinical intents and both patient-level and population-level queries. The pairs test robustness to Record-level, Value-level, and Query-level noise, while interactive SQL/Python execution and outcome verification support trajectory collection and training. Evaluating multiple LLMs reveals substantial robustness gaps: average task success across proprietary and large-scale open-weight models drops from 62.2% on Clean questions to 37.9% on Noise questions. At k=4, pass^k consistency falls below 50% for most evaluated models, exposing instability in clinical task completion. Supervised fine-tuning and reinforcement learning in EHR-RobustGym improve performance, with gains generalizing to five external EHR benchmarks. Together, these results position EHR-RobustGym as a testbed for evaluating and improving the evidence-grounded robustness of clinical agents. --- ### Exploring Heterogeneous Model Merging Approach for Complex Knowledge Transfer Authors: Jiahe Fan, Si Chen, Yinghao Hou, Wenbo Xia, Ke Xu, Hong Xie, Enhong Chen Published: 2026-09-30 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2609.39369v1 Specialized models encode task-oriented behavior, but transferring that behavior to a general language model usually requires training, distillation, or representation alignment. We study whether such ability can instead be transferred directly at the parameter level. We apply two existing training-free heterogeneous merging methods, previously shown to transfer knowledge between general language models, to specialist-to-general transfer, projecting a specialist donor into the recipient's shape and interpolating backbone parameters without gradient updates or semantic alignment. Intersection-Merge (IM) injects a prefix-aligned donor slice matching the recipient shape, while Activate-Prune-Merge (APM) uses forward-pass activation statistics to select which donor dimensions to retain before injection. Across embedding, reranking, reward modeling, and MoE code-specialist transfer, both methods improve the general recipient, showing that simple heterogeneous merging can move capabilities across diverse specialist roles. --- ### Making Grid Beam Search Less Greedy Authors: Sean Papay, Roman Klinger Published: 2026-09-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.39368v1 A common formalism for constraining the output of autoregressive text generation models involves lexical constraints, words or phrases which are required to occur in the generated text. DFA-constrained beam search and grid beam search are two widely used paradigms for decoding from autoregressive models while enforcing lexical constraints. As the former approach requires a number of forward passes exponential in the number of constraint tokens, it is often dispreferred to the latter, which requires only linearly many forward calls. However, while grid beam search achieves an exponential speedup, it does so in a manner which does not treat all of the constraints equally. In this paper, we demonstrate that grid beam search is biased to incorporate easier-to-satisfy constraints first, leaving harder constraints to the end of the sequence. This contrasts with DFA-constrained beam search, which exhibits no such bias. To address this shortcoming, we propose fair grid beam search, a modification to grid beam search which avoids this bias while still requiring only linearly many forward passes. Experimentally, we confirm grid beam search's bias on two constrained generation tasks, finding significant differences in how it orders constraint tokens as compared to DFA-constrained beam search and fair grid beam search. Furthermore, we find that fair grid beam search not only fixes grid beam search's bias, but finds higher-probability strings in the process. --- ### A Dynamical Theory of LoRA in Continual Learning Authors: Théo Marchetta, Filippo Alessandroni, Alessandro Breccia, Alessandro Ingrosso, Federica Gerace Published: 2026-09-30 Categories: stat.ML, cond-mat.stat-mech, cs.LG, math.PR, math.ST arXiv: https://arxiv.org/abs/2609.39367v1 Despite the widespread use of Low-Rank Adaptation (LoRA), little is known about its dynamics in continual learning and the mechanisms by which low-rank updates affect catastrophic forgetting. We provide an asymptotically exact dynamical characterization of LoRA in a solvable two-task teacher-student model. In the high-dimensional online-learning limit, we derive a closed system of ordinary differential equations for a finite set of macroscopic order parameters, yielding exact expressions for the generalization errors throughout both the initial Task 1 learning phase and the subsequent LoRA fine-tuning on Task 2. The theory quantitatively matches finite-dimensional simulations and exposes two characteristic effects of LoRA: low-rank adaptation reduces interference with features learned on the first task, but its initialization slows adaptation to the second task. Building on this mechanistic picture, we analyze a state-dependent masking strategy that freezes hidden units carrying the strongest first-task representations and restricts adaptation to the complementary subspace. This structural partitioning markedly reduces forgetting, while preserving plasticity on the new task. Our framework further clarifies the role of adapter rank: transfer improves only up to the intrinsic dimensionality of the target task and saturates beyond it, while forgetting continues to grow with rank. These results provide a dynamical and geometric account of how low-rank adaptation organizes information across sequential tasks and are qualitatively reproduced on a sequential MNIST benchmark. --- ### COBICount: Separating Object and Background Responses for Remote Sensing Object Counting Without Training on Target Data Authors: Junjing Zheng, Zhiyi Zhou, Ningrui Yang, Hongying Meng Published: 2026-09-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.39366v1 Remote sensing object counting estimates how many buildings, vehicles, or ships appear in overhead images. Most supervised counters predict a density map, whose sum gives the object count, and assume similar categories, sizes, and backgrounds. Applying them across regions, sensors, or categories often requires target data or further training, which may be costly or unavailable. We study source-only counting. Training for the counting task and model selection use one group of images that shares an object category and similar imaging conditions, with one point marking each object. Target images and information remain unavailable until the model is fixed. This reduces data preparation but makes transfer harder. A model trained on one source may place high density values, called responses, on real objects and repeated background structures. Road edges, parking grids, roof boundaries, and water boundaries may then be counted as objects, creating candidate origin ambiguity. COBICount separates response generation, acceptance, and background suppression. Candidate Evidence (CE) generates possible responses. Candidate Acceptance (CA) keeps compact responses centered on objects. Bias Isolation (BI) reduces responses associated with repeated background structures. Their outputs form the final density map. Trained on RSOC Building and evaluated directly on DOTA Large Vehicle, Small Vehicle, and Ship, COBICount achieves the lowest mean absolute error (MAE) averaged over the target domains among the compared methods, 174.132. It uses 5.07 million parameters and 17.41 billion floating point operations for a 512x512 input. COBICount improves transfer without target data or training for each target. The code will be available at: https://github.com/yixuxi22/COBICount. ---