# Research Papers — 2026-10 · bundle page 40 of 156 > Full-text markdown of papers #1951–2000 of 7799 published in 2026-10, newest first. AI-readable mirrors of the full 7799-paper 2026-10 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-10/page/40 [← Previous bundle](https://aipod.dev/papers/archive/2026-10/page/39.md) [Next bundle →](https://aipod.dev/papers/archive/2026-10/page/41.md) ### Facts Don't Speak Louder than Words: The Behavioral Essence of Long-CoT Distillation Authors: Yongcan Yu, Jian Liang, Lingxiao He, Kuangpu Guo, Yanbo Wang, Shuo Lu, Meng Wang, Ran He Published: 2026-10-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.17607v1 While long chain-of-thought (CoT) distillation significantly improves the reasoning abilities of language models, its underlying mechanism remains poorly understood. Current pipelines generally rely on rejection sampling to gather reasoning traces across diverse prompts, assuming that factual correctness and broad problem coverage are indispensable. Surprisingly, we find that training exclusively on flawed reasoning trajectories or a restricted prompt set yields nearly comparable performance. Driven by this counterintuitive finding, we propose the Behavioral Hypothesis: the essence of Long-CoT distillation is behavioral alignment with structured reasoning patterns, rather than factual knowledge memorization. We then validate this by demonstrating substantial reasoning gains even when models are fine-tuned exclusively on previously mastered problems-effectively isolating behavioral alignment from novel knowledge injection. Having established that reasoning patterns are the true bottleneck, we investigate how to learn them across varying levels of complexity optimally. We reveal a critical interplay: while the recent probability-based loss excels at learning simple patterns, the standard cross-entropy loss is essential for scaling to complex CoTs. We believe these insights demystify CoT distillation and provide a principled foundation for the future development of reasoning models. Code is available on https://github.com/yuyongcan/Long-CoT-Distillation. --- ### PLEDGE: Progressive Lossy Error-Bounded Compression of 3D Gaussian Splatting Authors: Mingze Xia, Yuxiao Li, Baixi Sun, Wenbo Li, Pu Jiao, Sheng Di, Franck Cappello, Hanqi Guo, Xin Liang Published: 2026-10-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.17605v1 Existing 3D Gaussian Splatting (3DGS) codecs report reconstruction quality after compression, and give users little control over the distortion of individual primitives. We present PLEDGE, a training-free, progressive, error-bounded codec that translates four user-declared tolerances into per-primitive quantization bounds: screen-space position, footprint deformation due to rotation and scale, view-dependent color, and opacity. The bounds apply throughout a declared camera domain, including previously unseen viewpoints. Position and opacity are bounded directly; footprint deformation is bounded under the rasterizer's affine projection model, and color is bounded over all viewing directions. PLEDGE organizes quantized residuals into a progressive bitstream with explicit error bounds for every valid prefix. Experiments across thirteen scenes verify all declared per-mechanism bounds and demonstrate competitive rate-distortion performance. The four tolerances incur substantially different rate costs, so users can spend rate where their application needs it. --- ### Morphology-aware deep learning predicts colorectal cancer survival from whole-slide images Authors: Hikmat Khan, Metin N. Gurcan, Anil Parwani, Wendy L. Frankel, Wei Chen, Muhammad Khalid Khan Niazi Published: 2026-10-13 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2610.17603v2 Background: Five-year survival prediction from hematoxylin-and-eosin whole-slide images could support risk stratification, but the task is weakly supervised, and the tissue morphologies carrying prognostic information remain incompletely characterized. Methods: We conducted a retrospective secondary analysis using TCGA-COAD/READ (n=562) for morphology-specific analysis, Alliance/ CALGB 89803 (n=424) for model development, and SurGen (n=218) for external evaluation. We propose MorphContrast, a morphology-aware contrastive multiple-instance learning framework that uses tissue labels as structural supervision for five-year survival prediction. MorphContrast combines gated-attention pooling with three auxiliary objectives: patch-level morphology labels define within-patient contrasts, outcome concordance or discordance defines cross-patient contrasts within matched morphologies, and diversity regularization discourages representational collapse. Morphology-matched patches from patients with discordant outcomes serve as hard negatives, encouraging prognostic discrimination within comparable histologic contexts. Results: Morphology-specific models show weak but distributed prognostic discrimination: adipose tissue achieves an area under the receiver operating characteristic curve (AUC) of 0.622, stroma achieves 0.604, and both perform comparably to tumor epithelium (0.601-0.605). On Alliance/CALGB 89803, the single model achieves an AUC of 0.642, while the post hoc ensemble reaches a pooled out-of-fold AUC of 0.70 and a risk-group hazard ratio of 3.79 (95% confidence interval: 2.55-5.63). On the external SurGen colon cancer cohort (n=218), the single model and ensemble achieve AUCs of 0.669 and 0.678, respectively. Conclusions: These findings support tissue morphology as structural supervision for outcome-aware representation learning in colorectal cancer prognosis. --- ### TDR: Tagalog Diacritic Restoration Dataset Authors: Ivan Yuri De Leon, Lanz Railey Fermin, Zachary Aldridge Africa, Richell Isaiah Flores Published: 2026-10-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.17597v1 Homographs are words that share identical spelling but differ in meaning and pronunciation. In Tagalog, these distinctions are disambiguated in writing through tuldik (diacritical marks), which are rarely preserved in contemporary Tagalog text. This scarcity of diacritics limits diacritic restoration, which is useful for downstream tasks such as prosody selection for text-to-speech synthesis. To address this gap, this study introduces TDR, an annotated corpus of 40 frequent Tagalog homographs constructed from news text. It also introduces a collocation-driven retrieval method to expand the dataset and mitigate severe class imbalance among minor variants. Finally, we show that TDR supplies a capability absent from pretrained models, and that this capability can be learned by small, inexpensive models as well as by fine-tuned LLMs. --- ### Tanawpamana: Benchmarking Vision-Language Models on Philippine Cultural Heritage Sites Authors: Ivan Yuri De Leon, Hiroki Ouchi, Sakriani Sakti Published: 2026-10-13 Categories: cs.CV, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2610.17596v1 Vision-language models are increasingly used to identify and describe places, yet their recognition and knowledge of specific cultures remain poorly understood, particularly in underrepresented regions such as the Philippines. This study introduces the Tanawpamana Dataset, a repository of Philippine heritage site images with metadata based on the Talapamana registry of the National Commission for Culture and the Arts of the Philippines. We also introduce the Tanawpamana Benchmark, comprising 4,046 tasks designed to evaluate models' recognition and knowledge of heritage sites. Evaluating seven vision-language models, we find that they struggle more with fine-grained visual discrimination among similar heritage sites than with coarse recognition, and that their geographic knowledge is weaker when inferred from image inputs than from text. --- ### Training Generalist Navigation Policies via Action Self-Distillation Authors: Bowen Feng, Keqin Wang, Yulong Yang, Amogh Joshi, Christine Allen-Blanchette, Dhruv Shah, Felix Heide Published: 2026-10-13 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2610.17593v1 Language provides a natural interface for humans to specify and reason about goals, but training language-conditioned robotic policies and reasoning typically requires expensive manual annotations. We propose Action Self-Distillation (ASD), a method for learning language-conditioned reasoning for robotic navigation without human-annotated language or reasoning labels. ASD uses an open-source VLM, which contains broad world knowledge and reasoning capabilities, as both a teacher network and a student policy. During training, the self-teacher receives privileged trajectory feedback and infers the underlying navigation goal together with goal-oriented reasoning. The student is then trained to condition on the inferred navigation goal, predict future ego-frame trajectory, and provide a description of the scene semantics, plan, and reasoning, from onboard observations alone. Across 13 challenging indoor and outdoor real-world navigation tasks, our method improves success rate over the strongest baseline by $30\%$ in indoor settings, $30\%$ on multi-stage tasks, and achieves $95\%$ success rate on outdoor tasks, validating that privileged trajectory feedback can enable self-distillation for scalable generalist navigation policies without human annotations. --- ### Physical-Field-Bridged Material Parameter Inference from Multi-View Deformation Videos Authors: Linrui Shou, Jie Li, Yu Liu, Tao Huang Published: 2026-10-13 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2610.17591v1 Estimating simulation-ready material parameters from visual observations is crucial for deformable-object manipulation but challenging because material properties are only indirectly revealed through physical responses. We introduce physical-field-bridged material inference, a single-pass framework that uses dense physical responses to connect multi-view RGB deformation videos with constitutive-type classification and continuous parameter regression. Unlike inverse-physics methods requiring per-scene reconstruction, online tuning, or simulation-in-the-loop optimization, our model predicts force/contact masks, projected motion-flow fields, and projected stress-response maps, then conditions material inference on these fields to reduce reliance on appearance or category shortcuts. We construct DeformFieldBench, a 3DGS MPM learning environment comprising 5,000 simulations across 100 object shapes and five mechanically informative loading modes, with dense pixel-aligned physical supervision. Our method achieves the best median errors on all four continuous parameters, improves stress-hotspot recall from 0.0762 to 0.5121, and attains 0.8676 SSIM/36.82 dB PSNR in same-simulator replay on unseen objects. Under a protocol-matched GSO evaluation, inference and future-state prediction take approximately 30 seconds, compared with 15-120 minutes for per-scene optimization. The method also yields measurable replay agreement on five real-world sequences. These results support dense physical fields as an effective bridge for fast material inference, while cross-simulator and real-world tests reveal remaining domain and identifiability gaps. --- ### Revisiting the 16x Pretraining Compute Gap between Diffusion and Autoregressive Language Models Authors: Guanghan Wang, Bing He, Zhan Shi, Benoit Dumoulin, Hanqing Lu, Volodymyr Kuleshov Published: 2026-10-13 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.17590v1 Diffusion language models (DLMs) have attracted wide attention for their fast, parallel decoding, but they are believed to be far less efficient to train than autoregressive language models (ARMs): a widely cited study reports that a DLM needs roughly 16x the training compute of an ARM to match its likelihood, a figure that has made pretraining DLMs from scratch look prohibitive at scale. We find that the methodology behind this figure has fallen out of step with current DLM practice: it scores the model with its evidence lower bound (ELBO) and trains a full-sequence, decoder-only model. We therefore revisit the scaling laws of DLMs, adopting the exact likelihood under the model's own decoding order, block diffusion training, an encoder-decoder architecture, and a sweep over the block sizes used in practice. Under this new protocol, we study across ten model variants, about 1,700 models in total, and find that pretraining DLMs is far cheaper than previously thought. Concretely, scoring with the exact likelihood reduces the compute multiple to 12.8x; block diffusion training and an encoder-decoder architecture further reduce it to 7.8x at block size 32, and smaller block sizes narrow it to 4.6x at block size 8 and 3.0x at block size 4. We complement these scaling analyses with an empirical rule for the optimal decoder depth of encoder-decoder block diffusion, a held-out compute budget beyond the fitting range at which the gap between variants persists, and downstream benchmark results where likelihood improvements carry over to accuracy. Overall, the 16x figure substantially overstates the pretraining cost gap between DLMs and ARMs, and pretraining DLMs from scratch is far more viable than previously assumed. --- ### Taming Softmax at the Limits of Muon: A Unified Approach through Hilbert Geometry Authors: Aditya Somasundaram, Charles Guille-Escuret, Alexander Moreno, Zhengzhong Liu, Eric Xing Published: 2026-10-13 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.17588v1 Muon controls weight updates through the RMS movement of a linear layer's output. This implicitly treats the linear output as a proxy for the full module, including the nonlinearity that follows. This proxy can be misleading for softmax, where the RMS shift in activations does not faithfully measure the change in the output distribution. We propose Hilbert distance as a natural metric for bounding changes in these output distributions. Hilbert distance bounds changes in cross-entropy loss and limits probability redistribution. For softmax, it takes the form of the variation seminorm of the preactivation perturbation, allowing probability constraints to be expressed as parameter constraints. Formulating the steepest descent problem with a Hilbert distance constraint brings two recently proposed methods under a unified mathematical framework. For the LM head, solving a row-wise approximation to the resulting diameter-constrained problem leads us to RowNorm \citep{pethick2025trainingdeeplearningmodels}. For scaled dot-product attention, the same principle yields the first-order query--key steepest descent problem underlying Compositional Muon \citep{keigwin2026compositional}. These connections motivate using Hilbert distance as a guiding principle for optimizer design in softmax modules. --- ### RAN-JEPA: An Action-Conditioned World Model for Energy-efficient Mobile Network Control Authors: Binghan Wu, Kai Zeng, Kai Yang, Ya-Qin Zhang, Joseph Sifakis, Ye Ouyang Published: 2026-10-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.17584v1 Operational mobile networks are rich in observations but poor in interventions: they continuously generate large volumes of passive telemetry, while controlled action--response trajectories remain comparatively scarce and costly to collect. This observation--intervention asymmetry is a central obstacle to building practical world models for RAN control. We address this problem with RAN-JEPA, an action-conditioned world model that separates representation learning from intervention learning. The model first learns a predictive latent representation from observation-only network data, adapts that representation to the target deployment domain, and then learns action-conditioned latent dynamics from controlled sleep/wake trajectories while keeping the encoder fixed. We evaluate RAN-JEPA using public operator performance data for pretraining and a real-equipment four-cell 5G testbed for domain adaptation, post-training, and control. Across four future 15-minute intervals, RAN-JEPA achieves lower action-conditioned prediction error than a GPT-2 world-model baseline and a mechanistic rule, while remaining close to a strong persistence reference. What-if evaluation further shows that the model produces distinct and coherent future trajectories under matched SLEEP and KEEP plans. In closed-loop control, RAN-JEPA consistently supports higher sleep ratios than the two baselines at comparable congestion cost. These results show that observation-first, action-conditioned learning can turn abundant passive telemetry and limited intervention data into a practical predictive model for energy-aware RAN control. --- ### Chasing Label Shifters: A Change-Aware Framework for Dynamic Graph Node Classification Authors: Junghoon Kim, Seungyoon Choi, Hyunsung Kim, Chanyoung Park Published: 2026-10-13 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.17582v1 Entities in real-world systems often evolve over time: users shift between information consumption patterns, researchers migrate between fields, and firms transition between financial risk states. When such systems are modeled as dynamic graphs, these transitions correspond to nodes whose class labels change between consecutive snapshots, which we call shifters. Correctly classifying shifters is often more consequential than classifying stable nodes with persistent labels, as detecting such transitions enables timely intervention in high-stakes settings. Yet, we identify a systematic failure mode across all major dynamic graph neural network architectures: shifter performance consistently lags behind stable nodes, with errors concentrated on the old label. Our structural analysis traces this failure to embedding inertia: neighborhood aggregation keeps shifter representations anchored to the old-class centroid, and this effect is strongest precisely where it is hardest to correct, namely for shifters whose neighborhoods remain aligned with the old class. Guided by this finding, we propose CHASE, a model-agnostic CHange-Aware framework for Shifting nodEs that wraps any dynamic GNN with targeted components for detecting label shifts and overriding stale neighborhood signals. CHASE consistently improves shifter performance across all tested models and datasets (up to 114.9% and 202.5% improvement on accuracy and F1 score, respectively) while preserving stable-node performance. We additionally contribute three dynamic graph benchmarks with naturally shifting labels, filling a gap in existing resources. The source code is available at https://github.com/jhkim611/CHASE --- ### Risk-Averse Inference-Time Diffusion Model Alignment with Finite-Sample Guarantees Authors: Yuchen Liang, Xian Yu Published: 2026-10-13 Categories: stat.ML, cs.LG, math.OC arXiv: https://arxiv.org/abs/2610.17579v1 Inference-time alignment steers diffusion models toward downstream objectives without costly fine-tuning, but existing methods typically optimize expected cost (or reward) without explicitly controlling tail risk. In this work, we propose a risk-averse framework for inference-time alignment of diffusion models that balances expected cost and Conditional Value-at-Risk (CVaR) under trajectory-level Kullback-Leibler regularization. We characterize the optimal path distribution and reverse transitions as functions of the CVaR threshold, reducing the alignment problem to a one-dimensional optimization problem over the threshold. We show that this one-dimensional optimization problem can be nonconvex in general, establish sufficient conditions for convexity, and introduce quadratic regularization to enable efficient derivative-free ternary search. Under suitable assumptions, we provide finite-sample guarantees for threshold optimization and value estimation, and combine them into a terminal total-variation bound relative to the regularized target under exact resampling. Experiments on synthetic data and image generation using Stable Diffusion demonstrate improved tail performance over risk-neutral baselines while maintaining competitive average cost. --- ### Dissociating Answerability from Extraction in LLM Question Answering over Radiology Reports Authors: Priyanshu Sinha, Kelsey McDonald Published: 2026-10-13 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2610.17576v1 Answering questions from radiology reports involves two decisions: whether the report contains an answer and which span gives it. A false answer presents an unsupported claim as fact; an over-abstention hides what the report says. Yet RadQA results are reported as a single F1 that merges both. We propose an evaluation method that separates them, reporting false-answer and over-abstention rates beside F1 and splitting F1 changes into extraction and answerability terms. We apply it to 13 LLMs on the RadQA test set, zero-shot and with three cumulative demonstration sets, the last adding an unanswerable example. Models with similar F1 differed more than twofold in false-answer rate. The unanswerable example changed when models answered, not how well they extracted: 12 of 13 models abstained more often, and three-quarters of the answers they withdrew had F1 $\geq$ 0.5. Within models, false answers showed no clear association with extraction quality, but acting on the decision itself helped: keeping an answer only when enough other models also answered lowered the zero-shot false-answer rate by 4 points without a detectable F1 change. Because the two decisions can change independently, we suggest radiology QA evaluations report them separately, not through F1 alone. --- ### Benchmarking Self-Supervised 3D Medical Vision Foundation Models and Transferability Estimation Authors: Jiaqi Tang, Yu Wang, Yang Liu, Jing Tao, Fandong Zhang, Zhou Zhen, Xiahai Zhuang, Qingchao Chen, Yining Yang, Yizhou Yu Published: 2026-10-13 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2610.17573v1 Self-supervised pretraining has expanded the pool of 3D medical foundation models, but published evaluations use different datasets, endpoints and fine-tuning protocols. Models also differ in architecture, pretraining objective and data, while downstream targets range from voxel-level masks to patient-level diagnoses and outcomes. As a result, published findings provide little directly comparable evidence for choosing a model for a new task. Direct comparison of adaptation performance requires fine-tuning candidates on labelled target data, at substantial computational cost. We benchmark 23 candidates across the same 14 segmentation, classification and regression tasks spanning multiple anatomies and modalities. No candidate ranked among the top three across all segmentation tasks or across all classification and regression tasks; a convolutional encoder could outperform a transformer trained with the same objective on one task but underperform it on another. We benchmark transferability estimators against the fine-tuned rankings and find that their agreement varies across dense segmentation, classification and regression. InsightRank uses task-appropriate frozen-feature statistics and architecture-aware pairwise comparisons to rank candidates before fine-tuning. Across the 23-model pool, mean Kendall tau-b was 0.431 for segmentation and 0.352 for classification and regression. The segmentation Top 3 contained a task winner on four of nine tasks; the image-level Top 3 contained none on the five tasks, despite better full-ranking agreement than the matched conventional estimators. A three-model shortlist reduced recorded extraction-plus-training job time by 85.8% across seven segmentation tasks. Together, the benchmark provides a common reference for model selection and InsightRank offers a lower-cost way to prioritize fine-tuning, with shortlist performance that differs by target type. --- ### EdgeWise: Bringing Long-Horizon Agents to the Edge via Selective Cloud Delegation Authors: Zeru Shi, Jindong Jiang, Ryo Hachiuma, Yonggan Fu, Byung-Kwan Lee, Peter Belcak, Saurav Muralidharan, Ayush Agarwal, Ruixiang Tang, Ambrish Dantrey, Pavlo Molchanov, Anjul Patney et al. Published: 2026-10-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.17560v1 Complex and long-horizon agent tasks often rely on frontier models deployed in the cloud to achieve strong performance. However, using these models for every step of a long-horizon trajectory incurs substantial inference cost, even though not all steps may require the same level of model capability. In this paper, we find that allocating the LLM to only a small subset of key steps can achieve performance comparable to full LLM execution while significantly reducing inference cost. Motivated by this observation, we propose EdgeWise, an edge-cloud collaboration framework that deploys an SLM on the local device as the primary solver and selectively delegates critical steps to a cloud LLM when stronger model capacity is needed. To enable autonomous delegation without additional models at inference time, we introduce a step-level RL method that jointly optimizes task solving and delegation, with fine-grained credit assignment for individual delegation decisions. We also introduce an external judge-based delegation strategy and use it to systematically investigate key design choices in edge-cloud collaboration, including when to delegate, how delegation decisions should be made, what context should be shared, and how frequently the cloud LLM should be invoked. Experiments show that EdgeWise matches or outperforms pure-LLM execution while reducing inference cost up to 62% on SWE-Rebench and 34% on Terminal-Bench 2.1. We further deploy EdgeWise on a local workstation, demonstrating comparable cost savings in a practical edge-cloud setting. --- ### FlashVSR+: Efficient Video Super-Resolution via Hybrid Attention and Reward-Yield Distribution Matching Authors: Ruchang Yao, Shi Guo, Junhao Zhuang, Mingde Yao, Xin Cai, Jiahao Zhan, Bin Fu, Xinyuan Chen, Yu Qiao, Tianfan Xue Published: 2026-10-13 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2610.17552v1 Recent video super-resolution (VSR) models achieve efficient one-step generation through diffusion distillation. However, high-resolution inference remains costly, and distilled models are difficult to align with human preferences. These challenges call for improvements in both model architecture and training strategy. We present \textbf{FlashVSR+} to address both limitations. On the architecture side, we introduce hybrid attention based on the strong locality observed in pretrained VSR models, while retaining sparse global interaction for long-range consistency. It achieves up to $2\times$ DiT speedup and 45\% lower peak memory, enabling spatially untiled 4K VSR on a single 24GB RTX 4090. On the training side, we propose Reward-Yield Distribution Matching Distillation (Ry-DMD) for preference-aligned one-step generation. Ry-DMD uses reward-weighted teacher rollouts to incorporate black-box rewards into distribution matching, without backpropagating through the reward model. We further show that Ry-DMD generalizes beyond VSR to T2I generation. Together, FlashVSR+ delivers stronger restoration quality and substantially improves high-resolution efficiency, with consistent gains in user preference. We release our code, models, and training data at \href{https://www.flashvsr.tech}{\textcolor{FlashBlue}{\textbf{www.flashvsr.tech}}}. --- ### Reference Wording Shapes Retrieval of Robot Task Instructions Authors: Jahnavi Yelamanchi Published: 2026-10-13 Categories: cs.AI, cs.CL, cs.IR, cs.RO arXiv: https://arxiv.org/abs/2610.17549v1 Identifying a robot task from a short instruction is sensitive to which descriptions are available for retrieval. We investigate this effect in the natural-language instructions included with the RLBench manipulation benchmark. We extract 296 fixed descriptions from 62 publicly available task files and compare five training-free lexical rankers over 80 random choices of one indexed description per task. Exact strings assigned to conflicting task labels are excluded from the primary score. Character n-gram TF-IDF achieves 61.3% mean top-1 accuracy on the resulting held-out instructions, compared with 55.6% for BM25 and 54.9% for word TF-IDF. Across gallery choices, character TF-IDF ranges from 55.2% to 66.8%; its 5th-95th percentile range is 56.9%-64.8%. Adding a second indexed description improves character TF-IDF by 7.0 percentage points on matched queries. These results quantify the influence of reference wording and representation choice on instruction-to-task retrieval under a consistent evaluation protocol. --- ### Many Steps into One: Reasoning Contraction and the Limits of Safe Memory Reuse for LLM Agents Authors: Jianghong Zhou, Hao Rong, Chen Lin, Daoan Zhang Published: 2026-10-13 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2610.17544v1 Thought templates, skill libraries, agent memories and caches turn many reasoning steps into one. We call this reasoning contraction. A contracted memory saves reasoning steps and errors until its facts change, then quietly answers wrong. Most systems trust memories by counting successes and failures. We prove that such counters are badly tuned change detectors: a symmetric counter notices a partial change only after a power of its false-alarm horizon, and an unclipped one may never notice it. On five LLMs answering multi-hop questions over edited facts, ExpeL- and ACE-style counters serve 7.0-13.5x more stale answers than certified memories given the same information, and on code tasks with an exact verifier 35-73x more. Safety also has a price. When facts change and each memory is judged only by its own verified outcomes, one number, the certification load, sets how much reasoning any safe memory can skip, and under Zipf demand it yields a scaling law. Our recipe weighs each memory's failures by its own likelihood ratio, certifies its utility against live reasoning, and restarts the certificate when facts change, with the likelihood-ratio detector as the safety net for unannounced changes; for large edits it also invalidates the memory. --- ### Convex-Analytic View of Query Selection for Safety Verification of Markov Decision Processes Authors: Han Bao, Shinsaku Sakaue, Kazuki Watanabe Published: 2026-10-13 Categories: math.OC, cs.AI, cs.LO arXiv: https://arxiv.org/abs/2610.17541v1 Safety verification of a Markov decision process (MDP) asks whether the probabilities of reaching several failure states jointly lie in a convex safe region under every scheduler. Watanabe and Unno (2026) prove safety by refining an outer approximation of the failure probabilities, where each query bounds a nonnegative weighted sum of the probabilities. Their rule selects weights by the largest Euclidean violation. We present a unified framework to measure violation in an explicitly chosen error unit: directions are scored by the support-function gap between the outer approximation and the safe region, normalized by the support function of the unit. We show that the maximal score, when positive, equals the smallest enlargement of the safe region in multiples of that unit that contains the outer approximation. The Euclidean unit recovers the earlier rule; two new rules are generated by the unit cube and the safe region itself. We experimentally evaluate how the choice of measurement rule affects the performance of safety verification for MDPs. --- ### TacitVLA: Reasoning Vision-Language-Action Models Without Reasoning Latency Authors: Jack Lu, Yurong You, Boyi Li, Yulong Cao, Thomas Tian, Chaowei Xiao, Xiangyu Chen, Wenjie Luo, Boris Ivanovic, Marco Pavone, Yan Wang Published: 2026-10-13 Categories: cs.AI, cs.RO arXiv: https://arxiv.org/abs/2610.17540v1 Textual reasoning before acting has improved vision-language-action (VLA) models, but at the cost of latency: every action conditioned on the reasoning text must wait for autoregressive decoding. We show that actions do not need to wait for or condition on the generated reasoning to benefit from it, because the reasoning supervision already improves the backbone representation. We introduce TacitVLA, a reasoning VLA whose action expert never attends to the reasoning it generates for the current call. On long-horizon tasks where the reasoning text also serves as episodic memory, it can generate each entry during action execution rather than before acting. We evaluate it in a controlled study on four benchmarks spanning manipulation and autonomous driving, memory and non-memory tasks: RoboMME, RMBench, LIBERO, and PhysicalAI-AV. On all four, TacitVLA matches the performance of its explicit-reasoning counterpart at up to 3.4x lower latency, and matches the latency of the same architecture trained without reasoning at up to +17.1% success. In absolute terms, it surpasses the best previously published results on the RoboMME Counting suite (82.7% vs. 66.8%) and RMBench (77.5% vs. 56.5%), and reaches 72.9% on LIBERO-Plus and a 52.5% scene score on the public split of the PhysicalAI-AV closed-loop driving challenge. Project page: https://tacitvla.github.io. --- ### Everyone Was Right: Lexical Representations in Language Models Are Both Abstract and Holistic Authors: Zachary Nicholas Houghton, Yu Zhou, Dan Pluth, Vijay K. Gurbani, Vsevolod Kapatsinski Published: 2026-10-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.17538v1 Lexical representations can encode both abstract information and information specific to particular contexts. We investigate how these forms of information are organized in language models by decomposing contextual word representations into item, class, and word-class interaction components. Across six pretrained transformers and two linguistic categories, we find that the interaction is consistently present, grows across layers, and contains information associated with both item and class. Unlike the nearly orthogonal item and class effects, the interaction overlaps with both and encodes class information beyond the shared class effect. An interaction also emerges in artificial-language learners even when the input contains only additive structure. Together, these findings show that lexical representations combine abstract information with structure specific to particular word-class combinations. --- ### CrossPortrait: Cross-Species Portrait Animation via Adversarial Motion Alignment Authors: Gezhong Pan, Zhe Li, Yunfan Tao, Yongheng Zhao, Shiqi Zhou, Juyong Zhang, Xiaosong Jia, Yanyong Zhang, Shuquan Ye, Shaofeng Zhang Published: 2026-10-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.17532v1 Cross-species portrait animation, which aims to animate a source portrait of species A using a driving video of species B, is particularly challenging due to substantial anatomical differences in facial structures across species. Previous works typically fine-tune human portrait animation models on animal video datasets but often suffer from driving-species leakage. To address this, we propose CrossPortrait, a novel framework for expressive cross-species portrait animation, supporting diverse scenarios including human-to-animal, animal-to-human and cross-species animal-to-animal (e.g. cat-to-dog) animation. Specifically, we decompose the portrait motion into rigid head poses and expression keypoints. To accommodate species-specific facial structures while facilitating cross-species expression alignment, we introduce a species-routed expression encoder that incorporates species-specific LoRAs into a unified expression encoder. Furthermore, we introduce expression-level adversarial domain adaptation (Ex-ADA) to suppress driving-species-specific information in the expression latents, thereby mitigating species leakage and promoting a shared expression space across species. Extensive experiments show that our method enables expressive and identity-preserving portrait animation across diverse species and outperforms other state-of-the-art approaches. --- ### Towards Green AI: Evaluating Energy Efficiency for Quantized LLM Inference Authors: Petar Basta Published: 2026-10-13 Categories: cs.LG, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2610.17531v1 While it is known that quantization of large language models (LLMs) reduces memory usage via lower-bit weights, studies quantifying the resulting impact on energy usage and carbon intensity are scarce. We present the first unified evaluation of weight-only quantization strategies for LLM inference across varying input/output lengths and GPUs, highlighting differences in energy efficiency in addition to accuracy degradation and runtime. We study quantized inference on Llama 2 7B, Phi 3.5 Mini Instruct, OLMo 1B, Qwen 2.5 7B, and Qwen 2.5 14B across GLUE MNLI, MMLU, HumanEval, and GSM8K datasets, evaluating 10 post-training quantization (PTQ) strategies on NVIDIA H100, A6000, A100, and L4 GPUs. We identify a novel trend showing that quantization techniques tend to exhibit peak energy efficiency relative to full-precision baselines when inputs are sufficiently long and outputs are short. Furthermore, we show that quantization strategies become marginally more energy-efficient relative to full-precision models as batch sizes increase, though gains are modest. Notably, fused-kernel implementations such as EETQ int8 and Bitsandbytes int8 offer the highest energy savings, up to 4x compared to FP32 on short text generation, with negligible accuracy loss. Finally, we observe that energy usage closely tracks runtime on our evaluated benchmarks, indicating that, in practice, latency optimization can serve as a reliable proxy for reducing the environmental footprint of LLM services. We conclude with suggested directions for strategically selecting low-carbon quantization strategies based on specific inference requirements. --- ### TwinPrune: Density-Aware Two-Phase Token Pruning for Vision-Language Models Authors: Kai Liu, Anqi Li, Junxian Li, Zhixin Wang, Zhikai Chen, Renjing Pei, Yulun Zhang Published: 2026-10-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.17530v2 We propose a unified spatial-density signal to score token importance for both inference phases: bipartite merge for prefill and KV eviction for decode, yielding measurable gains in each stage. To isolate the two phases, we split benchmarks by scoring logic. Prefill probes (MMBench, POPE, ScienceQA) evaluate only the first decoded token; their accuracy reflects prefill logits argmax before any decode KV eviction. Full-pipeline probes (TextVQA, DocVQA, MM-Vet) assess the complete generated sequence and capture both phases. We identify a critical evaluation pitfall: decode pruning claims validated solely on prefill probes measure prefill quality, not decode performance. Experiments show discarding all visual KV during decode barely affects prefill-probe accuracy but degrades TextVQA and MM-Vet drastically; this insensitivity stems from the scoring rule, not compression intensity. Evaluated on seven model variants (InternVL-3.5, Qwen3-VL, LLaVA-1.5) and three full-pipeline benchmarks, our method achieves a three-way Pareto frontier across compute, memory and accuracy. Density-based prefill compression maintains strong accuracy, scales linearly with visual token count, and delivers 100x faster token selection at high resolution. For decode, density top-k KV eviction consistently outperforms strong baselines H2O, SnapKV and StreamingLLM on TextVQA and MM-Vet across three retention ratios. At 0.125 keep ratio on TextVQA, it surpasses H2O by 9.6 points; InternVL-3.5 models (2B to 38B) maintain a 7 to 10 point advantage. Compression scales favorably with model size: every measured 8B to 38B model transition reduces accuracy loss instead of worsening it. We suggest MM-Vet or DocVQA as mandatory full-pipeline validation for any decode-phase claims. Our code is available at https://github.com/Kai-Liu001/TwinPrune --- ### ATTUNE: Agentic Throughput Tuning for LLM Training Authors: Leo Fan, Hongyang Wang, Wenbo Chen, Jingguo Liu, Xian Li, Xuan Wang, Ruochen Wen, Yiming Yan, Hao Wu, Zheshen Wang, Benoit Dumoulin Published: 2026-10-13 Categories: cs.DC, cs.LG arXiv: https://arxiv.org/abs/2610.17528v1 Training recipes are tuned by hand for one model, cluster and workload, and every new model, accelerator, framework version or dataset means tuning again. Automated tuners search a fixed space of knobs and check only that a job runs, yet a configuration can run to completion while it silently changes training. ATTUNE is a single coding agent that tunes any working recipe for the workload and stack at hand, unattended, within a GPU-hour budget the user sets. It diagnoses each run and changes one lever at a time, guided by a catalog of lessons from past campaigns, and ships a recipe only if it passes a correctness gate: a configuration check against objective-changing settings and known stack defects, and a convergence check of its loss curve against the baseline's. On four held-out models at 64-128 GPUs, ATTUNE raises mean throughput over the strongest public recipe run on our stack by 6.7% on Llama-3.1-405B (best campaign 11.9%) and 33.9% on GLM-4.5 (54.7%), whose public recipe was written for H100. It keeps Mixtral-8x22B's recipe, where nothing it finds clears the noise band. Under a common GPU-hour budget it beats OptiCo, Bayesian optimization and random search on GLM-4.5 and MiniMax-M2; on GLM-4.5 its mean gain is more than four times the best alternative's at less than half the GPU-hours, and on both models its tuning pays for itself within a day of training. The gate rejects no legitimate run and catches 16 of 24 faulty runs, missing only ones that barely move the 20-step loss. Ablations tie its best campaigns to one of its search rules: retrying an out-of-memory layout with recomputation. We release ATTUNE's code and TrainingThroughputBench, a leaderboard of the fastest known recipes for MoE models up to 744B parameters on up to 256 GPUs, each with its throughput, cost per million tokens and a passed correctness check, at https://github.com/amazon-science/attune. --- ### Box-WAM: Box Trajectories as Compact State Representations for World Action Models Authors: Qinxi Yu, Wenzhou Ding, Gloria X. Wang, Albert J. Zhai, Shenlong Wang Published: 2026-10-13 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2610.17526v1 World action models (WAMs) are a category of policy models that ex- plicitly predict both actions and future world states. They have been shown to outperform action-only models across various robotic manipulation tasks. How- ever, representing the future with full-frame video prediction can be computation- ally expensive during both training and inference. This raises a central question: what compact state representation preserves the planning and supervision bene- fits of future prediction? In this paper, we propose BoxWAM, which replaces dense future frames with oriented bounding box trajectories of task-relevant ob- jects. By explicitly imagining object-centric future motion, our method provides a lightweight prediction target that captures the key physical changes induced by robot actions. We show that box trajectory prediction substantially reduces com- putational cost while improving action prediction performance, suggesting that object-centric compact states can serve as an efficient alternative to video-based world action modeling for robotic manipulation. Result videos can be found on https://box-wam.github.io --- ### Enhanced Detective: A Dual-Stage Proactive Defense Against Internal Poisoning Attacks in Financial Fraud Detection Using Federated Learning Authors: Maria-Ioana-Andrea Ivan, Orhan Ermis, Ruxandra F. Olimid Published: 2026-10-13 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2610.17523v1 With recent developments in Artificial Intelligence (AI), the adoption of distributed learning paradigms such as Federated Learning (FL) has emerged. In simple terms, FL enables multiple entities to collaboratively train AI models without sharing local data. The FL paradigm is particularly valuable in privacy-sensitive settings, such as financial services, because it enables institutions to collaboratively improve fraud-detection models while keeping sensitive transaction data local. However, FL schemes are prone to security vulnerabilities, where malicious clients can poison local data or model updates and degrade the global model, and hence the performance of the resulting model might be affected. Therefore, in this work, we propose Enhanced Detective, a dual-stage robust aggregation strategy that combines Median Absolute Deviation (MAD), distance-based update filtering, and FedMedian aggregation. Experiments on an imbalanced credit card dataset evaluate targeted label-flipping and weight-scaling attacks over 50 communication rounds. With 40% malicious clients, Enhanced Detective achieves an AUPRC of 0.796 and a Recall of 0.847. --- ### YUBI-Real2Sim: 3DGS Scene Verification for Reliable Policy Evaluation Authors: Hiroki Nishizawa, Takehiko Ohkawa, Nicola Scianca, Tatsuya Matsushima, Shigeo Morishima, Kei Ota Published: 2026-10-13 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2610.17521v1 Evaluating VLA policies on real robots is costly, time-consuming, and difficult to reproduce, making real-to-sim simulation essential for scalable evaluation. While 3D Gaussian Splatting (3DGS) enables rapid real-to-sim scene generation, the reconstruction quality required for reliable policy evaluation remains unquantified. In particular, policies relying on wrist-mounted fisheye cameras (e.g., YUBI handheld gripper data) are heavily exposed to visual artifacts (holes, floaters) in wide-angle views, directly degrading task performance. To address this, we present YUBI-Real2Sim, a unified framework for 3DGS-based scene reconstruction and real-to-sim policy evaluation under dual fisheye wrist views. We develop an integrated pipeline combining 200-degree fisheye camera capture, 3DGS training, 3D foundation models for object modeling, and MuJoCo-based physical simulation, reproducing the observed real-world policy ordering in eight of nine scene-task comparisons. Using this framework, we construct a benchmark across two bimanual robot platforms, three scenes, three tasks, and dual pi0.5-based policies. This systematically measures real-to-sim rank agreement and evaluates policy sensitivity against counterfactual 3DGS artifacts (ceiling holes, floaters, warping) and capture disturbances. We further analyze whether novel-view quality scores can indicate policy-ranking reliability under a scene-held-out evaluation protocol. The results show task-dependent performance and limitations of quality-based reliability prediction, highlighting the need to assess reconstruction quality when using Real2Sim for policy evaluation. These results do not yet establish a generally reliable scene-acceptance rule. Project Page: https://yubi-real2sim.airoa.io. --- ### Gaussian Splatting for Real-Time Scene Reconstruction: Methods, Systems, and Trade-offs Authors: Ashim Dahal, Rabab Abdelfattah, Nick Rahimi Published: 2026-10-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.17513v1 3D Gaussian Splatting (3DGS) allows for high-quality real-time novel-view synthesis. Since its inception in 2023, its explicit and highly configurable scene representation has been extended toward sparse-view generation, dynamic reconstruction, efficiency and compression, streaming, and simultaneous localization and mapping (SLAM). Although Gaussian Splatting can provide real-time rendering, rendering an existing representation is distinct from constructing, updating, or maintaining the scene itself. In this survey, we synthesize current literature, categorize them and provide a connection of current approaches and tools towards an end-to-end pipeline. Explicitly, we categorize GS scene reconstruction into five overlapping families: single-shot generation, dynamic representations, efficiency and compression, streaming and immersive systems, and Gaussian Splatting SLAM. We distinguish render-only throughput from task-specific scene generation, update, tracking, mapping, and optimization costs, and combine controlled sparse-view benchmarking with native evaluations to identify cross-family quality, latency, memory, and update-cost trade-offs. --- ### CÆNL: Collapse-Based Active Neural Learning with Objective-Aligned Representation Control Authors: Saad Alqithami Published: 2026-10-13 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2610.17509v1 Active learning changes the representations used to acquire subsequent labels. We study this interaction through Collapse-Based Active Neural Learning (CÆNL), which separates acquisition, Dynamic Collapse Regularization (DCR), and its coefficient policy. DCR penalizes a normalized within-class to between-class scatter residual above a frozen reference, with a separate class-separation safeguard. Fixed, scheduled, deterministic-feedback, and learned-feedback policies apply this objective. The analysis establishes scatter invariances, conditional local descent, and coefficient bounds, and shows why clean geometry alone cannot guarantee input robustness. Six-seed classification comparisons are complemented by a 104-run study with separate control selection and ten-seed evaluations on each of two backbones. At 60% annotations on ImageNet-100, entropy acquisition with DCR and MACC-Lite reaches 73.420 +/- 0.512% accuracy on ResNet-50 and 73.086 +/- 0.397% on ResNet-18 (mean +/- seed SD), exceeding entropy alone by 1.742 and 1.834 percentage points. Both gains survive Holm correction under paired-t and exact sign-flip tests, with unchanged feedback settings across backbones. Independently tuned constants attain slightly higher mean accuracy; the paired comparisons establish neither adaptive superiority nor equivalence. Separate six-seed spectral studies yield a small fixed-regularization C4 loss reduction, worse CIFAR-10 diffusion FID, and inconclusive AudioCaps captioning effects. Earlier classification studies find near-zero AutoAttack accuracy at L-infinity radius 8/255 and no added benefit from learned control. The results support the evaluated combined classification treatment and identify the task dependence of geometry-informed regularization. --- ### Merit: Making every modality earn its contribution in multimodal attention decoding Authors: Ali Alavi, Donald S. Williamson Published: 2026-10-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.17507v1 More than 1.5 billion people have hearing loss. When several people talk at once, hearing aids amplify every voice alike. Auditory attention decoding (AAD) aims to solve this by reading a listener's brain signals to find the attended talker, letting the device amplify only them. A real device will not see the brain alone; smart glasses and earbuds also track eyes, head, and scene. These behavioral signals help, as people often look at who they listen to. However, they show where a listener looks, not whom they hear. A decoder relying heavily on them fails when a listener cannot move their head or listens without looking - exactly when a brain-based device is needed. A multimodal decoder must use these signals without letting them replace the electroencephalogram (EEG). Accuracy alone cannot show whether it does. We present MERIT, a decoder and evaluation method asking: how much accuracy does each input earn? MERIT shuffles each input stream across test examples, measures the accuracy drop, and splits the result across streams using Shapley values. It also blocks two shortcuts: candidate audio is checked before training so it cannot reveal the answer, and the scoring function cannot beat chance if it ignores the brain. On a public dataset with EEG, eye tracking, head motion, and scene video, MERIT improves on the published benchmark, reaching 0.82 four-way accuracy within listeners and 0.74 on unseen listeners (chance is 0.25). The measurement reveals what accuracy hides: adding behavioral streams raises overall accuracy but almost halves the brain's share of it. On two other datasets, the same tests find a label imbalance in a widely used benchmark and flag results that accuracy alone would report as brain decoding. --- ### Collective Benefits and Efficiency in Coupled Echo State Networks Authors: Polyphony Bruna, Rick Dale, Michael J. Spivey, Christopher T. Kello Published: 2026-10-13 Categories: physics.soc-ph, cs.MA, cs.NE, q-bio.NC arXiv: https://arxiv.org/abs/2610.17506v1 Simple aggregation of independent responses ("wisdom of crowds") generally improves collective performance through statistical facilitation, but interaction among members can sometimes hinder group outcomes. However, under certain circumstances, coordination studies show that interacting groups can outperform their individual members and nominal groups, and interaction can also be more efficient than independence. We present a reservoir computing model to investigate how interaction can enhance joint performance in terms of accuracy and efficiency. Echo state networks were trained independently to identify Japanese speakers from vowel recordings and tested jointly with and without coupled feedback. Model pairs reproduced the dyadic advantage reported by Bahrami et al. (2010) with interaction via pooled-feedback, but not when independent responses were aggregated together. Model dynamics revealed that interaction was beneficial whereas aggregated outputs were prone to diverging from runaway feedback over time. In terms of efficiency, larger groups of smaller interacting models outperformed smaller groups of larger models while equating for total amount of group computation. Our results offer a formal framework for explaining when and why interaction enhances collective intelligence. --- ### Foundation Models for Event Prediction Across Heterogeneous Event Logs Authors: Fabian Spaeh, Sean Jaffe, Shandian Zhe, Bin Shen Published: 2026-10-13 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.17503v1 Event logs are ubiquitous across real-world domains, including business processes, manufacturing workflows, healthcare, and many other operational systems. Yet event logs can differ substantially in their event semantics, label spaces, interaction patterns, and temporal scales, making it difficult to build a single foundation model that generalizes directly to previously unseen systems. We address this challenge with the Foundation Event Predictor (FEP), a simple and scalable in-context architecture that performs next-event prediction through learned, event-level nonparametric inference. Causal self-attention encodes context and target histories into key and query representations, respectively, while the observed next context events are encoded as values. Cross-attention then performs learned, relevance-weighted aggregation of next-event outcomes over all context transitions, allowing the entire nonparametric prediction procedure to be expressed as standard attention operations and efficiently parallelized with modern kernels such as FlashAttention. To promote cross-system generalization, we introduce permutation-robust embedding learning and random fixed embeddings to decouple event IDs from persistent semantics, together with empirical quantile transforms and robust normalization to handle diverse temporal scales. We pretrain FEP on 696 real-world event datasets spanning heterogeneous event systems and evaluate it on 50 held-out datasets unseen during pretraining. Across these datasets, FEP generalizes effectively to new event systems without parameter adaptation, frequently approaching the performance of strong models trained separately on each target dataset while substantially outperforming existing foundation-model baselines, particularly on challenging prediction tasks. --- ### Does Personalization Break Trust? Open-Set Rejection Calibration Under Few-Shot On-Device Intent Adaptation Authors: Vaibhav Prajapati, Pushp Garg Published: 2026-10-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.20652v1 Always-on virtual assistants increasingly personalize on-device to new user-specific commands via few-shot fine-tuning (e.g., LoRA), but this adaptation is evaluated almost exclusively on whether it learns the new commands, not on whether the assistant can still recognize an input that matches none of its intents - the out-of-scope (OOS) rejection problem. We show that naive few-shot LoRA personalization degrades OOS-rejection AUROC (area under the ROC curve) on every one of five public intent-classification benchmarks (mean drop $0.055$--$0.258$, five seeds each), while in-scope accuracy is preserved. A scorer-invariant check shows part of this drop is an artifact of the standard confidence scorer's own miscalibration under adaptation, though a smaller, genuine effect remains under any scorer; we trace it to a measurable shrinkage of the embedding margin around known-intent regions (pooled Spearman rho=0.61$). A deployment-cheap fix is scoring rejection by Mahalanobis distance instead of softmax confidence without extra training/retraining recovers most of the lost quality on 3 of 5 datasets at no accuracy cost, beats two further OOD scoring baselines, and generalizes across shot count, LoRA rank, and a second base encoder. We report honestly where the fix falls short and release all code for reproducibility. --- ### Towards automatic digital garment assembly Authors: Alejandro Rodriguez Published: 2026-10-12 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2610.20651v1 Creating digital garments from existing two-dimensional patterns remains a time-consuming process. Although patterns are widely available in digital form, their assembly in garment CAD software involves manual definition of sewing operations and arrangement of the pattern panels for drape simulation. We present two learning-based approaches that automate both tasks using the 2D vector pattern as their sole input. Our automatic sewing model operates at the segment level, leveraging a Transformer encoder with multiple prediction heads. Our novel architecture supports many-to-many, ordered segment correspondences, as well as hems, overlapping seams needed for multilayer garments, and construction properties such as seam allowances and stitch types, required for the finished virtual garment but neglected by previous methods. A complementary panel-level model predicts body-region assignments, layers, and placement coordinates to initialize the drape simulation. We evaluate both models on a curated dataset of 4,035 professionally assembled garment instances. The sewing model exactly recovers all seam and hem topologies of 63.3\% of test garments, while the arrangement model meets the specified placement criteria for all panels in 66.2\% of test garments. We also integrate both methods into garment CAD software, demonstrating automatic assembly of successfully predicted garments. --- ### TorchSpin: Differentiable Electron Paramagnetic Resonance Simulation in PyTorch Authors: Alec H. Follmer Published: 2026-10-12 Categories: physics.chem-ph, cs.LG arXiv: https://arxiv.org/abs/2610.18924v1 Interpreting electron paramagnetic resonance (EPR) spectra commonly requires repeated forward simulation and optimization of spin Hamiltonian parameters. Established software provides mature simulation and fitting methods, but these calculations are not generally available as differentiable components within machine-learning workflows. We present TorchSpin, an open-source PyTorch framework that ports the organization and numerical conventions of EasySpin into a tensor-based computational environment. Representative calculations spanning continuous-wave EPR, ENDOR, pulse EPR, spin dynamics, trajectory simulation, and magnetometry closely reproduced corresponding EasySpin results. In matched benchmarks, TorchSpin CPU execution was faster than EasySpin for six of nine workloads although performance depended strongly on the calculation. We therefore focused on the capabilities enabled by automatic differentiation in PyTorch. In a Cu(II) powder-spectrum demonstration, feedback propagated through TorchSpin improved the quality of a supervised convolutional neural network (CNN) without using parameter labels during refinement. Models trained from randomly initialized CNNs using only noisy spectra and TorchSpin reconstruction loss achieved median similarities of $\geq$ 0.99. CNNs trained on TorchSpin-generated libraries also transferred without adaptation to independently generated EasySpin spectra with performance comparable to EasySpin-trained controls. Once trained, the CNN produced initial parameter estimates in approximately 1 ms per spectrum while a batch of 512 was processed in approximately 1.3 ms with GPU acceleration. TorchSpin therefore provides both a tested Python implementation of established EPR calculations and a differentiable physical layer for rapid learned inference, spectral refinement, and parameter-label-free training. --- ### Popularity Trajectories and Mixing Patterns of Urban Venues in Two European Cities Authors: Wang Ngai Yeung, Lakmal Meegahapola, Daniele Quercia, Riccardo Di Clemente Published: 2026-10-12 Categories: physics.soc-ph, cs.LG, cs.SI arXiv: https://arxiv.org/abs/2610.18917v1 Urban venues such as restaurants, shops, bars and parks host the daily life of a city, and their collective rise and fall signals how vibrant a neighbourhood is. The usual assumption is that a venue's fortunes follow its neighbourhood's, so that how wealthy an area is and how many people live there will decide a venue's performance. Yet whether there is a common performance trajectory shared by venues over time is underexplored. In this study, we use 5.5 years of Foursquare data for about 10^4 venues in London and Barcelona. We found six distinguishable shapes recur in both cities, that are (1) Fall, (2) Rise, (3) Rise & Fall, (4) Steady, (5) Ephemeral (an early hit that loses popularity fast) and (6) Underdogs (a slow starter that gains popularity late). However, no recovery shape appears, that is neither city yields a U-shaped fall-and-rise group. Additionally, we found that deprivation and population density are not indicative which shape a venue follows. We also discovered that how early a shape can be recognized depends on when its distinctive segment occurs, not a shape's complexity. Proximity between venues, however, does predict how well-performing a venue is. We uncovered a mixing pattern where venues of the same shape tend to locate together more often than chance within roughly 200 to 600 metres. Finally, our qualitative reading of two contrasting districts, one rising in London and one falling in Barcelona, show that comparable socioeconomic conditions but divergent gentrification histories can generate vastly different popularity trajectories. All in all, our results altogether point at that urban vibrancy emerges at the block- and street- level, and social and historical contexts matter in terms of the characteristics of such patterns. --- ### A Sense of Proprioception in Language Models Authors: Jonas Geiping Published: 2026-10-12 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2610.17495v1 In humans, proprioception corresponds to the sense of self-movement or position, e.g. understanding the position of one's arm. This sense is often less well-understood and in popular understanding sometimes conflated with introspection. But, notably, proprioception is a separate sense, with dedicated receptors and verifiable outcomes. On the other hand though, language models cannot observe their own internal states during training (and for example answer the question which experts activated in a certain layer of an MoE) and so cannot accurately report on them. Yet, such information is, by virtue of being internal to the model, both accessible, and readily constructed into verifiable signals. We argue that this provides the basis for a digital analog of proprioception. As such, we train models through SFT and on-policy training to equip them with this ability. We show that modern models can be trained to understand a range of subtypes of proprioception, such as routing decision awareness, token entropy, decision depth or logit lens information, without affecting model capabilities. We then run these models through a broad evaluation of situational awareness, legibility, and epiphenomenality, to evaluate in what ways access to proprioception changes model behavior. --- ### Longitudinal Learner Participation Profiling in Online Learning: Heterogeneous Consensus Clustering under Unequal Observation Windows Authors: David Otoo-Arthur, Terence L. van Zyl Published: 2026-10-12 Categories: cs.LG, cs.CY arXiv: https://arxiv.org/abs/2610.17494v1 Learning management system traces are clustered to identify participation profiles, but unequal observation windows may cause profiles to reflect duration rather than participation alone. Using 16,448 complete learner--course sequences from 4,599 learners across 152 courses at a South African public university, we evaluated eight participation measures. All remained related to observation-window length even when expressed as rates or shares. Course-grouped adjustment reduced these relationships. Five retained measures were evaluated using K-means, Gaussian mixtures, Ward agglomerative clustering and K-medoids, with standardised measures and principal-component summaries. Evidence supported a broad two-profile grouping and a more detailed adjusted four-profile consensus: Gradually declining, Early-concentrated, Cyclical variable and Sustained active. Profile membership accounted for 2.87% of the variation in duration in the primary consensus, versus 38.18% using original measures. Mean assignment support was 0.739; 8.35% of assignments fell below 0.50, with greatest uncertainty in Sustained active. Two week-by-week sequence analyses agreed strongly with each other but only modestly with the four-profile consensus, indicating that the profiles combined multiple aspects of participation rather than distinct sequence patterns. Profiling should therefore assess duration effects, compare clustering methods and participation summaries, and report assignment consistency. --- ### VeriPIE: Checkable Query Plans and Evidence-Guided Selection for Text-to-SQL Authors: Piyush Jha, Cruise Song, Zhengyu Li, Yatharth Sejpal Published: 2026-10-12 Categories: cs.LO, cs.AI arXiv: https://arxiv.org/abs/2610.17493v1 Financial Artificial Intelligence (AI) governance and model risk management (MRM) emphasize independent validation, transparency, and effective challenge of AI-generated computations. Text-to-SQL translates natural-language questions into Structured Query Language (SQL), but queries that agree on one database can still express different computations. We present VeriPIE, a neurosymbolic framework combining language-model generation with symbolic checks. It ensembles direct SQL generation with QuerySketch, a structured plan language checked by a backend implemented in Lean, a theorem prover and programming language. Plan diagnostics guide repair before SQL generation, while execution agreement and bounded searches for distinguishing databases inform candidate selection. These checks expose malformed plans and hidden disagreement without proving agreement with the user's intent. In single-run experiments on the complete Spider development set, VeriPIE achieves 72.05% test-suite accuracy (745/1,034), compared with DeepEye's 65.67% (679/1,034). Its two-query shortlist covers 78.43% (811 questions), compared with 74.66% for DIN-SQL (772) and 69.05% for DeepEye (714). On BIRD, VeriPIE reaches 68.90% execution accuracy and 73.73% two-query coverage. The central benefit is reviewable evidence about the generated computation: explicit plan checks, repair diagnostics, and concrete disagreements that support safer financial analysis. --- ### A Time-Synchronous Prequential Evaluation Framework for Next-Week Student Disengagement Prediction from Moodle LMS Logs Authors: David Otoo-Arthur, Terence L. van Zyl Published: 2026-10-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.17490v1 Retrospective evaluation of early-warning models may not reflect information available when predictions are issued and outcomes become observable. We developed a time-synchronous prequential framework for online prediction of next-week student disengagement, operationalised as inactivity onset, from Moodle logs. Ordered by calendar time, models were updated only with available outcomes and remained unchanged for all predictions at each prediction cutoff; development, calibration and evaluation were chronologically separate. We compared stochastic gradient descent logistic regression (SGD-LR), online sequential extreme learning machine (OSELM) and echo state network (ESN) across predictive performance, fixed, frozen and rolling threshold policies, calendar-time variation and four behavioural feature sets. Held-out evaluation comprised 49,329 predictions with 37.68% inactivity-onset prevalence. Discrimination was similar (average precision 0.665-0.679; ROC-AUC 0.755-0.774). OSELM had the highest recall, SGD-LR the highest precision and specificity, and ESN the highest Matthews correlation coefficient and balanced accuracy. Lower thresholds increased recall and alert volume, whereas rolling adaptation did not improve MCC over frozen thresholds. Weekly performance and calibrated-probability distributions varied without sustained deterioration. During model selection, cumulative-and-temporal features achieved the highest individual-set AP, with modest gains from combining all feature groups. These findings indicate that streaming early-warning evaluation should consider calibration, threshold-dependent performance, alert burden and calendar-time variation alongside aggregate discrimination. --- ### Structure-preserving fidelity diagnostics for partial differential equations Authors: Kyriakos Flouris Published: 2026-10-12 Categories: cs.LG, physics.comp-ph arXiv: https://arxiv.org/abs/2610.17483v1 Machine learning surrogates of partial differential equations (PDEs) are commonly trained on data generated by numerical solvers. Therefore, the training data obey not the PDE but the modified equation of the numerical scheme, and the test loss, computed on data from the same solver, cannot distinguish a model that learned the physics from one that learned the discretization error. Here, we show that the difference is nevertheless visible in the trained model. We propose a suite of structure-preserving fidelity diagnostics, simple scores that measure whether a learned model respects one known property of the physics, such as a conserved quantity, a symmetry or a Hamiltonian structure, without access to the training data or the governing equation. Over five systems, the diagnostics track the error with respect to the true dynamics with a rank correlation of up to $0.94$, while the test loss is uncorrelated or anti-correlated with it. For the Burgers, Korteweg-de Vries and Navier-Stokes equations, the diagnostics separate numerical schemes that the test loss ranks as equivalent, including schemes of the same order. order. --- ### REA: From Correct LLM Judgments to Safe Decision Delivery Authors: Jingxiang Meng, Aofan Liu, Yaoshuai Ma, Fangxin Liu, Yongbiao Chen Published: 2026-10-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.17473v1 Generative safety guards must classify requests correctly and return outputs that applications can parse. Reasoning guards can improve classification accuracy while producing outputs that applications cannot parse. When applications cannot extract a correct prediction, fallback handling can allow harmful requests or block safe ones. We introduce Resolve--Express--Act (REA), a framework that traces judgments through parsing and fallback to application actions. Experiments on classifiers and safety guards show that correct predictions can appear in incorrectly formatted outputs. Parsing the safety verdict preserves the reasoning guard's accuracy advantage, while stricter explanation requirements reject additional correct predictions. Accepting formatting variations recovers most rejected correct predictions. Held-out tests confirm that output requirements and generation limits affect whether correct predictions can be parsed. In our fail-open replay, matching the parser to the output and fixing formatting reduced the fraction of harmful requests allowed despite correct guard judgments from 95.5% to 0%. A fixed-output comparison shows that model-based extraction can preserve guard verdicts, but is not automatically reliable; deterministic normalization already repairs the observed native-format failures. Fallback replay shows that the same correct prediction can lead to different safety actions depending on the parser and fallback policy, including allowing requests the guard correctly identifies as harmful. --- ### Scaling Inference-Time Compute with Teams of Coding Agents Authors: Keenan Samway, Daniel D'souza, Omar Darwiche Domingues, Marzieh Fadaee, Tan Yi-Chern, Nouha Dziri Published: 2026-10-12 Categories: cs.MA, cs.CL arXiv: https://arxiv.org/abs/2610.17471v1 Multi-agent systems promise a new axis for scaling inference: rather than having one agent think longer or sample more attempts, a task is split across many agents that work in parallel and coordinate. However, in practice, more agents can easily produce duplicate work, coordination failures, and higher costs. We therefore formulate team design as a compute allocation problem: starting from a solo agent, where should additional inference compute go to reach the reward-cost Pareto frontier? We build a minimal multi-agent harness from the ground up and trace this frontier by varying, one at a time, the workflow stage at which a lead delegates to its workers (planning, implementation, or verification), the models that form the team, and the number of workers. On ProgramBench, teams outperform solo agents but cost three to seven times as much. With the right compute allocation, however, a heterogeneous 17-agent team comes within 1.4 points of a strong homogeneous 5-agent team at 70% lower cost. This efficiency stems from three findings. First, planning is the most valuable use of workers: in a homogeneous team whose lead decides how many workers to spawn, a lead that delegates only planning to its workers, and then implements and verifies the code itself, matches the reward of a lead that delegates to workers throughout planning, implementation, and verification, at half the cost. Second, cheap models pay off as planners but not as implementers: a strong lead with cheap planners recovers 47.5% of the reward gain of an all-strong team for only 13.9% of its additional cost, whereas cheap implementers lower reward. Third, planners keep improving reward as the team grows, whereas implementers and verifiers plateau beyond four workers. Together, our results offer a guide to spending an agent budget where it counts, given the task, cost, and latency constraints a user has. --- ### Assessing the Performance of AI Models in Misinformation Detection Using Predefined Social Noise Constructs Authors: Manar Alsaid Published: 2026-10-12 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.17469v1 Social media platforms generate vast volumes of user-generated content that often obscure meaningful discourse, a phenomenon conceptualized as social noise. While existing misinformation detection methods primarily focus on factual verification, they largely overlook the role of social noise in amplifying misinformation. This study assesses the performance of six text-based models and a graph neural network (GNN) in mitigating the effects of misinformation using predefined social noise constructs. The dataset consists of 500,000 tweets collected from the X platform using the Ukraine hashtag during the Russia-Ukraine conflict from March 2024 to March 2025. Advanced machine learning models achieve strong performance, with accuracies ranging from 79.94% to 97.17%. RoBERTa demonstrates the highest performance, with an accuracy of 97.17%, Cohen's kappa of 0.9660, MCC of 0.9660, and AUC of 0.9977. The GNN achieves an accuracy of 64.52% and an AUC of 0.899, demonstrating performance above random-chance classification by exploiting the relational structure between tweets. All text-based models achieve kappa values greater than 0.75, indicating substantial overall agreement. Explainable AI analysis using LIME reveals that 89.6% of predictive weight is attributed to contextual features rather than isolated keywords. The findings highlight that integrating social noise into AI pipelines enhances misinformation detection and supports more effective mitigation strategies in large-scale social media environments. --- ### From Orbit Matching to Docking: A Hierarchical Reinforcement-Learning Approach to Multiphase Rendezvous Trajectory Design Authors: Mariko Storey-Matsutani, Anatoly Zlotnik, Lee Holguin, Zigfried Hampel-Arias, Richard Linares Published: 2026-10-12 Categories: cs.RO, cs.LG, eess.SY arXiv: https://arxiv.org/abs/2610.17468v1 As the complexity of space missions increases, autonomous spacecraft guidance must accommodate transitions between mission phases with distinct dynamics, objectives, and constraints. Rendezvous and proximity operations (RPO) are particularly challenging because they span multiple operating regimes, from orbital-scale matching and far-range approach to close-range maneuvering and terminal docking. Existing reinforcement-learning approaches generally address only a subset of this sequence or rely on manually defined switching conditions between controllers. This study presents a hierarchical reinforcement-learning framework for autonomous, three-degree-of-freedom RPO that spans the complete trajectory from orbit matching to docking. Five specialized policies are trained for orbit matching, far-range approach, mid-range approach, close-range approach, and docking. A learned high-level manager policy then selects among these phase-specific controllers based on the evolving spacecraft state. The hierarchical approach is evaluated over the full end-to-end rendezvous sequence and compared with a fixed sequential-invocation heuristic to assess trajectory performance and transition behavior. Training and inference metrics are also analyzed for the individual phase policies and the complete hierarchical system. --- ### Efficient Fréchet Distributional Decoder Alignment for Latent Generative Models Authors: Xianghong Fang, Jiajun Zhu, Esma Aimeur, Dehan Kong, Tim G. J. Rudner Published: 2026-10-12 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2610.17466v1 Fréchet Distributional (FD) objectives provide an effective distribution-level signal for post-training generative models. For latent generative models, however, existing FD-based post-training methods optimize only the latent generator while keeping the decoder frozen: the decoder is trained on reconstruction latents obtained from real images but deployed on generator-produced latents at generation time. When these latent distributions differ, this \textbf{decoder train-generation mismatch} means that the decoder is deployed on inputs drawn from a distribution it was not directly trained on. We introduce \textbf{Fréchet Distributional Decoder Alignment (FDDA)}, an efficient post-training method that freezes the latent generator and directly optimizes the decoder on generation-time latents using an FD objective. A single epoch of FDDA consistently improves gFID and gFDr$^6$ across diverse flow-based and autoregressive latent generative models. Across all 11 evaluated models, FDDA reduces gFDr$^6$ by 34.0-59.6\% from the original pretrained models and provides a further 10.2-57.2\% reduction after generator-side FD post-training. FDDA also reduces total wall-clock time by factors of $3.6\times$-$328.7\times$ relative to generator-side FD post-training across these models. These results show that generator-side post-training alone does not exhaust the benefits of FD optimization, and that further gains can be obtained by adapting the decoder at substantially lower cost. --- ### An FPGA-Based Spiking Neural Network for Spatiotemporal Pattern Learning and Classification Authors: Jingang Jin, Yue Ma, Zhenhang Zhang, Qinru Qiu Published: 2026-10-12 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2610.17463v1 Spiking Neural Networks (SNNs) are promising for energy-efficient spatiotemporal pattern recognition at the edge, but efficient deployment and on-device adaptation require specialized hardware. In this work, we present an FPGA implementation of multilayer SNNs for spatiotemporal pattern classification, in which both inference and training take place on the same hardware. Our design adopts a temporal-forward-only training algorithm that avoids the memory and latency overhead associated with traditional Backpropagation Through Time (BPTT). A mixed-precision scheme balances training stability with resource efficiency, and architectural optimization maximizes hardware and memory utilization. We further identify and resolve hazards that arise when inference and learning share the same memory, including port conflicts between the forward and backward access patterns and read-after-write dependencies in floating-point potential accumulation. Experimental evaluations on MNIST and five multivariate time-series classification datasets demonstrate that, with fully on-chip training, our SNN model achieves accuracy comparable to SNN or LSTM trained with BPTT. Compared to CPU and GPU based implementations, our FPGA design delivers 2.5 to 6 times higher throughput while consuming an order of magnitude less energy per sample. --- ### Distilling Text LMs into Speech-to-Speech LMs by Matching Internal Text Predictions Authors: Ju-Chieh Chou, Jiawei Zhou, Karen Livescu Published: 2026-10-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.17461v1 Text language models (LMs) acquire broad linguistic and factual capabilities through large-scale pretraining, while comparable capabilities remain difficult to learn from speech alone. Recent work has shown that knowledge distillation from pretrained text LMs offers a promising way to transfer their linguistic and factual capabilities to speech models. However, existing distillation approaches have largely focused on speech-input, text-output models. This idea has yet to be explored for {\it speech-to-speech} models, which operate on both speech input and speech output. In this work we introduce a speech-to-speech pretraining method that creates an internal text interface for knowledge transfer while preserving the speech-only input and output. The model first consumes speech context without its transcription, switches to text prediction, and then uses the predicted text to lead future speech generation word by word. It also provides an interface for knowledge distillation: the internal text predictions can be directly distilled from the base text LM. To the best of our knowledge, this is the first application of text LM distillation to a speech-to-speech LM. Under matched training conditions, the proposed sequence construction substantially improves the generative perplexity of spoken continuations over speech-only and interleaved speech-text models, approaching the performance of a text-leading inner-monologue model with external ASR prompt transcription. More importantly, distillation improves factual performance under both text and speech evaluation, indicating better retention of knowledge from the base text language model. --- ### Selective Inference for Clustering Under Unknown Covariance Authors: Yiqun T. Chen, Lucy L. Gao Published: 2026-10-12 Categories: stat.ME, cs.LG, stat.AP arXiv: https://arxiv.org/abs/2610.17458v1 Unsupervised clustering is widely used to discover underlying group structure, after which researchers often seek to validate these groups via post-hoc hypothesis testing on the population means. However, using the same data both to form clusters and to test for a difference in means inflates the Type I error rate. Recent work in selective inference has proposed solutions when the underlying data are drawn from a multivariate Gaussian distribution with a known covariance matrix or an unknown isotropic covariance matrix. We propose a new selective test for the difference in means between two clusters that provably controls the Type I error rate under an arbitrary unknown covariance matrix. Our test statistic does not require estimating the feature covariance matrix; instead, it leverages a Monte Carlo sampling procedure over the set of orthogonal matrices. We show that this new selective test can be computed efficiently, and we derive closed-form solutions when clusters are formed using k-means or hierarchical clustering. In simulations, we demonstrate that our proposed p-value controls the selective Type I error rate and achieves substantial power, and we illustrate its application on gene expression and drug review data sets. ---