# Research Papers — 2026-10 · bundle page 28 of 156 > Full-text markdown of papers #1351–1400 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/28 [← Previous bundle](https://aipod.dev/papers/archive/2026-10/page/27.md) [Next bundle →](https://aipod.dev/papers/archive/2026-10/page/29.md) ### Contextual Credit Policy Optimization Authors: Huiwen Han, Ziyao Zeng, Zihao Zhu, Sisong Bei, Hao Wang, Hongyu Xu, Yan Han, Degui Zhi, Zhiwen Fan Published: 2026-10-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.19103v1 Group-based reinforcement learning enables large language model agents to learn from sparse outcome rewards in long-horizon tasks. Recent methods derive step-level credit by comparing observation-matched experiences across trajectories. However, identical observations can occur in different contexts, and matched peers are not equally informative for a given decision. Moreover, favorable terminal outcomes can obscure redundant actions or detours within successful trajectories. To address these two challenges, we propose Contextual Credit Policy Optimization (CCPO). For the first, CCPO weights observation-matched peers from other trajectories by contextual similarity, computed from frozen LLM representations and accumulated trajectory statistics, allowing peers from similar contexts to contribute more to a step's baseline. For the second, CCPO pairs historical credit, which compares the realized return against the weighted peer baseline, with future credit, which measures the change in contextual outcome value over a short realized continuation. A step is thus credited for the progress it makes, not only for its trajectory's eventual outcome. Both credits are computed in hindsight from rollouts already collected for training, enabling CCPO to address these challenges without an auxiliary value critic. Across two Qwen2.5-Instruct backbones (1.5B and 7B), CCPO achieves up to 97.4% success on ALFWorld and 79.4% on WebShop and outperforms GRPO by up to 21.6 and 18.5 points. Ablations show that contextual weighting outperforms uniform weighting, and that historical and future credit serve as complementary learning signals. --- ### The Gap Is in the Geometry: A Convergent Meta-Analysis of Multi-Facet Aerial and Remote Sensing Video Understanding Authors: Georgios Angelidis, Aggelos Psiris, Maria Vakalopoulou, Georgios Th. Papadopoulos, Giorgos Sfikas, Iraklis Varlamis Published: 2026-10-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.19102v1 Aerial and remote sensing video is increasingly evaluated like web video, by posing multiple-choice questions to multimodal large language models (MLLMs) over sampled frames and reporting accuracy. This paper argues that this recipe measures the wrong aspect, and supports the claim with a convergent meta-analysis of a broad set of published results, organized in four evidence tiers, in which a claim becomes a position only when collected evidence agrees. Parameter scale exhibits a median of +3.4 accuracy points per tenfold increase on aerial benchmarks, far below a human gap of at least 19 points, whereas acquisition conditions control perception, as 315 of 318 evaluations in 19 within-paper contrasts lose accuracy when conditions such as altitude, view, object size or time horizon become harder. No aerial benchmark in the corpus combines video input with per-task human and random baselines, competence collapses from answering to acting in closed-loop navigation, and the same MLLMs score higher on the aerial benchmark than on ground spatial ones, but lower on studies that test cross-view geometry. From these findings the current study derives five falsifiable principles and proposes the AVU-Card, a reporting card for aerial video benchmarks --- ### GroundGUI: GUI Grounding by High-Quality Data and Distillation-to-Reinforcement Learning Authors: Qingsong Xie, Jiahao Tian, Jiacheng Tang, Zhifeng Li, Madalina Ciobanu, Navan Preet Singh, Qingqing Mao, Ritankar Das Published: 2026-10-13 Categories: cs.AI, cs.CL, cs.CV arXiv: https://arxiv.org/abs/2610.19100v1 Constructing robust GUI agents relies on multimodal visual grounding: the ability to precisely map natural language intents to actionable on-screen components. Despite abundant desktop, web, and mobile benchmarks, high-fidelity resources tailored for diverse environments are surprisingly scarce. To bridge this gap, we introduce the Screen Referring Grounding Dataset (ScreenRef), a comprehensive GUI grounding dataset consisting of GUI screenshots paired with natural language referring expressions and box or point annotations. Spanning desktop, web, and mobile domains, ScreenRef comprises 586K screenshots and over 633K referring expression instances, covering tasks such as text recognition, visual matching, spatial understanding, and refusal scenarios. To boost the model's grounding performance, we propose the Distillation-to-Reinforcement Learning (D2RL) method to address the limited generalization of supervised fine-tuning and the sparse reward problem in reinforcement learning. Utilizing ScreenRef, we train Qwen3-VL-8B-Instruct via sequential SFT and D2RL training, yielding GroundGUI-8B. GroundGUI-8B achieves 95.2% on ScreenSpot-V2, 63.9% on ScreenSpot-Pro, 65.4% on OSWorld-G, 86.8% on MMBench-GUI L2, and 38.3% on UI-Vision. Among 8B-scale models, it produces substantial gains over models trained on open-source datasets, with performance comparable or even superior to models trained on closed-source data. Code, models, and datasets are available at https://github.com/PrentisAI/GroundGUI. --- ### Similar Models, Broken Odds: Where Luce's Axiom Fails in Chatbot Arena Authors: Soovadeep Bakshi, Apurba Bose, Aishwarya Bose, Sandip Nandi Published: 2026-10-13 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2610.19095v1 Chatbot Arena ranks language models with the Bradley-Terry model, which gives each model one score and so assumes Luce's choice axiom. Choice theory predicts where this fails: near-copies are told apart more decisively than their scores imply. On 1.8 million Arena votes, votes between versions of one model are 1.37 times as decisive as Bradley-Terry predicts, between sizes of one generation 1.26 times and between models of one lab 1.12 times; a release a year later gives consistent multipliers, and the effect survives alternative tie treatments, prompt subsets and topics, and timing checks. How alike two models' answers are worded and formatted tracks the effect. A correction with four to six parameters predicts held-out votes better than Bradley-Terry and than models with hundreds of parameters, mostly by modelling ties; frozen and carried to new releases in a test fixed in advance, its gains are concentrated in ties, and better head-to-head odds are not established. The leaderboard order barely moves. With language-model judges and three-answer menus, a near-copy takes votes mostly from its twin when choices are pooled over prompts (log-odds shift +0.10, 95% interval 0.05 to 0.16); within a prompt the shift is smaller and clear for two of four judges. --- ### DexMimic: A Generalist Dexterous Hand-Object Tracking Policy via Value-Guided Reset Allocation Authors: Zhexi Luo, Zhixuan Xu, Rui Yang, Zeyu Xiao, Yiwen Hou, Lin Shao Published: 2026-10-13 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2610.19089v2 Achieving human-like dexterous manipulation remains a central challenge in robotics. Learning from human hand-object interaction (HOI) datasets offers a promising pathway to diverse dexterous skills, yet existing physics-based approaches train specialist policies for individual trajectories, thereby limiting skill reuse at scale. We introduce DexMimic, a generalist dexterous hand-object tracking policy jointly trained across diverse HOI trajectories. Efficient joint training requires allocating each rollout to both an undertrained phase and a starting state that supports continued tracking. DexMimic realizes this insight through Value-Guided Reset Allocation, which adapts the initialization distribution online to prioritize difficult phases and select reset states with higher expected tracking returns. We further introduce a benchmark spanning training, fine-tuning, and generalization. Experiments show improved tracking success and training efficiency, faster fine-tuning, and the potential for zero-shot generalization to unseen trajectories and objects; larger training sets further improve efficiency and generalization. Finally, we validate DexMimic on a real-world dexterous manipulation platform. --- ### Beyond Aggregate Accuracy: Item-Level Transitions in Prompt Optimization Authors: Chinmoy Mitra, Tarek Mahmud Published: 2026-10-13 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2610.19084v1 Automatic prompt optimization (APO) uses feedback from model responses to improve prompts automatically. However, its effectiveness is usually measured through overall scores, which do not reveal which questions become correct, which previously correct answers become wrong, or whether improvements extend to unseen questions. We introduce Reflective Feedback-Driven Prompt Optimization (RFDPO), a tool that tracks recoveries (incorrect to correct), regressions (correct to incorrect), and churn (all changed outcomes). RFDPO uses this feedback to guide subsequent revisions and records prompt changes throughout optimization. We evaluate RFDPO across five benchmarks covering law, knowledge, instruction following, mathematics, and privacy, using GPT-5 as the optimizer and GPT-4o-mini and GPT-4.1 Mini as solvers. Our results show that overall accuracy can hide substantial changes: in five of nine configurations, churn was at least five times the absolute net change, and a single-item net change concealed up to 17 changed outcomes. Average validation gains were 7.9 percentage points, compared with 5.2 points on held-out tests. In a controlled ablation on LegalBench-Hearsay, item-level feedback reduced churn by 40% ($p=0.024$) while maintaining similar net gains. These findings motivate reporting recovery, regression, churn, and performance on unseen data alongside overall accuracy. --- ### Backpropagating Verifier Rewards Through Continuous Flow Language Models Authors: Xu Han, Jiajing Hu, Li-Ping Liu Published: 2026-10-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.19080v1 Reinforcement learning (RL) has substantially improved the reasoning of autoregressive and discrete-diffusion language models. Language models that generate continuous token embeddings are emerging as a strong alternative, but RL post-training for them remains understudied. We propose \method{}, a post-training framework for continuous flow language models. Such a model denoises token embeddings over multiple steps and decodes them into discrete tokens only at the last step. To obtain pathwise gradients, which backpropagate through continuous actions and have much lower variance than REINFORCE, we introduce a critic that estimates the value of intermediate token embeddings, bypassing the non-differentiable decoding step. The critic must also keep track of the value function as the policy changes; to this end, we design a critic that predicts a value from every token representation and improves policy optimization. Across four reasoning tasks, \method{} reliably improves a continuous flow language model through RL post-training and outperforms baseline methods of the same type. --- ### Theoretical and Practical Advances in Hierarchical Bayesian Deep Learning Methodology Authors: Neil K. Chada, Simon Cotter, Kody J. H. Law, Xinzhu Liang Published: 2026-10-13 Categories: cs.LG, stat.CO, stat.ME arXiv: https://arxiv.org/abs/2610.19074v1 Reliable uncertainty quantification remains an important challenge in AI. Hierarchical Bayesian methods provide a principled framework for this by representing unknown quantities through posterior distributions. Joint inference of neural-network parameters and prior hyperparameters is challenging for conventional Markov chain Monte Carlo (MCMC) methods due to strong dependencies. In this work, we introduce the multilevel particle marginal Metropolis-Hastings (MLPMMH) method, which combines pseudo-marginal inference for the hyperparameters with coupled sequential Monte Carlo (SMC) across hierarchy of network-width truncations for conditional parameter inference. The hierarchy is induced by a trace-class neural network (TNN) prior with width-dependent decay, motivated empirically by the compressible structure observed in trained neural-network parameters. Under standard multilevel coupling assumptions, we establish that MLPMMH achieves mean-square error (MSE) $\mathcal{O}(\varepsilon^2)$ at expected computational cost $\mathcal{O}(\varepsilon^{-2})$, and verify the predicted rate on a Bayesian regression problem. To address larger-scale applications, we further introduce S-MLPMMH, a practical approximation that replaces the exact sampling components with a PCA-based hierarchy and scalable Bayesian Monte Carlo. Experiments on MNIST demonstrate competitive predictive performance and uncertainty quantification while exploiting the parallel structure of the approximation. Software has been made publicly available at https://github.com/submission-code-anon/mlpmmh-anon. --- ### MonoMIP: Multi-Height Inverse Perspective Mapping for Monocular 3D Object Detection Authors: Emir Ulurak, Furkan Kıraç Published: 2026-10-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.19071v1 Monocular 3D object detection methods increasingly rely on depth-guided transformers, but they operate entirely in the perspective image plane where spatial relationships are distorted by foreshortening. We propose MonoMIP, a dual-decoder framework that adds complementary 3D geometric reasoning through Bird's-Eye View (BEV) features constructed via Multi-Height Inverse Perspective Mapping. We perform IPM at K elevation planes spanning ground to rooftop, producing an ordered stack of height-conditioned metric BEV features that reduces above-ground misprojection and exposes depth-dependent appearance variation across planes. A BEV decoder with multi-scale deformable attention aggregates this multi-height evidence per query, while a depth-guided 3D decoder provides complementary perspective-space predictions. Without extra training data, MonoMIP attains 25.84% Moderate AP3D|R40 on KITTI val and 21.66% on the official test set for Car, outperforming recent published monocular methods on both the KITTI and Waymo benchmarks. --- ### Plan or Retrieve First? A Scale Study of Tool Discovery Architectures Authors: Mingfei Zhang, Amit Surana, Ziauddin Majid, Chenxi Wang, Michael Xu Published: 2026-10-13 Categories: cs.AI, cs.IR arXiv: https://arxiv.org/abs/2610.19068v1 Tool-augmented LLM agents discover relevant APIs from large registries before planning execution, yet finite context windows prohibit injecting all tool definitions into a single prompt. The dominant approach, which we term Retrieve-then-Plan (RtP), embeds the user query and retrieves similar tools via approximate nearest-neighbor search. We study an alternative Plan-then-Retrieve (PtR) paradigm in which the LLM first generates Abstract Tool Stubs (hypothesized function signatures describing needed capabilities) which then serve as retrieval queries against the registry. Evaluating on ToolBench (46,984 unique API endpoints, 50 categories) across single-tool (G1), intra-category multi-tool (G2), and cross-category multi-tool (G3) query subsets, we find a clear complexity-dependent crossover: RtP outperforms PtR on single-tool queries while PtR outperforms RtP on multi-tool queries. This crossover holds at every retrieval budget (k=1 to 20), is robust across registry sizes from 1k to 47k APIs, and is consistent across model families (Gemini 2.5 Flash and gpt-oss-120b). We characterize a stub-hallucination failure mode (the LLM invents plausible but non-existent API names) that acts as a double-edged sword: on simple queries PtR's stubs abstract away proper-noun signals that RtP matches directly, yet on complex queries the same mechanism decomposes multi-faceted intent into functional sub-needs. We further analyze token overhead and show that PtR's extra discovery call roughly doubles inference cost, which pays off on multi-tool queries but hurts on single-tool ones, motivating complexity-adaptive routing as a practical direction, one that can be driven by a zero-cost signal already present in the pipeline (RtP's top-1 retrieval score). --- ### Revisiting Generative vs. Dense Retrieval: A Static Value Prior Reverses the Gap Authors: Renbo Tu, Yang Liu, Shuying Sun Published: 2026-10-13 Categories: cs.IR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2610.19065v1 Generative retrieval (GR) has emerged as a strong candidate generator for sequential recommendation as language models and semantic-item identifiers have improved. However, GR is not a uniformly stronger replacement of dense retrieval (DR) in online retail candidate generation. We examine their differences on two Amazon Toys datasets under different metrics. GR leads on best relevant item value among users both methods cover, while DR leads on exact-target recall and relevant value across the ranked list. With deep analysis, we find that popularity contributes the most to GR's measured value lead. Adding the same static item value to DR in one reranking step reverses this lead and keeps recall above GR. Finally, on an industrial-scale internal e-commerce dataset with LLM-judged relevance, we show that a 14B SID-LLM still underperforms a $47\times$ smaller dense encoder. --- ### How Inner Optimizers Shape Replica Scaling Authors: Eugene Belilovsky, Stefan Horoi, Edouard Oyallon, Benjamin Thérien Published: 2026-10-13 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.19064v1 Training large language models (LLMs) across geographically distributed and poorly interconnected compute pools or data centers has become a topic of significant interest. This has led to increased study of local optimization methods such as DiLoco for LLMs, especially those that use local (or inner) adaptive or preconditioned optimizers, which are critical for high-performance LLM training. However, a central challenge remains: it is well known that increasing the number of model replicas (replica scaling) while fixing the total training budget leads to monotonically decreasing performance. Existing work has empirically demonstrated that the choice of inner optimizer (Muon v.s. AdamW) can significantly improve this trend, but offers only limited explanation of the performance difference. In this work, we consider a range of inner-optimizers and identify two important factors that impact replica scaling: (1) the covariance structure of the pseudo-gradients and (2) the impact of batch size on the pseudogradient's noise scale. Based on these insights, we theoretically and empirically demonstrate that whitening-based pre-conditioning is a powerful inner-optimizer desideratum. Our empirical evaluation extends the results to reveal that whitening-based inner-optimizers achieve strong replica scaling (for 8-96 replicas), with performance relative to DP improving as parameters and data are scaled. --- ### WorldMemBench: A Comprehensive Benchmark for Memory of Video World Models Authors: Nan Zhou, Jianxiong Gao, Qiuyu Wang, Wen Wang, Jiahao Wang, Yufeng Yuan, Shuaiting Li, Hao Ouyang, Yujun Shen, Weiming Lu, Jun Xiao, Yueting Zhuang et al. Published: 2026-10-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.19063v1 As video models enable longer and more realistic interactive experiences, maintaining a world consistent with its history becomes essential. This requires both preserving previously observed content and ensuring coherent world evolution over time. World memory is a critical capability to evaluate alongside visual fidelity and video duration. We introduce WorldMemBench, a benchmark for systematically evaluating world memory in video world models. Across 260 test cases, it assesses static memory through the retention of human identity and appearance, object appearance and geometry, and environmental content and geometry, and dynamic memory through event progression and state persistence. Using controlled camera departures and multi-revisit trajectories, the benchmark evaluates static content against fixed initial references and dynamic events against expected state transitions. It combines appearance and geometry metrics with event-specific assessments, and reports video quality and camera-following accuracy as complementary diagnostics. Evaluation of nine representative models shows that strong static retention does not imply reliable dynamic state evolution, while repeated revisits reveal memory degradation beyond the first return. Human studies support the alignment between our automatic evaluations and human judgments. WorldMemBench provides a systematic testbed for diagnosing memory failures and guiding the development of persistent, temporally coherent video worlds. --- ### RLPE: Teaching LLMs to Prompt with Reinforcement Learning Authors: Rahul Singhal, Karime Maamari, Pradyumna Tambwekar Published: 2026-10-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.19062v1 Prompting is a widely used method for adapting general-purpose LLMs to domain-specific tasks. Effective prompts can be tedious to create manually, so prompt writing is increasingly handed to LLMs, with recent work training LLMs to write prompts for other models. These techniques either write prompts without observing how the task model behaves, blind to the failure modes the prompt should address, or must run alongside the task LLM at inference time, adding overhead to every query. Neither reflects how prompt engineering is often practiced. To close this gap, we introduce Reinforcement Learned Prompt Engineering (RLPE), which trains a model to analyze traces of a separate task model and write a prompt targeting the failures it observes. RLPE rewards the trained model strictly on prompt performance, so it learns the prompting strategies that improve the task model. The prompt is generated once and reused across the task, so inference does not require the trained model. Since RLPE needs only query access to the model it prompts, it is also compatible with closed-source models. We apply RLPE to Enigmata, BIG-Bench Extra Hard, and PlanBench. We train a 9B-parameter model that writes better prompts than state-of-the-art frontier models (gpt-5.6-sol and claude-opus-5) and prompt optimizers (GEPA and TextGrad) on 2/3 benchmarks. Although the model is never explicitly trained to iterate on prompts, this capability emerges at a level that matches or beats frontier models. The learned prompting capability also generalizes, with the trained model improving task models 6x larger than the one it trained with, including ones from entirely different model families, and matching claude-opus-5 on a fourth benchmark held out from training. --- ### Conformalized Physics-Informed Weak Regression for Parameter Estimation in Epidemic Models Authors: Allan Peter Engsig-Karup Published: 2026-10-13 Categories: stat.ML, cs.LG, math-ph arXiv: https://arxiv.org/abs/2610.19058v1 Compartment models of infectious diseases are often linear in coefficients that are physical parameters or products or ratios of them. We exploit this with closed-form least squares and equip the estimates with distribution-free uncertainty. Physics-informed regression (PIR) fits the parameters to finite-difference derivatives of the data; we introduce physics-informed weak regression (PIWR), which integrates the model in time instead, needs no derivatives of the data, estimates the initial state jointly and is high-order accurate. To quantify uncertainty we wrap both estimators in split conformal prediction, with a calibration population generated by the physics-based model itself, giving simultaneous intervals for all parameters with a finite-sample coverage guarantee. A residual-adaptive factor, computed without ground truth, scales the intervals to each data set (PIWR-RACC). On the eleven benchmark models of disease-informed neural networks (DINNs), PIWR or PIR-FD6 is one to four orders of magnitude more accurate than the reported DINN results wherever the sampling resolves the dynamics, in about a millisecond per fit instead of minutes to hours of training, and the 90% intervals achieve 87-92% coverage in all 88 settings. On the S3I3R model of the original PIR study, PIWR lowers the reported PIR errors by about three orders of magnitude. On real data from the 1978 boarding-school influenza outbreak, a variable-projection variant gives calibrated 95% intervals that overlap those of a Bayesian analysis. On a time-varying transmission benchmark, a B-spline expansion of beta(t) keeps PIR and PIWR linear; they are more accurate than physics-informed neural networks in three of four cases and comparable in the noisiest, with simultaneous bands for beta(t). The complete conformal calibration takes less than two minutes for every benchmark. --- ### Deep Generative Models for Phylogenetic Inference with Complex Evolutionary Processes Authors: Ethan Baron, Alan N. Amin, Andrew Gordon Wilson Published: 2026-10-13 Categories: cs.LG, q-bio.PE arXiv: https://arxiv.org/abs/2610.19053v1 Inference of phylogenetic trees from sequences plays a central role in understanding evolutionary relationships, with applications ranging from tracking pathogen spread to reconstructing the history of life. Conventionally, practitioners obtain posteriors over trees using likelihood-based methods like MCMC. However, likelihoods are only available for simple evolutionary models with restrictive assumptions. For realistic evolutionary models, inference using conventional methods is prohibitively expensive, inaccurate, or even impossible. In practice, practitioners settle for using as flexible a conventional method as possible, even though they expect it is misspecified. In principle, we could use simulation-based inference: simulate tree and sequence data from an evolutionary model and train a neural network to predict the posterior over trees given sequences. However it is a mathematical challenge to represent and train complex posterior distributions over trees. Here we present a flexible family of conditional generative models over trees. Our models iteratively build trees using three natural paradigms -- top-down, middle-out, or bottom-up -- and are trained using a discrete diffusion framework. For real and synthetic datasets of up to $65$ taxa and $>10^5$ tokens, our models recover MCMC posteriors much more accurately than the previous state-of-the-art simulation-based method Phyloformer 2. Finally, we compare to IQ-Tree, a popular flexible-but-misspecified conventional method. Our models match its tree estimates on simple data, but on more realistic data, our method is reliably more accurate. --- ### Why Do VLMs Fail at Remote Physiological Measurement? Rethinking with Physiological Grounding and Numerical Alignment Authors: Xiao Yang, Zekun Zhang, Yuxuan Fan, Duoxun Tang, Ziyang Liu, Dengbo He, Kaishun Wu, Jiyao Wang Published: 2026-10-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.19052v1 Video-based remote physiological measurement (RPM) has broad applications, while Vision-Language Models (VLMs) provide a promising opportunity to enable end-to-end physiological monitoring for future human-aware intelligent systems. However, existing RPM methods rely on task-specific models and cannot be seamlessly integrated with the multimodal understanding and interaction capabilities of VLMs. We revisit RPM with VLMs and provide empirical evidence for two major bottlenecks: generic visual semantic representations fail to preserve fine-grained physiological cues; while discrete token prediction in autoregressive generation is inherently misaligned with continuous numerical measurement. To address these challenges, we propose VITAL (Visual-physiological Token Alignment for Language Models), a visual-physiological token alignment framework for RPM and preserving general vision tasks. VITAL retains the original visual pathway for semantic understanding and introduces an independent physiological pathway to jointly model semantic and physiological information. Moreover, we propose a structured numerical alignment approach to improve the reliability of generative heart rate estimation by enhancing numerical relationship modeling. Extensive experiments show that VITAL improves cross-domain estimation performance on multiple rPPG datasets while preserving the general visual understanding capability of VLMs, demonstrating its effectiveness as a unified visual-physiological model. Code will be released. --- ### Smart Alone, Blind Together: Why Accuracy Fails to CertifyTheory of Mind in Multi-Agent Teams Authors: Will Beaumaster, Paul Schrater Published: 2026-10-13 Categories: cs.AI, cs.CL, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2610.19051v1 Coordinators that act on what they infer about teammates are usually certified by the accuracy of those inferences. We argue that accuracy is the wrong certificate, for two reasons. First, the accuracy needed to act depends on what a wrong action costs, so the bar belongs to the deployment, not the module. Second, a module's errors are rarely independent, and dependence has a sign: positively associated errors help where their damage overlaps and hurt where it compounds, so an accuracy threshold fails in a predictable direction, and once wrong beliefs interact and can do harm, no rule based on accuracy is right for every module. We test these predictions in task assignment, Level-Based Foraging and Hanabi, with injected errors, trained and Bayesian modules and five language models, and in human judgments. Accuracy fails in both directions, approving harmful language-model deployments in Hanabi, where shared errors compound, and rejecting beneficial ones in task assignment, where costly errors are rare. In our tasks it also buys far less redundancy than independence predicts: from GPT-5.4-mini to Claude Opus 5.5, error on teammates the models have evidence about falls from 32% to 11%, but the chance that all three observers misread one falls only from 16% to 9% (independence: 3.4% to 0.15%). We propose certifying the deployment, with a Blind-Spot Gate that prices error costs, pairwise interactions and measured dependence without deploying the module. On held-out data from the cells it was developed on, it makes no significant false approval in 20 splits (accuracy: 3.2 per split), and in preregistered tests on modules it was not developed on, it recovers what accuracy rejects (seven classifiers: regret 0.004 against 0.479) and catches what accuracy approves (a Bayesian module: significant false approvals in 17 of 20 splits for accuracy, 1 for the gate). --- ### Focus, Align, and Diffuse: Time-Series-Aware Keyframe Diffusion for Cardiac Dynamic Synthesis from Sparse Observations Authors: Junkai Liu, Haofan Wu, Nay Aung, Joao A. C. Lima, Steffen E. Petersen, Le Zhang Published: 2026-10-13 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2610.19050v1 Dense cardiac dynamics are essential for assessing cardiac function, yet in practice clinicians often observe only extremely sparse measurements. However, recovering full dynamics from such sparsity is a highly ill-posed problem due to the lack of temporal cues. While auxiliary time-series signals like ECG provide physiological guidance, effectively exploiting them is challenging due to the cross-modal representation gap and phase misalignment. In this work, we present CardioFAD, a Focus--Align--Diffuse paradigm that reformulates sparse cardiac dynamic synthesis as a recoverability--alignability anchor discovery problem. Our core insight is that resolving extreme temporal ambiguity requires a compact set of anchor states that are both sufficient to recover the visual trajectory and reliable for ECG--visual alignment. We therefore learn motion-salient keyframes under two complementary principles: trajectory sufficiency, which preserves trajectory-critical intra-modal motion content, and anchor alignment, which promotes consistent inter-modal correspondence at these anchors. We implement the Focus and Align modules optimized by the two aspects. Diffuse then performs two-stage generation by first synthesizing keyframes and subsequently interpolating the remaining frames. Extensive experiments on cardiac MRI and echocardiography videos demonstrate superior visual quality, temporal coherence, and improved functional consistency under the extreme one-shot regime. --- ### Pre-Trained Language Models as Zero-Shot Tools for Social Science Research Authors: Noah Dasanaike Published: 2026-10-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.19048v1 Record linkage and demographic inference from names are routine demands in social science. Most approaches to these problems require labeled training data that are difficult or costly to acquire. I show that pre-trained language models perform both tasks accurately without requiring task-specific training. For record linkage, I introduce EnsembleLink, an algorithm that uses pre-trained embeddings alongside string-based scorers to retrieve a short list of candidates and then identify the likeliest matches. EnsembleLink matches or exceeds the performance of most prior approaches while generalizing across scripts and formats that those methods are unable to handle. For ethnicity inference from names, I show that large language models (LLMs) achieve up to 83.8% accuracy on U.S. voter files, compared to 78.0% for name-supplemented BISG. Open-weight models offer reproducible implementations that approach these models in accuracy. Moreover, LLMs are able to infer group membership for religious, caste-based, and other ethnic group categories outside of the United States, and reduce bias in downstream estimates of geographic racial gaps. Where pre-training encodes the world knowledge required by each task, task-specific labels add less information. --- ### What Information Buys in Active Inference Authors: Melih Kandemir, Mustafa Mert Çelikok Published: 2026-10-13 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2610.19046v1 Information-theoretic exploration is of primary interest in methodological studies of reinforcement learning (RL) and computational cognitive neuroscience, while the established RL theory builds regret guarantees on confidence sets. This situation leaves open the conditions under which the information-driven exploration found in nature is more advantageous than the exploration of the established RL theory. We put the state-of-the-art methods of these two paradigms, Active Inference (AIF) and Bayes-UCBVI, on an equal footing: both act through the same state abstraction of a tabular MDP with $S$ states, and their greedy forms differ only in the exploration term. We find that AIF's information gain decays too fast to serve as a confidence width, locking greedy agents that explore by it out of the optimal action. Calibrating the information gain by a square root yields calibrated AIF, which attains regret of order $\sqrt T$ for an exact abstraction, but no better guarantee than Bayes-UCBVI for a fixed reward. When an adversary chooses rewards from the agent's data, Bayes-UCBVI's value-specific widths lock out, whereas calibrated AIF pays a factor $\sqrt S$, which no goal-memoryless agent avoids on some MDP whose start states the adversary also chooses. Calibrated information gain thus acts as a reward-agnostic $\ell_1$ confidence set, preferable to value-specific widths when rewards are chosen from the agent's data, not when they are fixed. --- ### RingNav: Task-Shaped Circular Memory for Visual Heading Authors: Naitri Rajyaguru, Aryan Tajne, Stephen Jardim, Cornelia Fermuller, Yiannis Aloimonos Published: 2026-10-13 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2610.19044v1 Tiny robots have limited computation and memory, yet visual navigation systems often maintain more state than a task requires. We ask whether persistent memory can instead be shaped by the task. We present \textbf{RingNav}, a \(10.6\)k--parameter visual heading estimator that constrains its memory to the circular manifold \(S^1\). RingNav learns only the turn between consecutive images, while heading is composed directly on the circle. On the TartanAir Visual SLAM Challenge, RingNav reduces mean absolute turn error by \(27\%\) and accumulated heading error over $4$ sec by \(15\%\) relative to a similarly sized learned-memory model. The structured update also gives exactly zero turn for identical frames and exact cancellation under sequence reversal. Without fine-tuning, RingNav transfers to real-world drone experiments and continues estimating heading under severe visual degradation. RingNav runs at $27.3$Hz on Raspberry Pi Zero 2W and can be deployed on an ultra-low power GAP8 processor at $33.4$Hz. --- ### Graph Coarsening Enables Escaping Local Optima in Compute-Constrained Nonconvex MAX-CUT Authors: M. Harper Langston, Pierre-David Letourneau, Dalton Jones, Harris Teague, Peter Scott, Mingu Lee, Richard Lethin, Chris Lott, Roland Memisevic, Fatih Porikli Published: 2026-10-13 Categories: cs.LG, cs.AI, cs.CL, math.NA, math.OC arXiv: https://arxiv.org/abs/2610.19043v1 Because its binary optimization landscape contains exponentially many local optima, MAX-CUT is highly sensitive to initialization. We study Particle Polynomial Relaxation (PPR), a moment-based nonconvex continuous reformulation possessing an advantageous optimization landscape. We warm-start PPR with Combinatorial Multigrid (CMG), a spectral graph-coarsening method that produces structure-aware initial solutions in near-linear time without training data. On \texttt{t2g20} ($n=400$), benchmark instance with known exact optimum, the combined CMG+PPR pipeline reaches $97.5\%$ of optimum on average and $98.4\%$ on the best run. An extended variant with discrete local-search refinement reaches the published optimum on all sixty Biq Mac instances evaluated by a recent neural branch-and-bound method. Using a sparse CSR representation, the same approach scales to G-set instances with up to $20{,}000$ vertices reducing memory requirements by up to $3333\times$ while maintaining a consistent improvement over the CMG warm start. Gains are largest on sparse weighted graphs; on dense graphs we complement the pipeline with spectral sparsification. --- ### Loss Curvature as a Sampling-Free Proxy for Memorization in Diffusion Models Authors: Shashank Sule, Xinyue Yu, Boonam Shin, Yuxuan Liu, Abolfazl Hashemi, Hayden Schaeffer Published: 2026-10-13 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2610.19042v1 Understanding the mechanism behind why diffusion models memorize their training data remains an open question in generative modeling. In this paper, we examine this question from two perspectives: (a) the model-level perspective concerning the onset of memorization in a model during training, and (b) the sample-level perspective concerning the proclivity of an individual sample to be memorized by a given model. We show that the so-called input loss curvature, or the Frobenius norm of the Hessian of the diffusion model's training loss, is an effective metric for quantifying both perspectives on memorization. In particular, we empirically demonstrate that input curvatures averaged across training and validation samples can identify when a model is likely to start regurgitating its training data when tracked over training time. However, this metric is not sufficient for measuring an individual sample's likelihood of being memorized. To address this perspective, we introduce a counterfactual definition of memorization in diffusion models, extending the analogous notion from supervised learning proposed by (Feldman, 2019). We prove that this counterfactual memorization is controlled by the input curvature of the leave-one-out model, thus establishing a direct theoretical link between a sample's local loss landscape and its generation likelihood. We validate our derived bounds through several empirical experiments and show that input-dependent curvature provides a proxy for memorization. --- ### Tracing Morphology, Semantics, and Divergence in Language Acquisition Authors: Forough Shirin Abkenar, Haoshuo Fu, Liang Feng, Ning Yan, Masood S. Mortazavi Published: 2026-10-13 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2610.19041v1 Understanding the dynamics of language acquisition in Large Language Models (LLMs) is crucial for uncovering how statistical representations evolve into structured linguistic capabilities. However, most existing studies focus primarily on fully trained models, leaving the developmental trajectory across intermediate training stages largely underexplored. In this work, we leverage intermediate checkpoints from open-source models (e.g., Pythia and OLMo) under teacher-forcing evaluation to systematically investigate language acquisition across training steps and model scales. We focus on four core characteristics: morphological structure acquisition, embedding drift, repetition dominance, and co-occurrence effects. Our findings reveal that models acquire morphological structures well before semantic embeddings stabilize. Furthermore, we show that training dataset size has a positive impact on divergence recognition, while co-occurrence during pre-training and repetition during inference have a negative impact on divergence recognition and associative link generation. --- ### Lag: A Mean-Field Optimal Policy for Online Assignment with Reusable Resources Authors: Keerthana Gurushankar Published: 2026-10-13 Categories: cs.LG, cs.PF, math.OC arXiv: https://arxiv.org/abs/2610.19038v1 We study online task assignment with reusable resources. This problem arises in peer reviewer assignment, skill-based call routing, rideshare matching, emergency dispatch, and crowdsourcing: Tasks arrive according to a geometric process and must be immediately assigned to servers that become temporarily busy, yielding rewards that depend on the task-server pair. The goal is to maximize long-run average reward. We cast the problem as a contextual restless multi-armed bandit (CRMAB). We derive an occupancy-measure LP (OCC-LP) that upper-bounds the reward of any work-conserving policy. From its dual we obtain Lag, a closed-form index policy. We introduce a scaling regime in which the number of copies of each server and the number of arrivals per step grow together. This regime yields the first deterministic fluid limit for a contextual bandit. In it, Lag is asymptotically optimal. Finally, we evaluate our algorithms on peer review datasets and call center routing. The Lagrangian index achieves 83-99% of the LP upper bound across all load levels. Moreover, the Lagrangian index policy significantly outperforms the natural greedy assignment scheme, improving reward by up to 12.3% on journal data and 36% on structured synthetic instances. --- ### Who Should We Listen to More? Welfare-Aware Preference Acquisition for Pluralistic Alignment Authors: Ruomeng Ding, Tianwei Gao, Lianrui Geng, Mohit Bansal, Zhun Deng Published: 2026-10-13 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2610.19035v1 Pluralistic alignment needs to accommodate diverse preferences under limited human feedback. Using AI simulators to label preference comparisons reduces annotation costs, but variation in simulation accuracy across individuals can leave some people's preferences poorly represented in training. We study how to allocate human feedback across people to construct training data for pluralistic alignment, and how this allocation affects the trained policy. To make this allocation explicit and controllable, we define a social welfare objective over individual supervision utilities that measure label quality. Each query's marginal welfare gain depends on its expected supervision improvement, the recipient's current utility, and application-designated priority. Welfare-Aware Preference Acquisition (WAPA) uses auxiliary reference models to estimate query gains and individual utilities, then selects queries by estimated marginal welfare gain while updating recipient utilities. We prove exact optimality of the acquisition algorithm for the estimated welfare objective under a fixed query budget and model predictions. Experiments on six Roleplay collections and four OpinionQA regions demonstrate improved supervision and controllable allocation tradeoffs. Policy training on four Roleplay collections improves preference prediction for both seen and unseen individuals. When prioritizing a designated group and poorly represented individuals, acquiring human labels for 20% of comparisons recovers 75-86% of the average predictive utility gap between policies trained entirely on AI-generated labels and entirely on ground-truth labels. --- ### How Many Ranks Does a Token Need? A Noise-Floor Squelch for Rank-One LoRA Experts Authors: Mei Okonkwo, Owen Castellanos, Ingrid Solberg, Yusuf Demirel Published: 2026-10-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.19033v1 Low-rank adaptation (LoRA) applies every rank-one component of its update to every token, and mixture-of-experts variants replace this with a learned router that activates a fixed number of components. We argue that the number of components a token needs is a detection question with a classical answer. A token's responses to the rank-one components of a trained LoRA consist of a few large values on a Gaussian noise floor whose width matches that of an untrained adapter, and the floor carries cross-talk rather than adaptation. We introduce SQUELCH, a router-free mixture of rank-one experts that (i) soft-thresholds each token's responses at a multiple of its own robust noise level, so the active rank varies per token; (ii) chooses that multiple for each module by Stein's unbiased risk estimate, so no rank budget is specified; and (iii) replaces the resulting marginal keep-or-drop decisions by one explaining-away step on the value Gram matrix, which suppresses redundant co-active components and recruits complementary ones. SQUELCH adds no trainable parameters to LoRA. We prove that the squelch is within a logarithmic factor of the oracle input-dependent allocation, that the selected threshold is risk-consistent, and that explaining away is a descent step toward the joint sparse code whose error is controlled by the coherence of co-active components. On commonsense reasoning, knowledge, math, code, and GLUE with LLaMA-3.1-8B, Qwen3, and DeBERTaV3, SQUELCH improves over LoRA by 2.2--3.2 points and over the strongest mixture baseline by 0.8--1.2 points while activating 8.6 of 32 components per token on average. --- ### Crossing the Gender Binary: Modelling Gendered Reference in Science Fiction and General Fiction Authors: Yuxuan Liu, Haim Dubossarsky, Ruth Ahnert Published: 2026-10-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.19028v1 Science fiction is widely credited with unsettling gender. This article asks whether that holds at the linguistic level, in how readily gendered reference gives way to its counterpart, a neutral term, or other social category, and whether it separates the genre from general fiction. It does so by masking man/men, woman/women, and person/people across same-period science fiction and general fiction corpora and classifying RoBERTa's five likeliest substitutes by gender. Retention and displacement are permutation-tested over five resampling rounds, and the underlying sentences are read closely. Both corpora cross the gender binary in both directions, but unequally: where woman is masked, the model predicts a masculine term about twice as often as it predicts a feminine term where man is masked. Each mismatch marks a statistical surprise, a word the corpus did not expect there. Against this shared pattern, science fiction shows greater gender permeability than the general fiction corpus, placing man in feminine contexts more often than general fiction while the reverse rate holds steady. Its degendering tendency is stronger too, drawing both gendered terms toward the neutral. Beyond the binary, a masked woman also draws substitutes naming a social category and no gender far more often than a masked man does. In measuring the gender permeability of man, woman, and person in linguistic distribution and testing whether genre changes it, the study gives science fiction studies linguistic evidence for thematic claims and computational literary studies a pipeline applicable to other category vocabularies, such as race and class. --- ### Optimization for One, Feasibility for Most: Decoupling Optimization from Feasibility in Chance-Constrained Programs Authors: Justin Dumouchelle, Shunyu Yao, Beste Basciftci, Thiago Serra Published: 2026-10-13 Categories: math.OC, cs.LG arXiv: https://arxiv.org/abs/2610.19027v1 Chance-constrained stochastic programs (CCSPs) require solutions that satisfy uncertain constraints with high probability. Standard approaches either embed scenarios directly into optimization by considering sample average approximation (SAA)-based reformulations, growing prohibitively expensive and often failing to find feasible solutions; or employ conservative reformulations that guarantee feasibility but sacrifice objective quality by design. We propose ACCESS (Adaptive Chance-Constrained Exploration via Structured Sampling), a structured sampling framework that decouples optimization from feasibility evaluation. First, high-quality candidate solutions are generated by solving many inexpensive single-scenario subproblems, avoiding sampling directly in the constrained high-dimensional solution space. Second, feasibility is assessed separately via large-scale batched simulation over a massive number of scenarios, which is naturally amenable to GPU parallelism. That reduces the search from a high-dimensional solution space to a two-dimensional parameter space controlling conservatism and scenario diversity; while concentrating on candidates near the feasibility boundary, where high-quality feasible solutions lie. We also introduce a variant, ACCESS($δ$), which provides certified feasibility guarantees with probability $1-δ$. Experiments across three benchmark classes and five scenario distributions show that ACCESS matches or exceeds the best objective found by any method in nearly every setting, while ACCESS($δ$) is empirically feasible on every instance. The conservative reformulations remain several percent worse in objective, and SAA is frequently infeasible while taking an order of magnitude longer on the harder benchmarks. --- ### Joint Subspace Sparse Attention for Efficient Long-Context Decoding Authors: Jiwon Song, Yoongon Kim, Jae-Joon Kim Published: 2026-10-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.19026v1 Sparse attention reduces the KV-cache traffic that dominates long-context LLM decoding, but practical methods largely operate at coarse granularity. Token-level selection offers finer control, yet presents two challenges: low-dimensional scoring may lose query--key structure needed for accurate ranking, while gathering scattered selected tokens can offset the resulting latency benefit. We introduce Joint Subspace Sparse Attention (JSSA) to address both challenges. For selection quality, JSSA learns a shared low-dimensional query--key subspace by minimizing token-score preservation error. We upper-bound the resulting non-convex objective with a tractable marginal objective that admits a closed-form spectral solution; direct refinement of the exact objective provides no measurable improvement in the tested settings. For execution efficiency, we develop a gather-free token-level indexed-attention kernel that supports distinct per-KV-head selections under the standard grouped-query attention (GQA) KV-cache layout. Across standard GQA, hybrid sliding-window/global attention, and Multi-head Latent Attention (MLA) models, JSSA consistently remains close to full-KV accuracy while avoiding the substantial generation-length inflation and architecture-dependent failures observed with competing methods. On an NVIDIA B200 GPU, JSSA achieves up to $6.43\times$ the decoding throughput of full-KV attention at 128K context. JSSA achieves reasoning accuracy comparable to model-native DSA without model training and reaches 96--99\% of its decoding throughput even at 700B scale large models. --- ### How Far Can Coding Agents Go in Visual Generation? Authors: Hengguang Zhou, Yuanhao Ban, Jiaqi Feng, Xiaohuan Pei, Justin Cui, Cho-Jui Hsieh Published: 2026-10-13 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2610.19025v1 Modern image generation largely relies on specialized generative models that leave the process of image construction implicit in learned parameters. We explore an alternative: general-purpose coding agents that construct images through executable programs. Our study of zero-shot drawing on AgentDrawBench, a 200-prompt benchmark, reveals a distinctive capability profile. Agents excel at preserving structure and satisfying precise visual constraints, achieving competitive results in domains where compositional accuracy matters more than photorealistic appearance, while remaining limited in perceptual richness. Their visual expressiveness varies with the drawing interface, and a qualitative study on reconstruction shows how procedural skills extracted from human demonstrations support different artistic media. We then examine code as an external visual language of thought: a structured, executable representation that agents can construct and inspect. We test it in visual question answering task and find reconstructed visual code retains substantial information for question answering and, in some domains, supports higher accuracy than the original image. These abilities raise a further question: do agents draw on a shared internal representation of scene content beyond a particular drawing program? We explore an internal visual language-of-thought hypothesis, in which a shared, compositionally structured representation supports visual operations across drawing languages. Cross-harness drawings and images assembled from independent single-pixel queries exhibit related layouts and tones. Agents also maintain self-generated room arrangements across viewpoints after visible drawings are removed. These results demonstrate that the coding agent would maintain a consistent and coherent world inside its imagine even before the harness gets involved and the generation starts. --- ### Can LLMs Access their World Knowledge for Event Prediction? Authors: Zijun Wu, Zhitian Zhang, Hossein Hajimirsadeghi, Nikita Dvornik, Alexander Pashevich Published: 2026-10-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.19021v1 Recent work has questioned whether large language models (LLMs) can be useful for temporal event prediction. Despite vast pretrained world knowledge, LLMs often underperform simpler specialized models. We ask whether this knowledge is truly inaccessible, or whether current methods fail to present event prediction in a form LLMs can use. We argue for the latter and show that LLMs become effective event forecasters when the interface is designed around two choices. The first grounds each event in a natural-language description, and the second separates event semantics from the prediction space to prevent semantic bias from label associations. To test this, we introduce DescribeEvent, a benchmark of ~150K events across seven datasets and six domains with event-level descriptions. We find that capable LLMs substantially benefit from descriptions and symbolic labels, outperforming description-free variants and non-LLM baselines, while weaker models gain little. These results suggest that accessing LLM world knowledge for event prediction is an interface problem, and that event descriptions offer a practical way to elicit the knowledge LLMs already encode. --- ### Discrete Diffusion Models are Minimax Optimal Under Sparsity Authors: Luca Blunda, Tyler Farghly, Umut Simsekli, Alain Durmus Published: 2026-10-13 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2610.19020v1 Discrete diffusion models have emerged as a leading alternative to autoregressive models for generating text and other categorical data, yet their theoretical foundations remain less developed than those of their continuous counterparts. For continuous diffusion models, a prominent line of theory suggests that these models can adapt to low-dimensional structure in the data, thereby improving statistical efficiency and generalization. In this work, we investigate the discrete analogue of this phenomenon by studying the statistical rates of discrete diffusion models under sparsity assumptions. By analyzing a nonparametric estimator derived from a regularized score-entropy objective, we establish minimax-optimal rates in the sparse regime. The proposed regularization can be viewed as an adaptation of label smoothing techniques introduced for classification, and does not require the knowledge of the sparsity parameter. This shows that discrete diffusion models can adapt intrinsically to sparsity. --- ### IR-PRM+ with Previous-Utility Prediction: Constant Regret and Best-Iterate Convergence Authors: Michael Sullins, Ian A. Kash Published: 2026-10-13 Categories: cs.LG, cs.GT arXiv: https://arxiv.org/abs/2610.19016v1 Regret matching (and its variants) and counterfactual regret minimization are central algorithms in practice for normal-form and extensive-form game solving. Yet these have historically lacked the stronger theoretical convergence guarantees available to optimistic and extra-gradient methods. Recent work introduced IREG-PRM+, a regret matching variant which does have strong theoretical convergence guarantees. However, it relies on a simultaneous, extra-gradient update. IREG-PRM+ is an instance of the more general IR-PRM framework, where empirically optimistic and alternating updates often have better performance. However, the prior extra-gradient analysis does not extend to these cases. We introduce a new approach that covers both settings. For simultaneous and alternating IR-PRM+ in finite two-player zero-sum matrix games, previous-utility prediction recovers the constant-regret and convergence-rate guarantees previously obtained with extra-gradient prediction: external regret bounded independently of T, an O(T^{-1}) average duality gap, and an O(T^{-1/2}) best-current-iterate gap. Moreover, the current duality gap vanishes and the current profile converges to the Nash equilibrium set. The key step bounds the component of consecutive strategy movement not controlled by the existing IR-PRM+ regret inequality using the relative growth of the nondecreasing regret-vector norm rho_t. Coupling this bound across the two players yields recurrences whose effective coefficient scales as 1/(rho_t^X rho_t^Y), preventing unbounded norm growth. We extend the analysis to finitely many simplex learners under a weighted Minty condition and, through the corresponding CFR variant IR-PCFR+, recover analogous guarantees for finite two-player zero-sum perfect-recall extensive-form games under the same full-reach condition as prior work. --- ### Scaling Cheap Synthetic Pretraining Improves Indoor Radio-Map Prediction Authors: Khoren Petrosyan, Artashes Mkrtchyan, Rafayel Mkrtchyan, Hrant Khachatrian, Theofanis P. Raptis Published: 2026-10-13 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.19015v1 Real measurements are too limited to train an accurate indoor pathloss predictor that works across a wide range of buildings. Large-scale synthetic pretraining offers a way forward, but real building layouts are also scarce, and accurate ray-tracing simulators are slow, expensive, and often proprietary. We address both problems by introducing a generator that automatically creates diverse indoor layouts and a fast, open-source approximate ray tracer that computes radio maps for them. Using this pipeline, we generate 128M synthetic samples, pretrain ResNet-101 and Swin-T encoder-decoders, and fine-tune them on high-quality benchmark data. Despite simulator mismatch, our ResNet-101 model reduces error by 15% on average relative to the best known methods across five indoor radio-map prediction tasks and improves transfer on a small real-measurement dataset. Both architectures show predictable data-scaling trends: power laws fitted on 2M-16M samples predict the mean normalized downstream RMSE at 32M-128M with 3.33% mean absolute percentage error for ResNet-101 and 7.10% for Swin-T. These results show that pretraining on large amounts of cheap simulated data can improve indoor radio-map prediction, even when real measurements and high-quality simulations are limited. --- ### Data Density Scaling Laws for Image Self-Distillation Authors: Alvard Barseghyan, Ani Vanyan, Hakob Tamazyan, Hrant Khachatrian Published: 2026-10-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.19013v1 Current scaling law formulations suggest that increasing the number of unique samples in a dataset improves model performance, while repeated exposure to the same samples provides diminishing value. In this work, we examine this assumption for image self-distillation models. Through systematic experiments across diverse datasets, namely Maxar, SATLAS, Waymo, nuPlan, Ego4D, ImageNet, and YFCC15M, we demonstrate that the effects of sample repetition on downstream performance are non-trivial and dataset-dependent. We identify settings where repeatedly training on a smaller random subset can outperform training on a larger set of unique samples. This finding highlights a limitation of existing scaling laws. To address this gap, we propose a modified version of a Chinchilla-style scaling law that explicitly accounts for two factors: the number of unique samples and repetition per sample. This formulation provides a framework for understanding data-compute trade-offs and improves prediction in some regimes where repetition plays a central role, although its benefits are not consistent across datasets. Finally, we examine how subset selection and augmentation affect downstream performance. --- ### PMO-Dock: Benchmarking Docking, Specificity, and Generalization in Molecular Optimization Authors: Gor Simonyan, Tatevik Abrahamyan, Narek Abelyan, Tigran Fahradyan, Hrant Khachatrian Published: 2026-10-13 Categories: cs.LG, q-bio.QM arXiv: https://arxiv.org/abs/2610.19011v1 The Practical Molecular Optimization (PMO) benchmark standardized evaluation in molecular optimization, but it is built on simple property-based oracles that do not capture structure-based drug design. As the field has moved to docking-based objectives, evaluation practice has become unstandardized, and different methods report results on different docking tasks, often without a shared protocol for fair comparison or sample-efficiency constraints. To address this, we introduce Practical Molecular Optimization for Docking (PMO-Dock), a benchmark and protocol for docking-based optimization consisting of 25 tasks covering hit generation, lead optimization, and a new specificity task requiring strong on-target binding while penalizing off-target interactions. The protocol separates model development from final evaluation: validation tasks are used for hyperparameter tuning, and test tasks are held out for final evaluation and are not used during development. Evaluation on the test tasks is done under a strict oracle budget to reflect realistic drug-discovery settings. We benchmark four diverse high-performing methods spanning different optimization paradigms, Saturn (reinforcement learning), GenMol (discrete diffusion), Genetic-guided GFlowNet, and ChemLlama (LLM-based evolutionary search). Our results show no universally best method across tasks, additional analyses of hyperparameter transfer (cross-task and cross-category) and sensitivity show that transfer is often limited and varies by method, motivating method-dependent selection strategies. This benchmark provides a concrete standard for evaluating generalization to unseen tasks and sample efficiency under a limited test-time oracle budget. --- ### Action Jets: Learning the Local Shape of the Action-conditioned Data Manifold Authors: Anton Arapin, Chahyon Ku, Bernadette Bucher Published: 2026-10-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.19007v1 World models are a powerful means of reasoning and planning, but many of these action-conditioned predictive models are high dimensional and computationally expensive. These challenges limit the number of action candidates that can be evaluated by a planner. We show that this cost is avoidable for planners over short horizons, which only require local information with respect to the current state. For a fixed state, the frames reachable by varying a low-dimensional action (a camera movement or an end-effector command) lie on a low-dimensional manifold. We estimate the local shape of that manifold directly via a network trained to estimate how each image region moves per unit of each action axis supervised by data collected from samples by the generator. A correction head fit to trajectory data estimates the shape of this manifold region up to a third-order Taylor polynomial. We call this network estimating the Taylor polynomial describing the manifold shape an Action Jet and compute its radius of validity in closed form. By traversing this approximation of the local manifold shape, we only have to perform inference once per state for any number of candidate actions. Scoring sixteen candidates from a single extraction is over 300x faster than with either source generator, and this gap widens with the number of candidates a planner evaluates. We measure against state-of-the-art action-conditioned generators, IRASim and WorldGym on BridgeData V2, a real 7-DoF manipulation benchmark, and FrameCrafter on DL3DV scenes, where we chart from the novel-view generators DepthSplat and LagerNVS. Because only the tangent comes from the generator and every other term from the data, the Action Jet also predicts held-out frames more accurately than IRASim, the generator that supplied its tangent, at short horizons and at over 100x less compute. --- ### CyberArena: Benchmarking AI Agents in Live Symmetric Attack-and-Defense Combat Authors: Bangya Liu, Jianhong Tu, Yueyang Pan, Hanhong Zhao, Zhe Ye, Hongwei Li, Saastha Vasan, Katherine Lambert, Junmin Zhu, Hao Wang, Jienan Chen, Yunze Xiao et al. Published: 2026-10-13 Categories: cs.CR, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2610.19005v1 AI agents are demonstrating increasingly strong offensive and defensive cybersecurity capabilities in the real world. Current benchmarks mostly evaluate agents in isolation against static targets. Real cyber operations, however, are dynamic and coupled: security postures constantly change as attackers and defenders adapt to each other in real time. Static benchmarks quickly saturate and miss an agent's ability to attack and defend simultaneously under live pressure. To address this gap, we present CyberArena, a dynamic, symmetric adversarial benchmark built around multi-round attack-and-defense combat. In isolated sandboxes, two agents compete under identical rules, acting concurrently as both attackers and defenders over continuously changing services. This converts static targets into evolving, semi-open challenges, directly testing an agent's speed and precision in discovering, exploiting, and patching vulnerabilities. To sustain the benchmark's longevity, an automated agentic pipeline continuously generates, reviews, and validates new environments. Furthermore, because pairwise contests are notoriously hard to quantify, we introduce a dynamical model that maps match dynamics into unified, multidimensional scores across offensive, defensive, and domain-specific capabilities. Evaluating 12 frontier LLM agents across 40 challenges in 466 matches, CyberArena separates model capabilities where single-agent baselines hit a ceiling. The trajectories read like a fight rather than an exam: defenders patch one hole and miss the next and certify repairs on stale evidence, while capable agents think a move ahead, planting backdoors for later rounds and, in one case, writing their own packet sniffer to watch the opponent. Beyond a benchmark, CyberArena serves as an adaptable, scalable experimental platform for future research on cybersecurity agents. --- ### Evaluating Large Language Models for Multilingual Abstractive Summarization: A Comprehensive Study of English and Bengali Authors: Khan Mahi Al Atahar, Nazifa Tasneem, Ajwad Abrar Published: 2026-10-13 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2610.19003v1 Abstractive summarization remains challenging across languages, where linguistic quality and factual consistency may diverge, particularly in low-resource settings. We present a standardized zero-shot benchmark of eight closed-source and open-weight LLMs on size-matched English and Bengali XL-Sum test sets. Our evaluation combines lexical and semantic metrics with reference-free factuality verification and multidimensional LLM-as-a-Judge assessment, providing a comprehensive analysis of both surface-level quality and factual reliability in multilingual summarization. Results reveal substantial cross-lingual variation: GPT-5.6 Luna leads several English lexical metrics but does not maintain the same advantage in Bengali, where LLaMA 3.3 70B achieves the highest ROUGE and BLEU scores. Gemini 2.5 Flash obtains the highest observed Bengali factuality score. Furthermore, evaluation methods produce different model rankings, highlighting the limitations of relying on a single metric for multilingual summarization assessment. These findings demonstrate that strong English summarization performance does not necessarily transfer to Bengali and emphasize the need for comprehensive evaluation frameworks for low-resource languages. --- ### Discovering Undisclosed Concepts in LoRA Adapters for Diffusion-Based AIGC Models Authors: Yupeng Qiu, Han Fang, Dhananjai Sharma, Ee-Chien Chang Published: 2026-10-13 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2610.18990v1 Low-Rank Adaptation (LoRA) has made diffusion model personalization affordable and widely shareable, but it also creates moderation risks when harmful or problematic content is not faithfully disclosed. Hence, it is desired to develop a mechanism that, given a LoRA adapter, discovers the concept it was trained to generate, so as to support downstream investigation. We characterize the target concept through the conditioning input that most clearly exposes what the LoRA has learned. Such an input should induce coherent LoRA outputs that are distinctive from those of the base model and strongly align with the learned LoRA subspace. We therefore formulate concept discovery as searching for the conditioning input that jointly maximizes output coherence, LoRA-induced distinctiveness, and subspace alignment. Even with a clear objective, however, optimizing it over an open-ended input space is prohibitively expensive, since reliable evaluation of coherence and distinctiveness requires repeated diffusion rendering. Crucially, we observe that an input need not be rendered to determine whether it is promising. Its alignment with the learned LoRA subspace provides a lightweight signal for localizing promising candidates before visual verification. Based on this insight, we develop a two-stage framework for text-to-image LoRAs. Subspace-Guided Evolutionary Search (SGES) uses render-free subspace alignment to explore candidate prompts and retain a compact shortlist, while Paired Visual Identification (PVI) renders only these candidates and compares the LoRA and base-model outputs to identify those exhibiting coherent and distinctive generation behavior. This design enables efficient and reliable discovery of previously unknown concepts encoded in LoRA adapters. --- ### Non-Abelian quantum Hall states at strong Landau level mixing: finding anyons with first-principles AI Authors: Pierre-Antoine Graham, Ahmed Abouelkomsan, Liang Fu Published: 2026-10-13 Categories: cond-mat.mes-hall, cond-mat.str-el, cs.AI arXiv: https://arxiv.org/abs/2610.18967v1 Non-Abelian anyons, strange particles forming the basis of fault-tolerant topological quantum computing, are predicted to emerge in fractional quantum Hall states at even-denominator filling factors. Identifying which topological order is realized has proven to be a challenging problem that requires an accurate, non-perturbative treatment of realistic Landau level mixing, which has so far been missing from theoretical studies. Here we present the first complete solution of non-Abelian quantum Hall problem that includes all electrons and all Landau levels, for spin-polarized electrons at filling factor $ν= 3/2$. We develop a momentum-resolved neural-network variational wave function, optimized solely on the microscopic Hamiltonian, which gives direct access to the topologically degenerate ground states. Without any physics input about the expected outcome, it discovers a degenerate ground-state manifold whose entanglement reveals anyons with quantum dimension $\sqrt{2}$, the hallmark of Ising-type non-Abelian order. By directly computing the overlap with trial wave functions, we further show that Landau level mixing favors the anti-Pfaffian over other candidate states. Our results demonstrate the power of neural-network wave functions in finding and characterizing non-Abelian anyons from first principles, in regimes of strong Landau level mixing, relevant to many recent experiments. --- ### $λ_0$: Scaling Open-World Egocentric Human Data for Humanoid Loco-Manipulation Authors: Lambda-humanoid Team Published: 2026-10-13 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2610.18950v1 Humanoid loco-manipulation requires coordinated whole-body interaction with the physical world, yet collecting robot demonstrations at scale remains costly. Human demonstrations offer a scalable alternative, but existing egocentric human supervision often omits locomotion and posture, while embodiment differences and controller dynamics hinder accurate end-effector execution. We introduce HumanVerse, a 500-hour dataset of open-world human loco-manipulation pairing egocentric video with synchronized body and hand motion. Our human-to-humanoid pipeline aligns camera viewpoints and arm appearance, and refines motion references and controller inputs offline to reduce end-effector errors while preserving whole-body coordination. We validate the pipeline through zero-shot transfer to Unitree G1 on representative whole-body manipulation and long-range loco-manipulation tasks, without target-task robot demonstrations. Building on this pipeline, we develop $λ_0$, a humanoid foundation model for whole-body loco-manipulation, with robot-aligned human demonstrations providing supervision for mid-training. Increasing whole-body human data consistently improves downstream task progress. $λ_0$ achieves 90.0% success on SIMPLE and 62.5% across real-world loco-manipulation tasks. We expect this study to guide scalable whole-body human data collection toward humanoid foundation models for richer interaction with the physical world. Homepage: https://lambdahumanoid.github.io/ --- ### Virtual-Alloy Physics-Aware Semantic System for extrapolative prediction of perovskite solar cells Authors: Qiwei Han, Chi Zhou Published: 2026-10-13 Categories: cond-mat.mtrl-sci, cs.LG arXiv: https://arxiv.org/abs/2610.18949v1 Existing machine-learning models for perovskite solar cells struggle to predict devices made from new materials. Most treat device layers as arbitrary categorical labels and represent perovskite absorbers either through featureless composition vectors or through rigid crystal graphs that require a pre-solved unit cell. As a result, they cannot generalize to unrecorded alloys or unfamiliar cell architectures. We present the Virtual-Alloy Physics-Aware Semantic System (V-PaSS), an architecture built around the physical continuity of perovskite solid solutions. V-PaSS represents arbitrary mixed-cation, mixed-halide absorbers by interpolating relaxed crystal graphs of 23 pure $ABX_3$ endpoint compounds via Vegard's law with learned bandgap bowing. For the device stack, it couples layer sequence and cell polarity (n-i-p or p-i-n) with interfacial band offsets and encodes chemical descriptions with a scientific language model. Evaluated under an institution-grouped protocol where test devices come exclusively from unseen laboratories, an untuned default configuration of V-PaSS achieves the lowest error among fourteen tested models (2.861% MAE, a 5.2% relative reduction over a gradient-boosted baseline at 3.017%, and outperforming the best tuned benchmark at 2.912%). V-PaSS pulls furthest ahead where test devices differ most from training: reducing error by 15.7-19.0% on unseen absorber alloys, by 16.1% on mixed absorbers from new laboratories, and widening its lead over the baseline by 3.6$\times$ on devices with unobserved transport layers. Combined with tree ensembles, V-PaSS sets a new state of the art across all five benchmark splits. --- ### Limits of Statistical Assurance for Embodied and Agentic AI under Adaptive Adversaries Authors: Inderjeet Singh Published: 2026-10-13 Categories: cs.CR, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2610.18948v1 Finite safety assessments cannot exclude an adversary that preserves unattacked behavior until certification and activates afterward. We characterize this limitation for embodied and tool-use AI. An adversary that matches the complete observation law until observable, irrevocable certification and retains intervention access afterward attains $v\mathbb{E}((n-S_0)_+)$ expected post-certification events over $n$ trials, where $v$ is the active event probability and $S_0$ the unattacked certification time. The result covers adaptive and privately randomized evaluators. Switching at certification is exactly optimal for a fixed likelihood-ratio test under memoryless, event-increasing interventions without a binding intervention budget. A positive clean-certification requirement forces linear worst-case expected excess when intervention raises event rates over an authorized deployment horizon, even if certification is deferred to the deadline. In simulated RoCo collaboration, switching yields commanded-separation violations in 34 of 36 post-certification episodes. Preregistered randomized AgentDojo trials estimate 1.98 additional security violations per four-task continuation (95% interval (1.67, 2.29)). An adversarial language-model controller infers hidden certification from noisy evaluation receipts and times intervention accordingly. With permanent revocation, a mixture likelihood-ratio monitor bounds cumulative excess above a prespecified reference rate at square-root order, up to logarithmic factors, on every sample path. A single fixed alternative can permit linear expected excess under stationary attacks. Against a controller observing the monitor's rule and statistic, live mixture monitoring reduces violations from 12.00 to 3.81 per 24 assigned task opportunities. Revocation also reduces tasks executed. --- ### Physical Layer Anomaly Detection via Adaptive Gaussian Mixture Model Authors: Mamady Delamou, Luan Chen, Arsenia Chorti Published: 2026-10-13 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2610.18946v1 Physical-layer spoofing attacks pose a critical threat to wireless localization systems by manipulating channel state information (CSI). Detecting such attacks becomes particularly challenging when the attacker and the legitimate node are spatially proximate, as their CSI characteristics become increasingly similar. To address this challenge in indoor scenarios, we propose an adaptive Gaussian mixture model (GMM)-based detection framework that learns legitimate CSI patterns and detects spatial inconsistency through statistical anomaly detection. Using a massive multiple-input multiple-output (MIMO) experimental dataset with 64 uniform linear array (ULA) antenna and 5 mm spatial resolution, we evaluated our detector against CSI spoofing attacks with spatial displacements ranging from 50 mm to 450 mm. The adaptive GMM achieves 95-98% detection rate for displacements above 150 mm while maintaining 1% false alarm rate. We benchmark our approach against conventional GMM, local outlier factor (LOF), one-class support vector machine (SVM) and k-nearest neighbors (k-NN) classifiers, demonstrating overall superior detection performance of our proposed classifier. --- ### Semi-Amortized Bayesian Inference with Reusable Local Posteriors Authors: Niek Stevenson, Paul-Christian Bürkner, Andrew Heathcote, Stefan T. Radev Published: 2026-10-13 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2610.18945v1 Amortized Bayesian inference uses simulations to perform Bayesian estimation when likelihoods are expensive or analytically unavailable. However, learning the full joint posterior is challenging in high-dimensional models with complex dependencies. We introduce a semi-amortized method that divides parameters into smaller blocks, and uses conditional independence to identify the information needed to infer each block. We train neural estimators for blocks whose posterior updates are computationally expensive or frequently repeated. Each estimator learns from simulations of the relevant model components to approximate the block's full conditional posterior, given the relevant observations and the values of the variables on which it depends. A Markov chain then alternates direct draws from these estimators with conventional updates of the remaining variables. Each neural update uses the current conditioning values and requires neither likelihood evaluation nor an acceptance-rejection step. Where the same conditional structure recurs, one estimator can be reused across blocks and datasets, with an output dimension determined by the block rather than the full model. We illustrate the approach in high-dimensional and computationally expensive hierarchical and spatiotemporal models. --- ### Wong--Zakai Convergence and FNO Learning for Stochastic Volterra Equations Authors: Wonjae Lee, Jiuk Jang, Hyungbin Park Published: 2026-10-13 Categories: stat.ML, cs.LG, math.PR arXiv: https://arxiv.org/abs/2610.18939v1 This paper studies Wong--Zakai convergence and Fourier neural operator learning for stochastic Volterra integral equations (SVIEs) describing random systems with memory. A Wong--Zakai theorem establishes convergence of pathwise solutions driven by piecewise linear approximations of Brownian motion to the corresponding SVIE solution. This convergence provides a foundation for using mirror-padded Fourier neural operators to learn the solution operator mapping initial conditions and driving noise to entire solution trajectories. Numerical experiments demonstrate competitive prediction accuracy and generalization to temporal grids finer than those used for training, while assessing the influence of padding and computational cost. As a follow-up to \citet{LKP:26}, this study extends their operator-learning framework to SVIEs through separate convergence and approximation analyses tailored to convolutional memory. --- ### Beyond Equation Search: Conjecture-Guided Discovery with SCOPE and ClosureBench Authors: Yuxiao Hu, Qian Li, Ding Wang, Siheng Chen, Linfeng Zhang, Jinyue Yan, Yuntian Chen Published: 2026-10-13 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2610.18938v1 Most symbolic regression methods optimize candidate equations, but improving an equation's fit does not establish whether its underlying scientific conjecture should be retained, revised, or rejected. A conjecture may admit multiple mathematical realizations, and similarly accurate equations may imply different explanations. This motivates a shift from refining individual expressions to developing and testing the conjectures that guide them. We introduce SCOPE, a framework that sustains multiple conjecture-driven research trajectories. Multiple scientist agents independently pursue conjectures through equation modeling, question formulation, and active experimentation, then exchange evidence to revise their conjectures and research directions. Their findings are consolidated into a scientific report linking models, conclusions, and evidence. Existing equation-discovery benchmarks primarily assess recovered expressions, leaving the evidence and scientific conclusions established through the investigation underexamined. We therefore introduce ClosureBench, an interactive benchmark of 60 closure-discovery tasks across five scientific domains. ClosureBench focuses on closure-discovery tasks to give equation discovery a concrete scientific purpose. Each task embeds an unknown algebraic relation in a known PDE system, where agents control experimental conditions in OpenFOAM to acquire new data for equation discovery. Beyond equation accuracy, ClosureBench proposes three metrics to evaluate the discovery process: evidence faithfulness, mechanism insight, and experimental effectiveness. Compared with diverse baselines, SCOPE achieves higher equation accuracy on both ClosureBench and a real-world scientific discovery case, while producing more accurate, reliable, and effective scientific discoveries. ---