# Research Papers — 2026-10 · bundle page 1 of 156 > Full-text markdown of papers #1–50 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 [Next bundle →](https://aipod.dev/papers/archive/2026-10/page/2.md) ### Learning to Correct Geometry in Generated Videos Authors: Weijie Lyu, Tiancheng Shen, Jason Li, Yujing Wang, Xiaoyuan Wang, Haobo Yuan, Yizhou Zhao, Ming-Hsuan Yang Published: 2026-10-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.23856v1 Generated videos often lose geometric consistency under camera motion: structures warp under viewpoint change, parallax becomes inconsistent, and smooth camera movement may collapse into shot-like transitions. We argue that this failure is largely a data problem. In web-scale video corpora, most visible motion comes from dynamic objects captured by static or weakly moving cameras, leaving only sparse supervision for viewpoint-induced appearance changes. To address this, we propose Video Geometry Corrector (VGC), a post-hoc video-to-video model trained on synthetic paired supervision. Starting from real videos with diverse camera motion and pose annotations, we construct VG-Pairs with a synthetic paired-supervision data generation pipeline. Each video clip is treated as a geometry-consistent target and paired with a distorted counterpart synthesized by a pretrained image-to-video inpainting model using trajectory-adaptive keyframes. VGC learns to map the distorted input to the geometry-consistent target without modifying the source generator, and uses optical flow as an auxiliary cue to help disentangle camera motion from object motion. Experiments on pose-conditioned and prompt-driven benchmarks show that VGC improves geometric consistency across multiple source generators, and scaling to a larger backbone further extends the framework toward more general video refinement. --- ### Rethinking the design space of Vanilla Pixel Diffusion Transformers Authors: Soumik Mukhopadhyay, Long Mai, Abhinav Shrivastava, Aniruddha Mahapatra Published: 2026-10-16 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2610.23854v1 Pixel-space diffusion models have recently re-emerged as a compelling alternative to latent diffusion, avoiding the lossy latent bottleneck and separately trained autoencoder. JiT shows that a vanilla diffusion transformer can generate directly in pixel space by replacing the commonly used velocity prediction ($\boldsymbol{u}$-prediction) with clean image prediction ($\boldsymbol{x_0}$-prediction). In this work, we revisit this choice and introduce MFlow, an adaptive parameterization that learns to interpolate between $\boldsymbol{x_0}$- and $\boldsymbol{u}$-prediction across principal directions of the data, learned end-to-end with diffusion training. We find that the preferred parameterization varies systematically with the data representation and model capacity -- notably, increasing model capacity shifts preference toward velocity prediction. We evaluate MFlow across ImageNet, UCF-101 video, and large-scale text-to-image generation, demonstrating competitive or improved generative performance across diverse settings. In addition, we find that vanilla pixel diffusion transformers, irrespective of parameterization, retain a persistent high-frequency deficit relative to real images. To address this, we introduce ConvRefiner, a lightweight convolutional module trained post-hoc with an adversarial loss while keeping the diffusion backbone frozen. With only a small amount of additional training, ConvRefiner restores the high-frequency statistics of generated images while preserving FID. Project webpage: https://soumik-kanad.github.io/mflow-diffusion/. --- ### Behavioral Couplings: From Formation to Behavioral Emergence in Language Models Authors: Dongyoon Hahm, Woogyeol Jin, Dennis Wei, Yi Zhou, Nathalie Baracaldo, Kimin Lee Published: 2026-10-16 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2610.23847v1 Fine-tuning large language models (LLMs) can induce behaviors beyond those explicitly targeted. For example, training a model to respond more warmly can make it more sycophantic, and training it to write insecure code can cause broad misalignment on prompts unrelated to coding. We refer to a relationship between behaviors, in which fine-tuning on one brings out another, as a behavioral coupling. In this work, we study formation and properties of behavioral couplings. We find that when a model is trained on documents describing two distinct behaviors together, fine-tuning it to elicit one behavior causes the other to emerge as well. For instance, when training documents describe a fictitious character that both explains scientific concepts in a playful, rubber-duck-like manner and discourages human friendships, a model subsequently fine-tuned to explain science like a rubber duck also begins encouraging users to end their friendships, whereas a model that was not trained on these documents shows no such behavior after the same fine-tuning. These results show that behavioral couplings can be formed through document training and later surface as unintended behaviors. More concerningly, we find that couplings can compose. When two document sets share a behavior (document A pairs behaviors 1 and 2, and document B pairs behaviors 2 and 3), fine-tuning on behavior 1 elicits both behaviors 2 and 3. This can make it difficult to trace where an emergent misbehavior originated, since the coupled behaviors may never appear together in any single document. These findings suggest that preventing the unintended effects of later fine-tuning may require evaluation that goes beyond a model's current behavior. --- ### AI-Driven Reproducibility and Analytical Robustness in Scientific Discovery Authors: Shicheng Liu, Krista Opsahl-Ong, Andrew Drozdov, Julian Killingback, Arnav Singhvi, Ronak Pradeep, Michael Bendersky, James C. Dickerson, Monica S. Lam Published: 2026-10-16 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2610.23845v1 Reproducible and analytically robust research findings are essential to scientific progress, but evaluating these properties typically requires costly manual effort. We investigate whether LLM agents can help automate reproduction and robustness analysis, using a medical case study grounded in the Surveillance, Epidemiology, and End Results (SEER) database, a widely used U.S. cancer registry underlying tens of thousands of published studies. First, we introduce SEER-Repro, a benchmark of 20 published SEER-based papers together with the data and resources required to reproduce their findings. Second, we create an AI agent that successfully reproduces 77.4% of 2,190 atomic claims, while providing executable baselines for further analysis. Third, we develop an agentic analysis pipeline to test the robustness of the medical findings by identifying analytical choices underlying each finding, proposing defensible alternatives, and rerunning the analysis to determine whether those choices affect the conclusion. Across published papers in SEER-Repro, our pipeline identifies potentially consequential analytical choices in 9.5% of fully reproduced findings and flags them for expert review. These results show how LLM agents can support scientific review by reproducing findings, systematically testing their robustness, and directing expert attention toward potentially consequential analytical choices. --- ### StopWatch: Goal Grounding for Object-goal Navigation Authors: Xinhao Liu, Yunsheng Tian, Yuheng Qiu, Pieter Abbeel, Xi Chen, Guanya Shi, Chen Feng Published: 2026-10-16 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2610.23841v1 Pretrained VLMs bring rich world knowledge and semantic priors to object-goal navigation, and fine-tuning a VLM into a navigation policy has become a common recipe. Despite this progress, success rates remain low, and it is unclear which capability these fine-tuned policies lack. Our diagnosis identifies goal grounding as the dominant failure. These policies explore well, yet often fail to notice that the goal is already in view or to estimate how far away it is. To address this failure, we ground the goal explicitly. Explicit grounding substantially improves success and reaches state-of-the-art results on six benchmarks across three scene collections. We also correct annotation defects in these benchmarks, so that future methods are evaluated more faithfully. Our analysis on the clean benchmarks shows that, with ground-truth grounding, our policy nearly matches the expert that generated its demonstrations, leaving the headroom in perception rather than policy learning. Our work points to goal grounding as a missing piece of object-goal navigation and offers a simple and effective solution to the task. --- ### DiscoveryRSI: Recursively Learning to Discover Valuable Hypotheses Authors: Jianyuan Zhong, Chenwei Wu, Zhaochen Yu, Xixian Jiang, Xuewei Li, Hao Xiao, Xilin Dai, Junyang Wang, Jiaru Zou, Zhiqing Cui, Boyuan Zheng, Jing Xiong et al. Published: 2026-10-16 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.23839v1 Scientific discovery requires developing worthwhile hypotheses into practical investigations, yet learning from this evolving research process remains challenging. We introduce an operational definition of valuable and testable research hypotheses: evidence-grounded claims about consequential uncertainties, coupled with feasible investigations, explicit decision criteria, and alternative explanations. Our DiscoveryRSI framework develops hypothesis trees through multi-agent evolutionary search, compiles selected investigations into executable Harbor tasks, and recursively learns through three mechanisms: hypothesis credit optimization attributes scientific assessments to documented research contributions; harness replay identifies productive strategies and recurring failures to refine research workflows; and rediscovery applies accepted improvements to new investigations, generating further experience for subsequent learning. We also introduce DFM-Bench, which provides comprehensive assessment of hypothesis quality and cumulative research progress at the levels of hypotheses, revisions, development paths and research runs. Across four life-science domains, automated evaluation shows that hypothesis quality rises from 4.86 for the base model to 5.39 after two rounds of self-improvement, with the large gains in falsifiability and data resolvability. We further validate hypothesis quality through expert review, comparing our DiscoveryRSI-27B with other research agents. Preliminary human assessments show that DiscoveryRSI-27B scores higher than GPT-6 Luna on hypothesis importance and whether claims are plausible and evidence-bounded. DiscoveryRSI-27B achieved a 6.3% rate of hypothesis correspondence with research published after the model cutoff, largely outperform GPT-6 with 2.5% and Claude Opus 5 with 2.3%, while delivering greater human-rated improvement along research paths. --- ### Task-aligned spectral inductive biases in parameterized quantum circuits Authors: Felix Frohnert, Adrián Pérez-Salinas, Sebastian Lange, Marcus Schwaebisch, Evert van Nieuwenburg, Vedran Dunjko Published: 2026-10-16 Categories: quant-ph, cs.LG arXiv: https://arxiv.org/abs/2610.23834v1 Parameterized quantum circuits are widely investigated in quantum machine learning, yet how their architecture can provide task-aligned inductive biases remains poorly understood. We study data reuploading quantum circuits with two distinct inputs: a signal that varies between samples and a fixed, task-defined spectral query that specifies how the signal should be probed. We show that encoding the query can change the circuit's hypothesis class over the signal by modulating how its existing signal frequencies are combined, without introducing new sample-dependent information. This mechanism matches tasks built on nonuniform Fourier transforms, whose evaluation frequencies specify the query and whose sampling positions guide its encoding. We examine this connection in a classification task inspired by synthetic aperture radar, where acquisition geometry determines a query for classifying unfocused spectral patches before image formation. Across small-scale spectral and radar-like tasks, aligned queries improve learning from limited data over parameter-matched circuits with mismatched or absent queries. These results provide a route from known spectral task structure to the design and validation of inductive biases in parameterized quantum circuits. --- ### Beyond the Answer: Student-Conditioned Trace Construction for Reasoning Distillation Authors: Shaoang Li, Yanhang Shi, Yufei Li, Mingfu Liang, Frank Shyu, Sandeep Pandey, Luke Simon, Xi Liu, Jian Li Published: 2026-10-16 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2610.23831v1 A reasoning trace can accompany a correct answer without providing effective supervision for a particular student. We study how to construct traces that improve learning beyond answer-only supervision by considering both their intermediate content and their accessibility to the target learner. We introduce ReDiST, a student-conditioned trace-construction and distillation framework for evidence-rich reasoning. Starting from the student's own attempts, ReDiST revises answer-correct drafts against the supplied evidence and repairs unsuccessful drafts with additional guidance from the verified answer. A frozen student-matched reader screens and ranks original and edited candidates using answer recovery and verified-answer probability, given the question, evidence, and candidate trace. We distill the selected targets while balancing trace and final-answer supervision with an auxiliary answer loss. Construction and selection occur offline, and inference uses only the distilled student. Experiments on question-answering benchmarks show that ReDiST can improve both source-task and cross-benchmark performance over answer-only, original-trace, and the evaluated trace-selection and rewriting baselines. Across supervision recipes, performance rankings can differ between source and transfer benchmarks, highlighting the importance of evaluating trace teaching utility across distributions. --- ### Waiting Buys Exactly Two Moments: Endogenous Identification in Prediction-Driven Allocation Authors: Rama AlHamidi, Rasul Khanbayov, Erchin Serpedin, Hasan Kurban Published: 2026-10-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.23830v1 A planner with a fixed budget of preventive help must decide whom to help and when. Waiting reveals risk but removes intervention opportunities as higher-risk individuals leave first. We characterize this tradeoff under repeated noisy signals and risk-dependent attrition: in the canonical model, a length-$τ$ observation prefix identifies exactly the latent risk moments $m_j=\mathbb E(p^j)$ for $j=0,\ldots,2τ-1$, buying two new moments per additional period. These identify average next-period attrition among survivors but need not identify allocation welfare or attrition among those prioritized for treatment. Our observationally equivalent constructions establish unavoidable timing regret at any sample size for a fixed observation length, while exact certificates determine whether all compatible populations share a unique optimal date. Matched experiments separate the effects of estimation, bootstrap averaging, and regret weighting. Longer observation often resolves timing ambiguity, but the optimal date may already have passed. In our experiments, bootstrap averaging and early stopping improve decisions, while regret weighting adds no improvement in pooled mean squared regret: better statistical fit need not yield better allocation welfare. The code and artifacts are available at https://github.com/KurbanIntelligenceLab/waiting-buys-two-moments. --- ### Quality-of-Transmission Estimation in Quantum Networks: Compute, Simulate, or Learn? Authors: Anis Bekri, Amar Abane, Van Sy Mai, Abdella Battou, Saddek Bensalem Published: 2026-10-16 Categories: quant-ph, cs.LG, cs.NI arXiv: https://arxiv.org/abs/2610.23827v1 Future quantum networks will rely on control-plane decisions such as routing, scheduling, entanglement provisioning, purification, and memory allocation. Each decision depends on a timely and reliable estimate of the quality of the entanglement that a candidate path can deliver, with end-to-end fidelity as a central metric. Inspired by the optical-networking experience with quality-of-transmission (QoT) estimation, this article asks when a quantum controller should compute fidelity analytically, simulate it, or learn a surrogate model. The optical analogy is useful but incomplete: optical QoT estimation often predicts a scalar transmission margin, whereas quantum QoT estimation must account for probabilistic entanglement generation, random memory waiting times, decoherence, state consumption, and measurement constraints that can make fidelity a stochastic target. We propose a compute/simulate/learn framework for quantum QoT estimation and illustrate it with a simulation-based proof of concept. Our study shows that analytical composition can be sufficient in simple regimes, that simulation becomes necessary when stochastic memory effects shape the delivered fidelity distribution, and that lightweight learned surrogates can approximate simulator labels at much lower runtime cost for online control. We close with open challenges for deployment, including stochastic targets, sim-to-real transfer, data-generation cost, physics-informed learning, and generalization beyond individual paths to full network topologies. --- ### Self-Building Labs Authors: Jiaru Bai, Yuchi Zhao, Han Hao, Miroslav Bogdanovic, Yang Cao, Varinia Bernales, Alán Aspuru-Guzik Published: 2026-10-16 Categories: cs.AI, cs.MA, cs.RO arXiv: https://arxiv.org/abs/2610.23826v1 Self-driving laboratories (SDLs) accelerate scientific discovery by automating experimental execution and optimization. AI agents can increasingly propose new experiments, but existing SDLs can only run the procedures they were built for. Adapting them to a new experiment still takes extensive manual engineering, which makes laboratory flexibility the bottleneck for scaling discovery. We introduce the self-building laboratory (SBL), which designs, configures, and operates its own laboratory setup given a high-level scientific goal. SBL starts from whatever already exists, from an empty room to a working SDL, and builds the missing capabilities: the lab layout, its digital twin, robot skills, and experimental workflows. We demonstrate the system working across different robots and setups, scaling from a single workstation to laboratories with several robots working together. We validate SBL's end-to-end capabilities through a real-world quantum-dot synthesis experiment. By shifting the role of human researchers from manually configuring and programming device automation to specifying scientific objectives, SBL makes scientific automation more accessible, flexible, and scalable. Project website: https://self-building-labs.github.io/ --- ### ENFR: Evidence Networks with Flow-Matched References for Amortized Simulation-Based Model Inference Authors: Kai Lehman, Jameson Dong, Carolina Cuesta-Lazaro, Niall Jeffrey, Benjamin D. Wandelt, Francisco Villaescusa-Navarro, Sven Krippendorf, Jochen Weller Published: 2026-10-16 Categories: stat.ML, astro-ph.CO, cs.LG arXiv: https://arxiv.org/abs/2610.23825v1 The evidence, $\mathcal{Z} = p(x | \mathcal{M})$, of a data-generating model $\mathcal{M}$ is a powerful tool in Bayesian frameworks: it enables model inference, model misspecification tests, and goodness-of-fit assessment as an alternative to standard discrepancy statistics, e.g. $χ^2$. While versatile, the evidence is notoriously difficult to compute, even when the likelihood is available. In both likelihood-based and simulation-based inference, estimating $\mathcal{Z}$ provides an immediate solution to high-dimensional goodness-of-fit or model misspecification tests: using $\mathcal{Z}(x)$ as the test statistic induces a minimum-volume level-$α$ test. Such tests are essential to assess model fidelity, which is necessary to trust simulation-based parameter inference. Existing learned approaches largely target Bayes factors, which only measure evidence ratios. Instead, we provide accurate, fast, and amortized estimates of the absolute evidence. We present ENFR: Evidence Networks with Flow-matched References. Building on the Evidence Network framework of Jeffrey & Wandelt (2024), the proposed method first learns Bayes factors with respect to a flow-matched reference, from which the absolute evidence is recovered. We show improvement in estimation of $\mathcal{Z}$ over the flow-based baseline in all applications considered and the best performance of all density estimation methods considered in our benchmarks. We furthermore introduce and provide the proof for an architecture that jointly learns the individual evidences of a set of models $\{\mathcal{M}_i\}$. We demonstrate the performance and scaling behavior of these approaches on data from a variety of scientific applications. --- ### Learning without relearning physical symmetry: an SO(3)-equivariant convolutional network (CNN) on the sphere Authors: Joshua Williamson, Niall Jeffrey, Lorne Whiteway Published: 2026-10-16 Categories: stat.ML, astro-ph.CO, cs.LG arXiv: https://arxiv.org/abs/2610.23821v1 Many of the most important datasets in the physical sciences live natively on the sphere, and these data often carry no preferred position or orientation. Using methods that do not reflect this symmetry leads to far higher simulation requirements, which can be catastrophic for scientific analyses (forcing reliance on cheap, imperfect models that bias results). We present a novel spherical implementation of a gauge equivariant mesh architecture that is specifically designed for the Hierarchical Equal Area isoLatitude Pixelization (\healpix{}) of the sphere. The $\mathrm{SO}(3)$-equivariant convolution is built from steerable filters, parallel transport and spin-weighted features. The architecture supplies the exact symmetry, so the network does not spend training data learning it. The convolution operations are constructed to give provably exact equivariance, given a band-limit. Our full CNNs can achieve SO(3)-invariance error at per-cent-level and lower, which is controlled through well-understood hyperparameters. On benchmarks, our technique gives the most accurate dense gradient regression and competitive cosmic microwave background foreground removal and denoising. The improved simulation efficiency matters most in simulation-based inference (SBI), where high-fidelity simulations are expensive and neural compressors require large training sets, so a fixed budget forces analyses with less accurate simulators. In cosmology lensing SBI, our technique yields the tightest posteriors at matched simulation count. This approach is a novel method that will enable new convolutional neural network analyses, including generative and inference tasks, for processes and data on the sphere. --- ### CocoRNA: Collective RNA Design with Cooperative Multi-agent Reinforcement Learning Authors: Tianmeng Hu, Biao Luo, Ke Li Published: 2026-10-16 Categories: cs.LG, cs.MA arXiv: https://arxiv.org/abs/2610.23820v1 Designing RNA sequences that reliably fold into specific secondary structures is essential for understanding their biological functions but remains a challenging computational problem. We propose CocoRNA, a cooperative multi-agent reinforcement learning framework for RNA inverse design. CocoRNA simplifies the design task by decomposing it into smaller sub-problems, each solved collaboratively by multiple agents. This approach reduces the complexity of the problem and improves the exploration of design policies. During training, a centralized critic uses global structural information to guide the agents, enabling them to jointly optimize their design strategies. As a result, CocoRNA learns high-quality RNA design policies that generalize effectively to unseen structures without additional training. Experiments on the Rfam dataset demonstrate that CocoRNA substantially outperforms state-of-the-art methods in both success rate and design speed. Further experiments on other biological sequence design tasks highlight the effectiveness and broad potential of CocoRNA for complex design tasks. --- ### Acceptance Is Not Speed: Length Inflation in Training-Free Lossy Speculative Decoding Authors: Chiatzen Wang, Bill Xu, Haochen Gu, Hongyang Zhang Published: 2026-10-16 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.23818v1 Speculative decoding typically characterizes speedup by draft tokens accepted per verification round. Lossless verification preserves the target model's output distribution and thus expected completion length, making this metric a meaningful efficiency proxy. Relaxed (lossy) verification accepts tokens that lossless verification would reject, potentially altering that distribution. We identify a length inflation phenomenon: relaxed verification lengthens completions, primarily by extending reasoning traces, largely offsetting apparent gains in accepted tokens per round. We evaluate existing training-free relaxed verification rules on twelve target-drafter pairs against lossless verification on identical prompts, measuring completion length, verifier rounds, wall-clock time, and task accuracy. At each rule's most relaxed evaluated setting, relaxed verification on average accepts $1.34\times$ as many tokens per round but produces $1.54\times$ longer completions. For rules with higher acceptance lengths, tokens accepted only under relaxed verification tend to have low target-model probability, contributing to length inflation. For rules that reduce verifier rounds, accuracy typically drops substantially. Further analysis traces some failures to continued reasoning that exhausts the budget needed to deliver a final answer. Overall, accepted tokens per round alone is an unreliable measure of decoding speed under relaxed verification. Completion length and verifier rounds must also be reported to assess actual efficiency. --- ### Learning Personalized Memory Gating from Delayed One-Sided Feedback Authors: Kaixuan Ji, Zixiang Chen, Wenting Zhao, Cheng Qian, Heng Wang, Weizhi Zhang, Jielin Qiu, Liangwei Yang, Quanquan Gu, Silvio Savarese, Shelby Heinecke, Huan Wang Published: 2026-10-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.23812v1 Long-term memory enables language-model agents to personalize future interactions, but a finite memory bank cannot preserve every extracted fact. Existing memory gating policies are typically shared across users and therefore fail to account for user-specific patterns of future reuse. In this paper, we study memory gating at the fact level. We first propose a retrieval-based labeling strategy that labels each fact by whether it is later retrieved and incorporated into responses. We then formulate online memory gating as contextual apple tasting with delayed one-sided feedback, and propose Warm-Start UCB, which combines offline learning from existing data with online adaptation to the current user. Our theoretical analysis establishes a high-probability regret upper bound of $\tilde{O}(Tε\wedge d\sqrt{T})$ when the delay window is at most $O(\sqrt{T})$, where $T$ is the total number of rounds, $ε$ is the initialization error, $d$ is the dimension of the feature map, and $\tilde{O}(\cdot)$ hides constant and poly-logarithmic factors. The results of our experiment demonstrate that our method outperforms all baselines under different memory budgets and history lengths, establishing it as a promising personalized memory gating policy. --- ### Explainable Machine Learning Analysis of Temperature Effects on Mechanical Strength of Fiber-Reinforced High-Performance Concrete Authors: Jagaran Chakma, Zhiguang Zhou, Badhan Chakma, Priyanta Chakma Published: 2026-10-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.23811v1 Predicting the compressive strength of fiber-reinforced high-performance concrete subjected to temperature exposure is challenging because to the intricate interdependencies of mixture composition, fiber properties, curing conditions, and temperature. A data-driven framework to predict compressive strength utilizing 1,204 experimental records containing a diverse array of material designs and exposure situations. This study evaluates eight machine-learning models and demonstrate that ensemble approaches routinely surpass individual learners. Both gradient boosting and extreme gradient boosting exhibit superior performance on unseen data, each attaining a R^2 of 0.903. Gradient boosting produces the minimal root mean square error (6.67 MPa), whereas extreme gradient boosting achieves the lowest mean absolute error (3.97 MPa) and mean absolute percentage error (10.60%). The models are further interpreted utilizing Shapley additive explanations and partial dependence analysis, which reveal temperature as the primary factor influencing compressive strength, succeeded by fine aggregate, superplasticizer, cement content, water-to-binder ratio, and water content. Strength diminishes significantly with rising temperature, albeit the extent of deterioration is contingent upon the specific combination design. The best performing models are subsequently implemented in a Python-based graphical user interface for expedited prediction. Our findings offer a precise and comprehensible methodology for evaluating temperature-dependent compressive strength and facilitate the practical, data-driven design of fiber-reinforced high-performance concrete. --- ### Steering beyond Language: Improving Multilingual Training-Free Text Embeddings via Paired-Residual Subspace Removal Authors: Ailiang Lin, Zhuoyun Li, Yusong Wang, Keyu Mao, Kotaro Funakoshi, Manabu Okumura Published: 2026-10-16 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.23807v1 While deriving text embeddings directly from frozen LLMs has emerged as a promising direction, existing methods focus almost exclusively on English, leaving multilingual settings largely unexplored. In this work, we present the first systematic study of multilingual training-free text embeddings in LLMs. Our analysis reveals a language-conditioned embedding geometry in which semantically equivalent sentences remain misaligned across languages. We hypothesize that language-specific variation can be disentangled from semantic content to improve embedding quality. To this end, we propose Paired-Residual Subspace Removal (PRSR), a training-free inference-time intervention that steers LLM representations toward a more language-invariant semantic space. PRSR first constructs paired residuals from multilingual parallel sentences to capture language-specific deviations. It then estimates layer-wise low-rank subspaces from these residuals and suppresses the corresponding components in the last-token hidden states. We conduct more than 200 monolingual evaluations across 18 languages using MTEB and MMTEB, along with cross-lingual bitext mining between English and over 200 other languages. Empirical results demonstrate that PRSR consistently improves the performance of existing training-free baselines in both monolingual and cross-lingual settings across different LLMs. --- ### Beyond SAEs: Consistent Concept Discovery with Sparse Coding Authors: Jinho Choi, Hyesu Lim, Jaegul Choo, Steffen Schneider Published: 2026-10-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.23801v1 Sparse autoencoders (SAEs) explain foundation model representations by decomposing activations into sparse combinations of learned dictionary atoms. However, the learned dictionaries can vary across training runs, limiting the reliability and reproducibility of SAE-based analyses. We propose Consistent Sparse Dictionary Learning (ConSDL), which replaces the standard linear encoder with per-sample sparse coding. This is motivated by our synthetic analysis showing that coefficients from a single linear encoder pass are suboptimal compared with those obtained by per-sample optimization, suggesting that sparse coding is a reliable mechanism for dictionary learning. Across 16 synthetic settings, ConSDL achieves near-perfect dictionary and coefficient recovery. These gains translate to state-of-the-art cross-seed consistency across four vision and language settings, where ConSDL improves dictionary and coefficient consistency by 17.6% and 35.9%, respectively, over the average of six SAE baselines. --- ### Task-aware Kernel Stein certificates for Rényi differential privacy Authors: Leoni Carla Wirth, Tara Trautwein, Gesine Reinert Published: 2026-10-16 Categories: stat.ML, cs.CR, cs.LG arXiv: https://arxiv.org/abs/2610.23798v1 Rènyi differential privacy, based on Rènyi divergence, has become a notion of choice for privacy guarantees. However, outside the Gaussian setting, Rènyi divergence can be difficult to compute. In particular, Rènyi differential privacy guarantees that exploit task-specific information, as in Rènyi Pufferfish privacy, can be challenging. Here we use kernel Stein discrepancies based on escort distributions to provide certificates for Rènyi differential privacy. By designing the kernel to focus on the relevant privacy directions, we also derive task-aware privacy certificates. We provide exact identities for Gaussian and Laplace mechanisms and bounds for exponential mechanisms, with separate task-aware guarantees. A real data set example illustrates how the protected comparison set and the released subspace jointly determine the resulting certificates. --- ### FuTransformer: FP8 prefill and INT4 decode for Llama-style inference on Hopper Authors: Wei Wang Published: 2026-10-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.23796v1 Transformer prefill reuses weights across tokens and is dominated by matrix multiplication and activation data movement; single-token decode has limited reuse and is dominated by weight and KV-cache reads. We present FUTRANSFORMER, a CUDA implementation of a Llama-style Transformer block for NVIDIA Hopper GPUs. It applies CODA's GEMM-plus-epilogue approach to inference, adding direct KV-cache placement, folding the fixed RMSNorm gain into weights, writing FP8 output directly with delayed scaling, and supporting prefill without padding. Decode uses INT4 projection weights and an INT4 KV-cache copy. Weights and keys follow Tensor Core fragment layouts for direct dequantization into MMA operands without full intermediate tiles. A block-diagonal Hadamard transform reduces cache quantization error from outlier channels. On one H100, prefill is up to 1.48x faster than compiled PyTorch FP8 and reaches 1.29 PFLOP/s. For gate/up projection with SwiGLU at the 8B shape, our BF16 path is 1.13x faster than CODA. Our FP8 path is 2.02-2.18x faster than the evaluated BF16 CODA path. Across 8B and 70B shapes at batches 1-32, INT4 decode is 1.3-2.4x faster than the faster of PyTorch's BF16 and INT4 blocks at each point: 2.1-3.3x faster than compiled, CUDA-graphed BF16 and 1.3-6.3x faster than the same block using PyTorch's INT4 projection kernel, which targets a single query row and loses to BF16 at batch 32. It is also 31-51% faster than our FP8 path. Complete Llama-3.1-8B decode takes 2.8 ms per step at batch one, versus 8.1 ms for the compiled transformers implementation. Decoding every WikiText-2 token through the INT4 weight path raises perplexity from 6.24 to 7.23 with round-to-nearest weights or 6.99 with GPTQ in the same format; the rotated INT4 cache adds 0.20. The kernels match a quantized reference computation within 0.001 perplexity. --- ### Persistent Planar Memory for Video World Models Authors: Yuze He, Bin Tan, Zelin Gao, Yujun Shen, Yong-Jin Liu, Nan Xue, Yinghao Xu Published: 2026-10-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.23795v1 Video world models that generate and explore environments at scale need a persistent 3D memory of what they have produced. Plane primitives offer a natural candidate: a compact set of oriented planes captures the dominant structural elements (e.g., walls, floors, facades) of indoor and outdoor scenes, while requiring only 7 parameters per primitive. We present PPMem, a video world model that adopts plane primitives as its persistent 3D memory. PPMem augments a video diffusion transformer with a planar prediction head and a Depth Token Fusion (DTF) module: each autoregressive chunk jointly produces RGB video and planar geometry, which merges into a persistent plane memory that conditions subsequent chunks via rendered depth. The resulting memory is three orders of magnitude more compact than per-pixel point clouds (~100K primitives, 5MB for a full scene), geometrically explicit (metric depth, normals, exportable surfaces), cross-view consistent (jointly predicted by the shared backbone), and adaptive (refined by the merging procedure as generation proceeds). On DL3DV and RealEstate10K, PPMem outperforms prior 3D-grounded world models in video quality while jointly producing metric-scale depth, surface normals, and exportable planar geometry, sustaining coherence across hundreds of frames under large viewpoint changes. Project page: https://hyzcluster.github.io/ppmem. --- ### DrugHarness: An Evolvable Agent Harness for Computational Drug Discovery Authors: Yuxing Chen, Zhisheng Zhang, Cheng Tang, Wei Li, Minghui Zhang, Ziyan Huang, Shaocong Wei, Jiawei Chen, Junru Hu, Hongze Zhu, Jianghan Shen, Min Cen et al. Published: 2026-10-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.23791v1 Computational drug discovery requires agents to compose scientific operations and adapt to changing evidence and constraints. Here we introduce DrugHarness, an evolvable agent harness coupling composable scientific execution with conditional skill induction. Its environment integrates over 80 scientific operations, biomedical resources and task-specific code, preserving associations among candidates, results and artifacts. From execution trajectories and outcome feedback, DrugHarness induces action hypotheses with observable applicability conditions, recommended actions and supporting evidence. An independent review agent evaluates candidate skills derived from these hypotheses through source verification and, when needed, targeted execution trials. Admitted skills guide subsequent tasks and are revised through feedback. Evaluation on MolBench and SMDD-Bench demonstrates capabilities in molecular screening, optimization and constrained design. Without evolution, DrugHarness exceeds reported MolClaw-CC results by 10.8 percentage points in affinity-comparison accuracy and 55% in mean top-three active hits on MolBench. Retrospective evaluation on skill-development tasks shows that evolution increases Qwen's affinity-comparison accuracy from 62.2% to 81.1% and optimization success from 79.5% to 87.2%. In a prospective HPK1 study, DrugHarness achieves a more favorable median docking score than Biomni among system-specific candidates. A synthesized compound achieves a cellular IC50 of 14.19 nM, a 2.64-fold potency improvement over the best input reference, with activity competitive with two selected compounds designed by experienced medicinal chemists. These results support conditional skill evolution for scientific agents and demonstrate a workflow connecting computational drug design with experimental validation. --- ### The Collection of a Real-World, Large-Scale Dataset for Automated Skill Evaluation in Central Line Dressing Change Authors: Ummey Tanin, Shannan K. Hamlin, Hsin-Mei Chen, Peizhu, Qian Published: 2026-10-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.23789v1 Central line-associated bloodstream infections (CLABSIs) remain a major source of preventable morbidity and mortality in healthcare settings. Proper execution of the central line dressing change (CLDC) procedure is essential for infection prevention, yet current approaches to competency assessment rely primarily on manual ob- servation by clinical educators, making evaluation time-intensive, difficult to scale, and limited in consistency and granularity. These challenges highlight the need for AI-assisted skill evaluation methods that can support more objective, reproducible, and scalable assessment of clinical performance. However, progress in this area has been constrained by the lack of broad-scale, clinically grounded datasets for developing and evaluating such methods. In this work, we present the collection process of a large-scale video dataset for CLDC skill evaluation, comprising 365 recordings of registered nurses collected during the 2026 annual competency exam at Houston Methodist Hospital. Each video is paired with subtask-level temporal annotations and clinical performance assessments spanning 17 subtasks of the procedure. We describe the data collection and curation pipeline, including pilot testing of record- ing configurations, annotation protocol design, and post-collection processing. We further establish the feasibility of video-based skill assessment through benchmark experiments with spatiotemporal deep learning models. This dataset provides a foundation for future research on automated clinical skill assessment, feedback generation, and AI-assisted training in nursing education. --- ### Parametric Resonance in Primal-Dual Learning for Slowly Non-Stationary Constrained MDPs Authors: Maxime Baelde Published: 2026-10-16 Categories: stat.ML, cs.LG, eess.SY, math.OC arXiv: https://arxiv.org/abs/2610.23788v1 Primal-dual methods for constrained Markov decision processes are analyzed under a two-timescale assumption, with non-stationarity entering through two channels. In the additive channel, where the constraint level oscillates, the dual oscillation saturates at a floor set by the moving optimum and is amplified linearly by the timescale ratio. In the parametric channel, where the constraint sensitivity oscillates, a coherent modulation carries no resonant forcing at any depth: the dual update's stiffness modulation cancels the primal update's damping modulation. Instability instead comes from a mismatch between the constraint estimate used by the primal update and the measurement used by the dual update, producing a parametric resonance at twice the pair's natural frequency. The tolerated mismatch grows with the square root of the forcing bandwidth and collapses with the square root of the dual-to-primal step-size ratio. These results hold on the tangent linear-quadratic reduction around an active saddle, for one constraint and for $K$ constraints under a common modulation and an isotropy condition. Driving both updates from the same estimate removes the resonant forcing but introduces a stationary offset equal to the estimator's bias. In a Lagrangian soft actor-critic agent, the multiplier locks onto the sub-harmonic at the timescale ratios its identified linear loop predicts and a coherent cost critic suppresses the lock-in, while a proportional (PID) term, predicted to leave the lock-in in place, suppresses most of it through the projection of the multiplier. --- ### DLite: History-free Speculative Decoding for Agentic AI Authors: Jiaming Xu, Hanzhen Wang, Tianlang Zhao, Jiewen Xiao, Chengze Yuan, Jiayi Pan, Yongkang Zhou, Jiancai Ye, Yu Wang, Guohao Dai Published: 2026-10-16 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.23787v1 Speculative decoding has become a mainstream technique for accelerating large language model (LLM) inference by using a lightweight draft model to generate candidate tokens that are subsequently verified by the target model. However, agentic workloads introduce long and continuously evolving contexts and frequent multi-turn interactions. Under such workloads, we observe that existing draft models suffer from up to an 80% degradation in acceptance length, while maintaining their historical KV cache introduces substantial system overhead. In this paper, we identify the growing historical context as a common source of both problems and introduce DLite, a history-free speculative decoding framework for agentic AI. DLite directly reuses contextual hidden states from the target model and performs local speculative prediction without explicitly maintaining the historical context, transforming an increasingly complex modeling problem into local simple prediction problem. A lightweight sequential head further restores intra-block causal dependencies with low overhead. To effectively train this heterogeneous history-free architecture, we introduce a tailored two-stage training strategy. Experiments on general-purpose, long-context and agentic workloads show that DLite achieves 2-6 acceptance length and outperforms the state-of-the-art speculative decoding method, DSpark, up to 70%. --- ### Sampling the XY model with an attention-based neural network Authors: Piotr Białas, Christian D. Morales, Tomasz Stebel, Dawid Zapolski Published: 2026-10-16 Categories: cond-mat.dis-nn, cond-mat.stat-mech, cs.LG, hep-lat arXiv: https://arxiv.org/abs/2610.23783v1 We present a transformer-based variational autoregressive network for sampling lattice systems with continuous degrees of freedom and apply it to the two-dimensional XY model near the Berezinskii-Kosterlitz-Thouless transition. The architecture is combined with physics-informed ingredients: locality-informed attention and approximate probabilities. The resulting sampler significantly outperforms existing neural samplers. We train the model on lattices up to $96\times96$, verify with a mode-dropping estimator that no parts of the configuration space are missed, and reproduce the energy, magnetization and helicity modulus obtained with the traditional Markov Chain Monte Carlo algorithm. --- ### Mesoscopic learning dynamics of extensive-width neural networks Authors: Shu Zhou, Jean Barbier, Sebastian Goldt Published: 2026-10-16 Categories: stat.ML, cond-mat.dis-nn, cond-mat.stat-mech, cs.LG arXiv: https://arxiv.org/abs/2610.23779v1 Understanding how stochastic gradient descent learns internal representations in wide neural networks trained on rich target functions is a central problem in machine learning. We study this question in two-layer neural networks learning target functions represented by networks of the same architecture, with arbitrary nonlinearity, and with network width and input dimension growing proportionally. In this regime, standard approaches for describing the learning dynamics require tracking a diverging number of overlaps, which measure correlations between learned and target features, leaving no obvious description in terms of a few order parameters. Here, we develop a mesoscopic description of learning by characterizing the distribution of overlaps. In the early stages of learning, we find that a Gaussian description of overlap statistics reduces the learning dynamics to a few collective variables that track learning of the target function's linear and quadratic components. We then estimate the timescale of specialization, when Gaussian closure breaks down and individual learned features begin to strongly correlate with specific target features. We find that specialization in extensive-rank networks is accelerated via a quadratic shielding mechanism, whereby learning the linear and quadratic components of the target function filters gradient fluctuations. We finally describe how the activation function determines the pattern of specialization and characterize the subsequent refinement of learned features. Together, these results show how collective learning gives way to individual feature discovery and clarify when learning in large neural networks admits a simple statistical description. --- ### Video Diffusion Avatars: Taming Video Diffusion Models into Controllable 3D Avatars Authors: Simon Giebenhain, Tobias Kirschstein, Liam Schoneveld, Davide Davoli, Zhe Chen, Matthias Nießner Published: 2026-10-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.23772v1 Video diffusion models (VDMs) trained on internet-scale data encode a rich prior on appearance, motion, and physics that is difficult to replicate with explicit 3D rendering and costly 3D data capture. We introduce Video Diffusion Avatars (VDAs), a method that creates photo-realistic, multi-view consistent avatars from a single image by fine-tuning a VDM for precise control over camera viewpoint, facial expression, and upper-body pose. Departing from 3D morphable models (3DMMs), VDAs use a learned expression space that lifts the expressiveness ceiling of 3DMMs, e.g., for the tongue and mouth interior. However, learned expression codes exhibit heavy viewpoint bias, as our DISTRACT benchmark reveals. We show that this bias can be removed through disentanglement, enabling their use as driving signals for multi-view consistent avatars. Camera and upper-body pose are controlled jointly via proxy-mesh renderings, giving independent control over expression, pose, and viewpoint. A camera-triplet training strategy makes the approach efficient: our models train for 34 hours on a single A100 using only public multi-view data. VDAs outperform state-of-the-art single-image 3D avatars on novel-view reenactment, reducing face LPIPS by 29% and improving perceptual quality (JOD) by 66% on BecomingLit. A static 3DGS reconstruction probe further confirms that our generations are the most multi-view consistent. Built on a video prior, VDAs produce effects beyond the reach of explicit renderers, including physically plausible hair dynamics, shadows, reflections, and refractions. --- ### Logic-Guided Graph Denoising Diffusion Models Authors: Samuel Cognolato, Luciano Serafini, Alessandro Sperduti, Andrea Cavallaro Published: 2026-10-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.23766v1 Graph diffusion models are competitive approaches for generating complex graph-structured data. However, when such distributions have strict structural constraints, diffusion models may fail to capture them exactly, resulting in the generation of invalid graphs. In this paper, we propose a method for grounding graph diffusion models in domain-specific knowledge via First Order Logic (FOL), leveraging its expressive and interpretable formalism to impose structural constraints on the generative process. We incorporate domain knowledge using classifier guidance, a technique that conditions the diffusion model's distribution on external variables to exert control over the sampled data. During the generative process, classifier guidance steers the denoising trajectory to optimize an objective function, which we define as a fuzzy and differentiable relaxation of the logical rules. Our methodology requires only the specification of constraints in FOL, whose satisfaction is encouraged at inference time to guide a pre-trained generative model. We evaluate our approach by comparing the unconditional generation of knowledge graphs with our logic-guided framework, which incorporates domain ontologies as structural constraints during inference. This approach significantly increases the proportion of generated graphs that satisfy the ontological constraints. --- ### Universal Semantic Enhancement for Weakly Supervised Anomaly Detection Authors: Siyu Zhou, Yuqin Xie, Hao Yuan, Yingjie Zhou Published: 2026-10-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.23765v1 Weakly supervised anomaly detection on tabular data is an essential task in many label-scarce applications, since tabular data is widely encountered and it is commonly observed in practice that only a limited number of labeled anomalies are available alongside abundant unlabeled samples. Most existing methods try to learn features that capture the inherent distribution patterns in the target domain. However, such features often struggle to provide a complete description of possible abnormal characteristics and are highly susceptible to overfitting the extremely scarce labels. To address this challenge, we propose a weakly supervised anomaly detection method based on universal semantic enhancement for tabular data, which fuses the universal knowledge from a pre-trained tabular foundation model with the domain-specific knowledge learned on the target dataset. The two types of knowledge are naturally complementary: universal semantics describe the common patterns of tabular data across domains, while the domain-specific features capture the inherent distributions of normal and anomalous behaviors in the target dataset. A prototype-conditioned modulation mechanism is then designed to effectively integrate the two types of features, allowing them to reinforce each other for improved anomaly detection. Extensive experiments on public datasets show that the proposed method outperforms competitive methods when only eight labeled anomalies are available in the training procedure. --- ### From Flow-Box Invariants to Global Conservation Laws: Machine Learning-Assisted Detection of Singularities and Near-Integrability Authors: Jimmie Adriazola, Ioannis G. Kevrekidis, Panayotis G. Kevrekidis, Wei Zhu Published: 2026-10-16 Categories: nlin.CD, cs.LG arXiv: https://arxiv.org/abs/2610.23760v1 Conservation laws reveal invariant structure in dynamical systems and constrain their evolution to lower-dimensional level sets. Locally, however, per the flow-box theorem, every $d$-dimensional system generically admits $d-1$ functionally independent conservation laws near a regular point even though, generically, only a few such laws persist globally. Data-driven methods typically learn conservation laws on a prescribed region of phase space from which training samples are drawn, leaving their behavior beyond that region unresolved. We formulate this local-to-global continuation problem and develop an {expanding-domain neural deflation} framework that tracks the number of independent conservation laws over nested domains. The method recovers the expected $d-1$ local invariants and detects their successive breakdown as the domain expands, relaxing to the expected global conservation law limit. It distinguishes the local invariants (associated with Frobenius integrability) from persistent global structure and shows that the domain scale over which additional laws survive reflects proximity to Liouville integrability. Pointwise losses can localize isolated obstructions, whereas in more complicated dynamics the breakdown of our loss functions is gradual and spatially diffuse. The framework thus provides a data-driven approach for studying the persistence and breakdown of (so-far-learned) conservation laws across phase space. --- ### A Paired RGB-Sonar Dataset for Fish Monitoring with Consumer Sonar Authors: Mourad Derbedrosian, Michael Hobley, Pietro Perona Published: 2026-10-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.23759v1 Imaging sonar enables underwater observation in conditions where optical imaging is ineffective due to darkness and turbid water. However, imaging-sonar systems previously used for ecological monitoring have typically been expensive, limiting their accessibility. Consumer forward-looking sonar has the potential to make fish monitoring more accessible, but its noisy imagery makes annotation and the development of automated methods challenging. We introduce the Huntington and Caltech Koi RGB and Sonar dataset (HaCKRS), which pairs Garmin LiveScope imaging-sonar recordings with top-down RGB video of koi carp. The dataset contains more than 105,000 temporally matched frame pairs, spanning approximately 3.3 hours of recordings across four range and orientation configurations. We provide frame-wise metadata, sonar geometry and coordinate information, synchronization data for all four configurations, and planar registration for the three horizontal configurations. The release focuses on paired observations and calibration rather than task-specific fish annotations. We intend HaCKRS to support annotation and the development of fish detection, tracking, and counting methods, and investigations into the potential of consumer sonar for ecological monitoring. --- ### MTEdit: Packed Trajectories Beat Rollouts for Multi-Turn Image Editing Authors: Houyuan Chen, Fanzhou Wang, Xiangyu Fan, Songlin Yang, Zhitao Yang, Lvmin Zhang, Pei Yang, Hao Zhao, Lei Yang, Anyi Rao Published: 2026-10-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.23751v1 Multi-turn image editing aims to modify an image according to a sequence of instructions, making it better aligned with human-AI collaborative creation than single-turn editing. However, constructing high-quality multi-turn training data remains challenging, as conventional sequential rollout accumulates errors and introduces visual-quality drift across editing turns. To address this challenge, we introduce MTEdit, a multi-turn image editing dataset built through a pipeline centered on packed trajectory canvas (PTC) generation. By jointly generating multiple editing states within a unified visual context, this pipeline reduces visual-quality drift across turns. Covering both step-wise and context-aware editing scenarios, MTEdit comprises 500K multi-turn image editing trajectories, with up to 8 turns and an average of 5.38 turns per trajectory, making it one of the most extensive datasets for multi-turn image editing. We further introduce MTEdit-Bench, a benchmark designed to evaluate both scenarios by assessing models' ability to follow editing instructions, maintain content consistency, resist visual-quality drift, and effectively use historical context across turns. Using MTEdit, we fine-tune Qwen-Image-Edit-Causal to obtain Qwen-Image-MTEdit. On MTEdit-Bench, we evaluate a broad range of closed-source and open-source image editing models, including Qwen-Image-MTEdit. Experimental results show that Qwen-Image-MTEdit achieves the best performance among the evaluated open-source models, demonstrating the effectiveness of MTEdit in improving models' multi-turn image editing capabilities. --- ### Exact Tail Laws for Nonlinear SGD with Infinite-Variance Gradients Authors: Xiaoli Li, Qianqian Lei, Ziyang Wei, Wei Biao Wu Published: 2026-10-16 Categories: math.ST, stat.ML arXiv: https://arxiv.org/abs/2610.23750v1 With infinite-variance gradient noise, SGD can have infinite expected excess objective even when most iterates are close to the optimum. We characterize its accuracy through exact first-order tail probabilities for the last iterate of nonlinear, constant-stepsize SGD. For regularly varying innovations of index $t\in(1,2)$, the leading measure transports one large gradient shock through the local Hessian flow. This is the same measure that governs the central stable Ornstein--Uhlenbeck limit; we prove its relative accuracy at shrinking tolerances above the central scale, with state-dependent noise and a growing observation horizon. The admissible window is nonempty for every available gradient moment $p>1$. The main technical step is a moment bound at the central fluctuation scale and a lower-moment control of the nonlinear error. The result yields explicit projection and excess-objective tails, extreme quantiles, and a factor $b^{1-t}$ for fixed batch size $b$. For affine population gradients, a sharper comparison gives the same law at fixed tolerances, including random sample Hessians. Coupled simulations in dimensions one to one hundred examine relative calibration, objective quantiles, batch effects, and the error due to random curvature. --- ### Beyond Multi-Stage Pipelines: A Label-Correlation Ensemble for Multi-Label Retinal Fundus Disease Classification Authors: Md Asif Uddin, Jannatul Ferdous, Asif Islam, Zobaer Mahmud Zisan, Promit Ghosh, Shah Ahafik Arman, Niloy Farhan, Rafeed Rahman Published: 2026-10-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.23747v1 Retinal fundus images frequently carry more than one disease, and public fundus datasets are heterogeneous and severely long-tailed. Clinical triage suggests a staged design, in which a screening gate, a disease-group router and group-specific classifiers operate in sequence, but it is unclear whether this hierarchy earns its complexity. We present a controlled comparison of three architectures on a unified 39-target label space built from RFMiD 1.0, RFMiD 2.0 and ODIR-5K (12,652 images): (i) a three-stage gated cascade of eight models, (ii) a flat model with 39 independent sigmoid outputs, and (iii) a label-correlation model that replaces the flat linear head with 39 learned label queries and a two-layer transformer decoder. All three share one Swin-V2-B backbone, one preprocessing pipeline and one training protocol, so differences are attributable to the architecture. Staging offers no consistent advantage: tracing every missed disease instance to the stage that lost it shows that the two coarse gates discard 34.2% of true instances while the fine-grained classifiers lose only 6.7%, and the gates' hard zeros depress the cascade's macro-AUC to 0.747. Label-correlation modeling gives the largest single gain, raising the detection rate from 0.621 to 0.682 (0.689 with test-time augmentation). Blending the flat and label-correlation models under four-view test-time augmentation is the best configuration on six of eight metrics (exact match 0.694, micro-F1 0.678, macro-F1 0.456, macro-AUC 0.972). On definition-matched class subsets it matches or exceeds four recent studies on macro- and micro-F1, most clearly on low-support pathologies. We also show that ensembling a gated cascade with continuous-output models is harmful, and that per-source negative sampling is needed to remove a dataset shortcut that otherwise yields a spurious AUC of 1.000. --- ### VocalGrad: Evaluating Acoustic Perception in Audio Language Models Authors: Koki Ryu, Hitomi Yanaka Published: 2026-10-16 Categories: cs.SD, cs.CL arXiv: https://arxiv.org/abs/2610.23745v1 Recent large audio language models (LALMs) have extended their capabilities beyond lexical speech understanding to tasks requiring paralinguistic and non-linguistic audio understanding, such as emotion recognition. However, these models still struggle to reliably utilize acoustic information, particularly when it co-occurs with spoken linguistic content. Existing benchmarks do not clearly distinguish acoustic perception from higher-level reasoning, making it difficult to identify the source of these failures. To address this issue, we introduce VocalGrad, a benchmark designed to evaluate LALMs' ability to perceive low-level acoustic variations. VocalGrad formulates this problem as a simple binary classification of temporal change direction, enabling evaluation largely independent of higher-level reasoning or semantic understanding. Our benchmark results reveal a substantial gap in acoustic perception between human annotators and state-of-the-art LALMs: while human annotators achieve high accuracy, LALMs perform at near-chance levels. We further conduct linear probing to identify structural bottlenecks in these models. Our analysis reveals two distinct failure modes: for some categories, task-relevant information is preserved in internal representations but not utilized by the language model head; for others, the information becomes progressively less linearly decodable across model layers. Overall, our results reveal substantial limitations of LALMs in modeling acoustic variation under controlled settings and expose representation differences not observable from text outputs. --- ### The Italian lawmaking process: a unified and structured dataset Authors: Matilde Contestabile, Chiara Ferrara, Giovanni Parrillo, Lorenzo Emer, Andrea Vandin Published: 2026-10-16 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.23741v1 The Italian legislative process is documented in detailed parliamentary records hosted in institutional websites. However, much of this information is available only as unstructured text, limiting its systematic reuse. We applied a controlled, systematic LLM-based extraction procedure, validated against manually annotated records, to convert these texts into ordered and dated events including, e.g., bill introduction, committee examination, plenary examination, and approval. The resulting dataset reconstructs the procedural histories of all 5346 Italian laws enacted between 1985 and 2026, spanning parliamentary terms IX to XIX, for overall 101413 events. Each event records the activity, date, and chamber, with additional procedural details where available. The dataset supports research in the emerging fields of computational legal and legislative studies, potentially combined with process-oriented data science methods to examine procedural paths and legislative timing across parliamentary terms. --- ### LagNet: Lag-Structured Operators for Long-Term Time Series Forecasting Authors: Zhenan Yu, Guangxin Jiang, Jiuyun Jiang, Jin Yang Published: 2026-10-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.23735v1 Long-term time series forecasting maps a finite history window to an extended future horizon. Many existing models focus primarily on the design of input representations and model structures, while paying less attention to the structural form of the history-to-future forecasting operator itself. We examine this operator directly and find that, across model families, sensitivity matrices exhibit recurring diagonal patterns whose diagonals correspond to relative temporal lags. Motivated by this observation, we develop a framework for direct multi-step forecasting based on lag-structured temporal operators. Its basic building block, LagLayer, constructs a Toeplitz matrix by tying history-to-future connections with the same relative lag and incorporates horizon-wise and history-wise scaling coefficients to relax exact sharing. This design enables LagLayer to serve as an effective replacement for temporal linear layers in existing forecasting models. Stacking LagLayer modules with activations and multiple feature maps yields LagNet. Experiments on long-term time series forecasting benchmarks show that our method is competitive with strong baselines, while sensitivity matrix diagnostics and limited-data experiments demonstrate that LagLayer provides an effective and sample-efficient alternative to a linear layer. --- ### Bridging the Language Gap in Scholarly Data II: Enhancing Gender Inference for Chinese Names Authors: Lisette Espín-Noboa, Mingrong She, Ana Maria Jaramillo, Liuhuaying Yang Published: 2026-10-16 Categories: cs.CL, cs.CY, cs.LG, cs.SI, physics.soc-ph arXiv: https://arxiv.org/abs/2610.23734v1 Perceived gender inference from names is important for inclusive scientometrics research, yet existing methods perform poorly on non-Western scholars. We address this gap for Chinese names, which appear in two forms, Hanzi and Pinyin, its Romanized form (e.g., Zhang Wei, Li Na). In international bibliographic records, names are often available only in Pinyin. However, a single pinyin name can correspond to multiple distinct hanzi characters with different gender associations, so gender inference from Pinyin alone is intrinsically ambiguous. To address this, we first develop two hanzi models, a regression model that produces a continuous gender score from 0 (male) to 1 (female), and a classification model that outputs one of three labels (\em{male}, \em{neutral}, \em{female}). We train them on a sample of hanzi names from Chinese-language physics publications, rated by 11 native Chinese speakers. On this sample, the models achieve an RMSE of $0.09$ and an R$^2$ of $0.85$ (regression), and macro-AUC of $0.97$ and a Cohen's $κ$ of $0.81$ (classification), demonstrating high performance that is robust to class imbalance. For pinyin names, we propose a pipeline that aggregates hanzi predictions via transliteration and frequency weighting, together with an ambiguity score that flags names whose gender cannot be resolved from Pinyin alone. Benchmarked against three off-the-shelf tools (Namsor, GPT, and Claude), our models achieve the highest agreement with human annotations for both gender scores and gender labels, in both scripts. Applied to an independent sample of Chinese-named authors in APS journals, our models assign a gender to every name, whereas existing Pinyin-based methods leave between 20\% and 100\% of names unclassified. These findings demonstrate the importance of hanzi-level information for reliable gender inference of Chinese names. Code and data are publicly available. --- ### Synthetic Image Oversampling for Rare-Class Representation Learning in Deep Facial Phenotyping Authors: Miles Liao, Zhanliang Wang, Hongzhuo Chen, Kai Wang Published: 2026-10-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.23730v1 Recent deep facial phenotyping methods can support the recognition of genetic syndromes, but patient images are often scarce and unevenly distributed across disorders. Synthetic facial images offer a way to supplement the training data without collecting additional patient photographs. Their usefulness, however, depends on whether they improve recognition of real patients: generated images may introduce artifacts or repeat features already represented in the training set. It is therefore necessary to examine both how much synthetic augmentation to use and which disorders benefit. We investigate disease-specific synthetic oversampling using images from the Phenotypic Disease Image Database to augment a subset of the GestaltMatcher Database. We compare increasing augmentation levels in an image-based model, GestaltMatcher-Arc, and a multimodal model, GestaltMML, while keeping the real training and patient-disjoint evaluation partitions fixed. Repeated training runs assess overall and disease-specific accuracy, and an exploratory embedding analysis examines changes in class compactness and separation. Augmentation improves mean recognition accuracy in both training setups, although gains remain modest in GestaltMatcher-Arc and continue across the tested levels in GestaltMML. These aggregate improvements are accompanied by uneven disease-level responses, including reduced accuracy for some disorders. In the embedding analysis, disorders with fewer real training images tend to gain more class separation, but geometric changes do not consistently track classification performance. Together, the findings support synthetic oversampling for limited-data facial phenotyping and emphasize the need to assess its amount and benefit for individual disorders within each training setup. --- ### Escaping Parameter Space: Tight Generalization Bounds via Representation Quality Authors: Niclas Göring, Shuofeng Zhang, Branton DeMoss, Ard A. Louis Published: 2026-10-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.23729v1 We derive a tight generalization bound for deterministic neural We derive a tight generalization bound for deterministic neural networks based on their last hidden layer representations. By evaluating representation quality with a parameter-free $k$-nearest-neighbor ($k$-NN) classifier, our certificate avoids traditional parameter-space complexity measures, KL divergences to a posterior, weight norms, and compression. The bound is tight: trained from scratch, it reaches an 8.0 percentage point gap to test error on CIFAR-10 (ResNet-18) and yields the first non-vacuous certificates we are aware of on CIFAR-100; with frozen DINOv2 representations, it certifies at 1.4\% on CIFAR-10 and 23.1\% on 1,000-class ImageNet. It decomposes additively into three empirical, independently measurable quantities: local class geometry ($k$-NN decoder error), decoder-network agreement, and training stability. This allows the bound to act as a diagnostic tool: we demonstrate that actively destroying local class geometry eliminates generalization while leaving dataset memorization intact, identifying class geometry as a causally relevant mechanism for generalization. Finally, we show that learned representations are significantly less sensitive to weight noise than linear readouts, suggesting why parameter-space certificates often struggle to remain tight. --- ### ECG-SDI: Single-lead Electrocardiogram Enables Continuous Sleep Depth Index Profiling and Scalable Digital Biomarkers for Sleep Health Authors: Donglin Xie, Qingshuo Zhao, Songchi Zhou, Haoyu Wang, Jingyu Wang, Yuxi Zhou, Thomas Penzel, Shenda Hong Published: 2026-10-16 Categories: eess.SP, cs.LG arXiv: https://arxiv.org/abs/2610.23727v1 Conventional sleep staging provides a coarse-grained representation that obscures within-stage depth variation. We developed ECG-SDI, a single-lead electrocardiography (ECG) framework for continuous sleep-depth profiling and digital biomarker extraction. Using 12,392 overnight polysomnographic recordings, we trained and validated a two-stage deep learning model supervised by conventional sleep-stage labels. Correlations with ordered stages excluding rapid eye movement (REM) sleep were 0.828 in the pooled internal test set and 0.848 in the external Cleveland Family Study; corresponding REM classification AUROCs were 0.954 and 0.977. Overnight trajectories captured within-stage variation. Biomarker-based phenotyping identified a disturbed subtype associated with poorer subjective sleep quality and higher all-cause mortality in the Sleep Heart Health Study (adjusted hazard ratio, 1.20; 95% CI, 1.05-1.38). Among 507 participants with paired recordings before and after continuous positive airway pressure (CPAP), normalized sleep-depth area increased by 6.1% and shallow-sleep burden below 0.3 decreased by 16.0%. Exploratory analyses linked reductions in approximate entropy and depth variability to reduced oxygen desaturation and increased sleep efficiency, respectively (Spearman rho = 0.24 and 0.12); both associations remained positive after covariate adjustment. Mean ECG-SDI within N2 increased by 0.017 (95% CI, 0.004-0.030). A wearable proof-of-concept illustrated the acquisition-to-report workflow. These findings support ECG-based sleep phenotyping and further evaluation of CPAP response monitoring at home. --- ### Beyond Large Language Models: A Mental World Model Framework for Mental Modeling, Simulation, Evolution, and Interpretability Authors: Qingshi Wang Published: 2026-10-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.23722v1 Understanding and simulating how subjective cognition and mental states emerge, evolve, and shape behavior is essential for advancing artificial intelligence toward deeper social cognition and general intelligence. Existing large language models (LLMs) and Theory of Mind (ToM) methods primarily infer mental states from linguistic information, lacking unified mechanisms for subjective world construction, cognitive-psychological interactions, dynamic evolution, and historical dependencies. This paper introduces the Mental World Model (MWM) and its implementation, the Multi-Branch Mental Evolution Architecture (MMEA), which explicitly constructs subjective worlds, models interactions between cognition and mental states, and simulates continuous mental evolution shaped by historical experiences. On DynToM and RecToM, MMEA achieves 96.48% and 94.00% accuracy, respectively, outperforming leading LLMs and specialized ToM methods. Additional experiments demonstrate improvements of 28.7, 39.3, and 16.6 percentage points in mental state and behavior prediction, long-sequence prediction, and implicit mental state inference, respectively. The results demonstrate that MMEA provides an interpretable framework for continuous mental modeling, enabling AI to move beyond surface-level semantic representations to infer individuals' underlying mental states from linguistic information and dynamically simulate their internal cognitive processes and evolution over time. MWM also provides a promising foundation for causal reasoning, personalized AI, sustained human-AI interaction, and future advances toward artificial general intelligence (AGI). --- ### Recognizing Study Lineage Is Not Enough: Over-Crediting Same-Trial Evidence in LLM-Based Medical Verification Authors: Mukand Krishna, Anoushka Harit, Chenghao Xiao, Zhongtian Sun Published: 2026-10-16 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.23721v1 Publication count is not study count. A model can identify shared trial lineage correctly in a direct task yet over-credit a second publication from the same trial when aggregating evidence. We evaluate this behavior in medical LLM verification using 14 source-audited clinical families and five model conditions. The families span provenance, clinical applicability, result direction, and composition; the provenance families provide the direct lineage tests. Recognition and aggregation are separate stateless calls, and repeated calls assess within-input stability. Across all three original provenance families, GPT-5.5 identifies the independent update in 10/10 recognition calls per family but over-credits the same-trial report in 5/5 separate aggregation calls per family. Selected Qwen3-4B and Ministral-3-8B conditions show the same cross-task contrast. A study-grouping instruction reduces GPT-5.5 over-credit from 4/5 to 0/5 in each later pure-provenance family. Other model conditions show mixed behavior, and rejected outputs limit several comparisons. The results identify a behavioral gap between elicited lineage recognition and evidence aggregation. The code and data artifacts are available at https://anonymous.4open.science/r/study-lineage-review-artifact. --- ### Neural Expansion: A Unified Mechanism for How Deep Neural Networks Generalize Authors: Chashi Mahiul Islam, Samuel Jacob Chacko, Mao Nishino, Canlin Zhang, Xiuwen Liu Published: 2026-10-16 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.23716v1 Deep neural networks demonstrate remarkable generalization despite being highly over-parameterized, challenging traditional statistical learning theories. While several theoretical paradigms such as margin-based bounds, PAC-Bayesian analyses, and neural tangent kernels provide global explanations, they often lack mechanistic insight into how generalization emerges from training dynamics. We introduce Neural Expansion, a unified geometric framework that characterizes generalization through the expansion of directionally-selective ray coverage in the input space. Using Generalization Intervals (GIs), we quantify direction-specific regions around training samples where the model's predictions remain stable. Our extensive empirical studies across diverse architectures and datasets reveal that training leads to progressive expansion of ray coverage, particularly along directions with low Jacobian singular values. This mechanism helps explain a large fraction of correctly classified test inputs, adversarial examples, and even mislabeled or out-of-distribution samples through the geometry of ray coverage rather than instance-level memorization. By connecting input-space curvature to predictive behavior, our framework provides a mechanistic foundation that complements existing global theories of deep learning. --- ### The Cognitive Cost of LLM Writing: A Reading-Time Comparison with Human Text Authors: Kamer Cekini, Elisabetta Biondi, Chiara Boldrini, Andrea Passarella, Marco Conti Published: 2026-10-16 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.23715v1 Although linguistic differences between human-written and Large Language Model (LLM)-generated texts have been extensively studied, their implications for the cognitive effort involved in reading remain less explored. In psycholinguistics, reading time is commonly used as an indirect measure of cognitive processing effort. Building on this perspective, we investigate whether human-written texts and their LLM-generated rewrites exhibit differences in predicted reading time that may reflect differences in processing demands for readers. To this end, we introduce RoBERTa-RT, a model trained on human eye-tracking data to predict word-level reading times. We evaluate the model on both internal and external test sets, construct a paired dataset of 496 human-written articles and their LLM-generated rewrites, and apply RoBERTa-RT to compare their predicted reading times. Our findings show that LLM-generated rewrites tend to be shorter and have slightly lower predicted total reading times, while exhibiting higher predicted reading times per word. These differences are associated with systematic linguistic changes, including longer and less frequent words, greater lexical diversity, and higher contextual predictability. From a cognitive perspective, our findings suggest that LLM-generated writing may redistribute reading demands: reducing the amount of text to process while increasing the predicted processing effort associated with individual words. This highlights the importance of considering not only the linguistic characteristics of machine-generated content, but also its potential implications for human cognitive processing. --- ### GLOBE: Evolving Structured Agentic Memory for E-commerce Product Optimization in Generative Search Authors: Hyunseo Kim, Suil Choe, Sukkyoung So, Daeyeon Yi Published: 2026-10-16 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2610.23709v1 Optimizing product listings for generative search requires language agents not only to rewrite effectively but also to continually self-improve by retaining successful strategies across diverse categories. However, existing approaches often treat structured listings as free-form text, leaving effective strategies implicit in prompts, search trajectories, or rewritten outputs rather than accumulating them as a reusable agentic memory. To address this limitation, we introduce GLOBE, an agentic framework that drives continual self-improvement by storing optimization knowledge in an evolving handbook of explicit, field-scoped behaviors. In each episode, an Editor applies relevant behaviors and receives rank-based feedback, which a Reflector converts into behavior updates. Crucially for dependable execution in real-world settings, a Moderator removes redundant proposals, a Curator commits accepted changes, and consistently harmful behaviors are deactivated. This cycle transforms episodic feedback into a persistent, field-scoped optimization memory. Experiments show that structured behaviors outperform monolithic prompt optimization, while feedback-driven evolution and moderation further improve effectiveness and reduce downside risk. The learned behaviors also remain effective on unseen product categories, suggesting that agentic memory evolution supports interpretable and transferable product optimization. --- ### Tool Recommendation for Multi-Step Agents: Finding Every Tool a Task Needs Authors: Sam Partee, River Stevens, Thierry Damiba, Valerie Fanelle Published: 2026-10-16 Categories: cs.LG, cs.IR arXiv: https://arxiv.org/abs/2610.23707v1 A multi-step agent task fails when a single tool it needs is missing, yet the tools an agent may need are too many to list: the roughly 8,200 tools on the platform we study have definitions that together exceed the context window of any model we evaluate. We present Tool Recommendation, a deployed system that gives an agent all of them, hundreds of times more than a typical MCP server exposes, through a fixed interface of three tools. It runs at the gateway between agent and tools, executing every call under the end user's own credentials and checking it against the user's consent for each service and the tools the agent may use. We evaluate it on both a public retrieval benchmark and billed end-to-end session cost. On ToolRet, Tool Recommendation places every tool a query needs in the top ten 57% more often than BM25, a lexical ranking that commercial tool search offers, and compares favorably with published systems up to nine times its size. In paired multi-step workflows, its first recommendation covered every required tool in 93% of Codex sessions, and against a fixed list of 100 tools it cut input tokens by 17% with Codex and 40% with Claude Code and the total bill in all 14 runs, by up to 40%, with no change in task completion. --- ### FedRAPP: Federated Test-Time Prompt Tuning for Vision-Language Models with Reliability-Aware Prompt Personalization Authors: Syed Md. Ahnaf Hasan, Md Akil Raihan Iftee, Sajib Mistry, Amin Ahsan Ali, AKM Mahbubur Rahman Published: 2026-10-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.23705v1 Federated prompt learning enables vision-language models like CLIP to collaboratively adapt lightweight soft prompts across distributed clients without sharing raw data. However, existing federated prompt learning methods are designed primarily for supervised settings with labeled client data and assumed relatively stable training distributions. At test time, source-free federated prompt tuning remains largely unexplored. Clients may receive unlabeled target samples with heterogeneous, often non-IID distributions that differ substantially across clients and from the source training distribution, causing locally adapted prompts to drift in different directions and reducing the effectiveness of federated aggregation. In this work, we explore Source-Free Federated Test-Time Prompt Tuning (SF-FTTPT), where distributed clients collaboratively adapt soft prompts on unlabeled test streams without access to source data. Our study reveals that conventional federated aggregation methods struggle under heterogeneous client distributions, as locally adapted prompts become increasingly specialized and difficult to combine effectively. To address this challenge, we propose FedRAPP, a personalized aggregation framework that combines reliability-aware client assessment, server-side exponential moving-average prompt memory, and similarity-guided peer aggregation. FedRAPP selectively incorporates information from reliable and compatible clients while preserving local specialization, enabling more robust adaptation under distribution shift. Extensive experiments across nine CLIP benchmark datasets and ImageNet variants demonstrate that FedRAPP consistently outperforms standard federated aggregation baselines under heterogeneous client distributions while maintaining the efficiency advantages of prompt-only adaptation. ---