跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

覆盖计算机全学科，以 AI 为快捷入口。关注方向、作者和关键词，把发现变成持续的研究积累。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+367新增论文
+288其中 AI 相关
+33已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-09 10:18 · 全站最近入库：2026-11-09 10:17各信源进度 →

统计口径与数据新鲜度

统计 2026-11-08 11:15 — 2026-11-09 11:15（北京时间） · 点击数字查看对应简报；AI 相关包含在新增论文内。

最近完成检查：2026-11-09 10:18最近发现新增版本：2026-11-09 10:17库内论文最新更新时间：2026-11-06 12:44

每分钟刷新已保存的数据。空检查不代表采集异常；新收录可能包含历史论文。AI 导读按新增版本计数。

17,467 已收录论文14,949 AI 相关4,222 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

时间范围跟随排序：版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常，查看状态 →

找到 17,467 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-09 10:16（北京时间）
新论文 · v1arXiv:2610.37880

Interpretable neural equation learning for high-dimensional materials data

Philip Jacobson, Prasad Iyer, Remi Dingreville, Saaketh Desai

原文摘要

Equation learning seeks to discover compact, interpretable equations from data using various machine-learning techniques. However, few workflows discover and interpret learned equations in sparse, high-dimensional materials datasets. We present nn-EQL, an equation-learning framework that generates candidate equations through iterative training, pruning, and retraining of a neural network with customizable, user-specified neuron-level activation functions. Candidate equations are ranked using a minimum description length (MDL)-inspired score, balancing error and sparsity, and diagnosed to assess term-wise contributions, input-scaled sensitivities, and uncertainties. We demonstrate nn-EQL on standard AI-Feynman benchmarks as well as multiscale high-dimensional materials datasets such as finite-element simulations of heterogeneous materials, and high-throughput experimental thin-film deposition data. nn-EQL integrates with tabular data and high-dimensional data via standard encoder models, learning equations and providing insight into learned terms. Looking forward, integrating physically interpretable representations, multimodal and multi-fidelity data, and adaptive data acquisition could enable equation learning to formulate and test mechanistic hypotheses.

cs.LG · cond-mat.mtrl-sci

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37875

Verification Learning Theory: A Process Model of Checking and Retention in AI-Assisted Judgment

Christoph Trattner

原文摘要

Accurate AI assistance can improve immediate judgments while reducing opportunities to practise the operations needed for independent performance. Verification Learning Theory (VLT) formalises this possibility for claim-evaluation practice followed by correct, independent, rule-specific feedback. The model links perceived assistant reliability to evidence checking and links the history of those checks to retained rule use. Its strict form assumes that task demands and perceived reliability influence learning only through checking, with equal learning per genuine check. It therefore predicts that perceived fallibility can improve delayed unaided judgment even without observed assistant errors, and that this advantage disappears when checking is already required and performed. Rule-specific gains and forecasts from checking histories provide further tests. Simulations examine the consequences and parameter dependence of these commitments; they do not constitute empirical validation. Comparisons with depth-of-processing and feedback-encoding accounts identify where predictions diverge and where the accounts remain observationally equivalent. The framework specifies experiments that can test the proposed mechanism and separates retention of practised rules from the broader problem of recognising which rule applies to a new claim.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37874

PairCLIP-SWA: Similarity-Guided Balancing and Stochastic Weight Averaging for Generalized Deepfake Image Detection with OpenCLIP

Md. Nakib, Sudipto Sarkar, A. J. A. Jubayer Talukder, Mohammad Ariful Haque

原文摘要

Deepfake detectors are almost always deployed as the single checkpoint that scored best on a validation split, yet the reliability of that choice is rarely measured. We measure it with PairCLIP-SWA, a single-backbone detector that adapts an OpenCLIP ViT-L/14 visual tower by progressive block unfreezing on a class-balanced corpus built by CLIP-similarity-guided one-to-one subsampling, and averages the fine-tuning trajectory in weight space. Trained in-domain on the IEEE SP Cup 2025 (DF-Wild-Cup) benchmark under the same protocol as the strongest published three-backbone ensemble, the weight-averaged detector reaches 97.04% accuracy, 98.64% AU-ROC and a 4.07% equal error rate, against 94.46%, 97.60% and 5.00%. Its training log shows why averaging matters: over the averaged epochs the non-averaged checkpoint swings across 5.34 points of validation accuracy while its validation loss more than doubles, whereas the average is never worse and is up to 5.99 points better. On an OpenForensics-derived benchmark the same instability becomes a misranking: the checkpoint that validation accuracy selects (98.43%) scores 88.85% on a disjoint 10,905-image test partition, rejecting 21.1% of genuine photographs, while the terminal average, ranked last on validation, scores 94.76%. A study of twenty-two in-house configurations on the identical DF-Wild-Cup split, including preprocessing ablations, shows that CLIP pre-training rather than ensembling drives accuracy, that secondary face cropping costs about 34 points, and that frequency-domain inputs transfer poorly. We recommend per-class selection criteria measured off the early-stopping split.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.27562

VidParse: Online Parsing of Egocentric Procedures Like a Pro

Anubhav Gupta, Archit Kambhamettu, Vatsal Agarwal, Pulkit Kumar, Abhinav Shrivastava

原文摘要

Translating continuous, noisy egocentric video streams into discrete, temporally ordered action steps is fraught with visual challenges. Heavy ego-motion, transient occlusions, and the high intra-class variability of unscripted human-object interactions cause standard frame-level online temporal models to struggle, often resulting in severe over-segmentation and structural collapse. To bridge the gap between unstable low-level perception and high-level procedural logic, we present VidParse, an online, training-free framework that treats activity understanding as a graph-constrained inference problem. Rather than relying on learned temporal filters, we dynamically identify semantic transitions using a temporal similarity matrix over manipulation-anchored features, which are extracted from frozen foundation models to prioritize foreground hand-object interactions. A beam search decoder then leverages an induced procedural task graph to explicitly enforce valid action transitions and prune impossible trajectories. By anchoring robust visual segments to hard procedural constraints, our approach preserves long-range state transitions and achieves up to a 10x improvement in complex multi-step parsing accuracy over strong online baselines, all without requiring a single gradient update.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37872

Set an Exploit to Catch an Exploit: Compiling Public Proofs of Concept into Threat Hunting Rules

Muhammad Shoaib, Alexander Suh, Joshua Andrew Tomiak, Wajih Ul Hassan

原文摘要

Public exploit code for a newly disclosed vulnerability usually appears before any published rule that detects its exploitation. Of the 45 CVEs we evaluate, 37 ever received a Sigma, Elastic or Splunk rule; in 33 the exploit came first, by a median of 22 days. Analysts still write every rule by hand. We present Encore, which compiles a public Python proof-of-concept exploit (PoC) into CVE-specific hunting rules over a web service's existing logs, without running it. Encore rests on the PoC Behavior Alignment Principle: a PoC performs the exploit, so its code already provides a rule's HTTP requests, payloads and host operations. That is hard to act on: a PoC is written against libraries and runs on the attacker's machine, while the target's web-server, proxy and host logs record only what arrived and what it did. Encore closes the gap with a map from library calls to the operations they cause, built once per library, keeping only the operations visible on the target. For 12 of the 45, Encore's rule states the exploit's own payload fragment or host operation, which is evidence of the exploit itself, and not of traffic to its endpoint. On matched controls it separates that exploit from the same request with a harmless value, and it raises no alerts across 27,081 legitimate and crawl requests. We never compile the exploit that produced the logs. Most are Splunk's public attack data, recorded by a third party. Without reading a single log, Encore's rules find 43 of the 45. Splunk's log-tested rules cover 30 of the 45, and Encore finds 28 of those, plus all 10 CVEs without an ESCU rule. Where Splunk's rules alert on 20 wrong CVE pairs, Encore's alert on only 2. Hunting can start as soon as a PoC is public, and rules can raise an alert when it provides a payload or host operation.

cs.CR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37871

ICALL-BENCH: Benchmarking LLM Interprocedural Reasoning in Binary Programs

Shenglong Yao, Zirui Liu, Xiangchi Yuan, Wenke Lee

原文摘要

Recent benchmarks show that LLMs achieve strong performance in both function-level binary understanding and end-to-end binary reverse engineering tasks, but whether LLMs can reason over interprocedural semantics in compiled binaries remains unclear. Function-level benchmarks offer limited visibility into cross-function relationships, while whole-program benchmarks typically evaluate final outcomes of tasks that may be solvable from local clues alone, making it difficult to disentangle interprocedural reasoning from exploration, tool use, execution, and retrieval. To address this limitation, we introduce ICALL-BENCH, a benchmark that directly evaluates whether LLMs and agents can understand and reason over interprocedural semantics in binary programs, using indirect-call target recovery as a measurable probe. ICALL-BENCH covers 50 complete real-world C/C++ programs spanning different complexity levels and multiple optimization configurations, with an average of 74,746 lines of code and 941 functions per program. We further introduce three analysis regimes spanning model-only reasoning, static tool-augmented agents, and Internet-enabled open-world agents to examine how intrinsic reasoning, active information acquisition, and external knowledge each contribute to interprocedural binary analysis. We evaluate five recent LLMs and their corresponding agents. Our results reveal a wide separation across current models and agents, with program-level verifiable success rates ranging from 23% to 81%. They also show that greater information access does not consistently lead to better results, with particularly limited gains on the hardest cases, where deeper interprocedural reasoning remains the primary bottleneck. Uneven performance across models and frequent verifiable failures even under an optimistic evaluation indicate that robust binary interprocedural reasoning remains an open challenge.

cs.SE · cs.CR

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2512.02436

Agentic AI for Clustering and Relationship Discovery in Prediction Markets

Agostino Capponi, Alfio Gliozzo, Brian Zhu

原文摘要

Prediction market platforms list thousands of contracts whose logical and economic connections are implicit in their resolution rules. We introduce a hierarchical agentic reduction (HAR) pipeline for constructing inspectable cross-event relation graphs and a behavioral benchmark for evaluating their alignment with market prices. This partitions a catalog of prediction markets, specified by question and resolution text, into topic clusters, applies typed LLM reasoning to small batches, and proposes signed relations with rationales between specific markets. We evaluate semantic relation graphs spanning eight monthly Kalshi catalogs (February to September 2026). Using data from 30.3 million trades, we compute a benchmark that compares linked pairs' signed price-change correlations with those of matched, unlinked controls from the same topic cluster on identical timestamps. Under full-sample and leave-first-week-out evaluation, relations identified by our pipeline exhibit higher signed Pearson price-change correlations, with statistical significance, than matched within-topic controls. This increase also appears under Spearman correlation and becomes larger among relations labeled as medium or high strength. This benchmark provides a criterion for comparing relation-discovery methods against observations beyond their input text, and our results indicate the ability of agentic AI and LLM reasoning to identify meaningful relations between individual markets in connected Web marketplaces.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37870

Multi-Agent Reinforcement Learning for Global Climate Policy Cooperation

Anne Moll-Elsborg, Oskar Bohn Lassen, Francisco Camara Pereira

原文摘要

International climate policy requires coordination among countries whose mitigation decisions impose local costs but generate global benefits. Classical game-theoretic and integrated assessment approaches can study these incentives, but typically rely on prescribed behavioural assumptions or equilibrium concepts. Recent work has therefore explored Multi-Agent Reinforcement Learning as a way to model climate-policy cooperation as an emergent outcome of repeated strategic interaction. We extend an existing MARL climate framework with a multi-stage negotiation mechanism in which agents propose agreements, accept or reject commitments, and face penalties for non-compliance. This allows us to study how agreement design affects learned mitigation behaviour, compliance, and climate outcomes. In an idealized setting with four homogeneous agents, we find that non-binding agreements do little to overcome free-riding, while moderate non-compliance penalties improve cooperation and reduce warming. However, excessively strong penalties discourage ambitious commitments, revealing a trade-off between enforcement and participation. We position the framework as a methodological contribution for testing agreement design rather than a predictive model of real negotiations.

cs.MA · cs.GT · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37869

Hardness of Coloring $2$-Colorable $3$-Uniform Hypergraphs with $\log^{Ω(1)} n$ Colors

Amey Bhangale, Krishna Priya KM, Simon Rubin-Toles

原文摘要

We show that it is quasi-NP-hard to color a $2$-colorable $3$-uniform hypergraph on $n$ vertices using $O((\log n)^{1/8})$ colors. This exponentially improves the result of Dinur, Regev, and Smyth [Combinatorica'2005], which showed it is quasi-NP-hard to color a $2$-colorable $3$-uniform hypergraph on $n$ vertices using $O((\log \log n)^{1/3})$ colors.

cs.CC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37868

Human-Residual Steering: Aligning Frozen LLM Judges with Human Judgment Distributions

Chen Lyu, Phong Do, Gabriele Pergola

原文摘要

Large language models (LLMs) are widely used as automated judges, yet most alignment methods target aggregated human judgments and overlook variation among individual annotators. Existing approaches to matching the full distribution of human ratings mainly rely on output-level calibration or parameter fine-tuning. We propose Human-Residual Steering (HRS), to our knowledge the first method to align frozen LLM judges with human judgment distributions through learned hidden-state interventions. An oracle analysis shows that low-rank corrections at a single layer remove most of the discrepancy between judge and human distributions. HRS learns to predict such corrections from the judge's hidden representation and rating logits, training on individual annotations with proper scoring rules for ordinal and nominal judgments and optimising through the frozen downstream layers. Across 14 benchmarks and four judges from three model families, HRS outperforms all evaluated frozen-weight baselines. With Qwen2.5-7B, it achieves the lowest Jensen-Shannon distance on 13 of 14 benchmarks, reducing the mean from 0.565 to 0.352 versus 0.377 for the strongest calibrator. HRS also raises mean Spearman correlation with aggregate human scores from 0.449 to 0.579, improves population-level estimation under limited annotation budgets, and trains about 88 times fewer parameters than distributional fine-tuning at a modest cost in alignment.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37867

What Constitutes Food Similarity? Visual Representations and Retrieval in Indian Cuisine

Saransh Kumar Gupta, Akshadha Sharma, Lipika Dey, Partha Pratim Das, Ramesh Jain

原文摘要

Food similarity underlies retrieval, recommendation, substitution, and other food computing tasks, yet food representations are typically evaluated by identity preservation. We ask what happens to food similarity beyond identity: how different visual representations organize foods into relational neighborhoods, what culinary relationships these neighborhoods reveal or obscure, and how consistently these structures emerge across representations. Indian cuisine provides a challenging setting in which visually similar foods may have different culinary identities, while foods within a culinary family can vary substantially in appearance. Using an expanded Khana dataset and seven pretrained visual representations spanning convolutional, transformer-based, self-supervised, and image-text aligned models, we evaluate image-to-image retrieval and image-to-dish neighborhoods, examining culinary-family structure, contrast cases, and cross-representation agreement. We also aggregate image representations to compare dish-level visual similarity across models and against recipe-derived similarity for the same dishes. Image-level neighborhoods vary substantially across representations, including similarities across culinary-family boundaries. At the dish level, aggregation reveals common visual structure despite local variation, but this structure corresponds less strongly with recipe-derived similarity. These findings show that recognition performance alone cannot characterize relational structure: food similarity depends on representation, modality, and abstraction level rather than being a fixed property of the food collection. Understanding these structures is therefore a prerequisite to combining multiple food information modalities into a coherent notion of similarity.

cs.AI · cs.CV · cs.IR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37866

Finite-Sample Optimal Conformal Prediction Sets under Covariate Shift

Zhongyang Li

原文摘要

We study conformal prediction under covariate shift with a known covariate density ratio, seeking prediction sets with minimum expected length under the target distribution. For every calibration sample size, we prove that the rule combining the inverse conditional-density score with randomized weighted conformal calibration minimizes this expected length among all rules valid over the full weighted-exchangeability class. We approximate the oracle using quantile and kernel histograms, including forest-weighted estimators, and select estimators and tuning parameters by resampling to estimate calibrated target length. On a bounded response domain, we bound excess length linearly in $L^1$ density error at fixed calibration size, without requiring a uniform positive lower bound on the true density. We also bound selection-pool and resampling errors. Under explicit growth conditions, the selected procedure approaches the same oracle while the calibration size remains fixed. Experiments on 36 known-density configurations and four public regression datasets compare coverage, prediction-set length, and runtime with existing methods. In targeted low-coverage and strong-shift comparisons, inverse-density selection yields shorter mean sets in most cases and lower mean runtime than the evaluated weighted baselines, with some differences in achieved coverage.

stat.ML · cs.LG · math.CO · math.PR · math.ST

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37865

Echo: Scaling Visual Reinforcement Learning with Off-policy Experience

Gagan Khandate

原文摘要

Scaling visual reinforcement learning (RL) with GPU-accelerated simulation is computationally expensive due to rendering and visual-policy inference costs. Consequently, two-stage teacher--student distillation is commonly used to train visual policies, but introduces an imitation gap. In this preliminary study, we introduce \echomethod{}, \textbf{a single-stage off-policy RL framework that scales experience collection without proportionally increasing visual computation}. Through \textbf{inverse distillation}, a state-based auxiliary policy imitates the evolving visual policy and collects inexpensive, unrendered experience. Echo leverages this experience for off-policy value learning, directly improving the visual policy through a shared privileged critic. We instantiate \echomethod{} with FastTD3 and evaluate it on three visual control tasks and two dexterous manipulation tasks in Genesis. Relative to \sdpgmethod{} under the evaluated configurations, Echo reduces time to reference returns by an average of \textbf{60\% across the three locomotion tasks} and \textbf{56\% across both hand tasks}, while improving peak mean returns by \textbf{62\% and 12\%}, respectively. Both hand tasks also achieve higher mean returns at matched simulator-transition budgets. These initial results suggest that scaling off-policy experience is a promising approach to efficient direct visual RL.

cs.RO · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2509.11311

Prompts to Proxies: Emulating Human Preferences via a Compact LLM Ensemble

Bingchen Wang, Zi-Yu Khoo, Jingtan Wang

原文摘要

Large language models are increasingly used as proxies for human subjects in social science research, yet external validity requires matching the response distributions of target human populations. We study population-level survey alignment: reconstructing aggregate survey responses from limited public survey data, without individual-level demographic profiles or model finetuning. We formalize this problem as preference reconstruction: rather than matching proxy agents to demographic profiles, we construct a functional basis of proxy agents and recover population preferences by weighted aggregation. We instantiate this idea via Prompts to Proxies ($\texttt{P2P}$), a two-stage inference-time system. Stage 1 uses structured attribute-based prompting with entropy-guided adaptive sampling to construct a diverse proxy pool spanning the latent preference space. Stage 2 employs L1-regularized regression to select a compact weighted ensemble matching observed target-population responses. Across 14 American Trends Panel waves, $\texttt{P2P}$ achieves an average test MSE of 0.014 at approximately 0.8 USD per survey, improving over prompting and demographic-conditioning baselines. On the World Values Survey, cross-locale transfer experiments show that basis expressiveness can outperform locale matching on average, while locale-specific generation helps on culturally divergent questions. A stress test against an SFT-aligned survey model shows competitive performance using less than 3\% of the training data. These results position preference reconstruction as a lightweight, externally verifiable alternative for survey-based population alignment. Code is available at https://github.com/bingchen-wang/P2P.

cs.AI · cs.CY

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.09802

SWE-Bench ProMax: Benchmarking Agents on Large-Scale Multilingual Code Refactoring

Yuling Shi, Jinghan Xu, Kelin Fu, Wenhao Zeng, Shilin He, Lei Zhang, Yue Liu, Zelin Zhao 等 15 位作者

原文摘要

As AI coding agents take on increasingly complex, long-horizon software engineering tasks, existing benchmarks are rapidly saturating and their evaluation quality has come under serious scrutiny: a recent audit found that nearly 60% of unsolved SWE-bench Verified instances contain flawed tests -- either overly narrow tests that reject correct solutions or overly broad tests that check unstated requirements -- and that frontier models can verbatim reproduce gold patches from training data. Code refactoring, which requires coordinated, behavior-preserving changes across many files, offers a substantially harder and more realistic test of agent capability, yet remains underserved by current benchmarks. We introduce SWE-Bench ProMax, an expert-curated, multilingual code refactoring benchmark of 170 instances drawn from real commits across seven programming languages (Python, Java, TypeScript, Go, C, C++, and Rust). Every instance undergoes rigorous, multi-stage curation that directly addresses the quality problems identified in prior benchmarks: issue descriptions are rewritten from scratch to provide precise, unambiguous specifications, and test suites are manually reviewed to remove overly narrow and overly broad tests. Tasks with insufficient complexity or limited cross-file scope are filtered out, yielding a benchmark of challenging, large-scale refactoring tasks that average 11.5 modified files and 261.6 lines of code per instance, substantially exceeding the scale of existing benchmarks. Experiments with frontier models under two agent scaffolds show that the best model achieves only 41.2% resolve rate, confirming that SWE-Bench ProMax presents a meaningful and unsaturated challenge for current AI coding agents. Our benchmark is available at https://huggingface.co/datasets/swe-bench-promax/SWE-Bench-ProMax.

cs.CL · cs.SE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37862

Improving Group Deliberation through AI-Guided Self-Reflection

Haiwen Li, Crystal Qian, Ben Usman, Stephanie Chan, Michiel Bakker, Srivignesh Rajendran, Avneesh Sud, Thomas Leung 等 12 位作者

原文摘要

As AI systems increasingly mediate human communication, identifying conditions under which they augment collective sense-making is a critical challenge. Through a randomized experiment (N=1,173 U.S. participants across 391 small-group deliberations), we investigate whether AI-guided self-reflection improves subsequent deliberative discourse. We show that engaging with a non-directive AI chatbot instructed to structure self-reflection prior to group deliberation yields significantly higher deliberation quality (measured by the Discourse Quality Index, DQI) compared to a baseline of no self-reflection (Cohen's d=0.31) and a condition of unassisted self-reflection (d=0.27), and the positive impact is most pronounced in groups with disagreement. This improvement may be driven by more sophisticated argument justifications, greater consensus-building effort, and increased respect for counterarguments. Furthermore, after self-reflection, participants in the AI condition reported higher empathy toward dissenting peers and a deeper understanding of opposing reasoning. Beyond observed behavior, our findings are empirically relevant to open debates between political philosophy and psychology surrounding self-reflection, demonstrating that interactive AI could transform solitary thinking into productive internal reflection. Together, these results demonstrate that even simple AI-based reflective scaffolds can foster more productive group dynamics, opening new avenues for leveraging AI to augment collective intelligence.

cs.HC · cs.CY

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37860

Effects of Deep Learning Architecture and Pretraining on Automated Vocal Fold Segmentation in Ex Vivo High-Speed Phonation Images

Varun Vinayak Kalaiarasan, Charles Farbos de Luzan, Khalid Malik, Ephraim Gutmark, Liran Oren

原文摘要

Two-dimensional (2D) intraglottal particle image velocimetry (PIV) of ex vivo phonation experiments quantifies vocal fold medial surface dynamics and the intraglottal flow field. However, it relies on manual segmentation because residual glare, low tissue-to-flow contrast, and tracer-particle speckle obscure the vocal fold boundaries. This study assessed how deep learning architecture and ImageNet pretraining affect automated vocal fold segmentation in these high-speed images. Four established architectures from three categories were benchmarked: the convolutional neural network (CNN)-based UNet and UNet++, the hybrid CNN-transformer-based TransUNet, and the pure transformer-based Swin-UNet, the latter two trained from scratch and from ImageNet-pretrained weights. Using 16,344 expert-annotated images from 227 phonation trials of excised canine larynges, the six pipelines were trained with five seeds under a standardized protocol and compared on 50 held-out test trials using trial-level Wilcoxon signed-rank tests with Holm correction. Mean Dice similarity coefficient (DSC) spanned only 0.9734 to 0.9764, so the pipelines differed mainly in boundary fidelity. Pretraining significantly improved the boundary F1 score (BF1) and 95th percentile Hausdorff distance (HD95) of the TransUNet and Swin-UNet, about four times more for the Swin-UNet. Once pretrained, the two performed similarly, although the Swin-UNet has only about a quarter of the trainable parameters. Without pretraining, the TransUNet had a significantly higher BF1 and a lower HD95 than both CNN-based pipelines and about half their share of images with HD95 > 50 pixels. To our knowledge, this is the first study to apply deep learning to vocal fold segmentation in 2D intraglottal PIV, and it offers a reference framework for segmenting experimental flow-visualization images with noisy optical conditions or highly deformable objects.

cs.CV · eess.IV · physics.flu-dyn

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37859

Seq@K: Evaluating Language Models Under Sequential Feedback

Thomson Yen, Gilbert Yang, Naimeng Ye, Minghui Chen, Dong Xia, Tianyi Shen, Yechan Jeon, Yaqin Chen 等 11 位作者

原文摘要

Language-model agents differ fundamentally from prior intelligent systems in their ability to learn from natural language in context. This capability enables agents to iteratively refine their answers in response to feedback, a prevalent mode of operation in modern agentic workflows. However, the community primarily ranks models by metrics such as Pass@1 or Pass@K, which cannot capture how they utilize feedback on prior attempts. We introduce Seq@K, a natural evaluation protocol that measures whether a model can solve a problem within K sequential attempts, provided feedback after each previous failure. Unlike multi-turn agentic benchmarks that examine long-horizon planning, Seq@K isolates and formalizes the core capability of refinement from feedback. We evaluate Seq@K on a suite of 7 benchmarks and 16 frontier models, and show that Seq@K reveals a materially different model-selection landscape: under Seq@K, (1) model rankings often differ, (2) the Pareto frontiers admit more efficient configurations and (3) the gains from choosing the optimal model configuration can widen or shrink relative to those of Pass@K. We further show that analyzing model trajectories under Seq@K helps characterize iterative refinement behavior, such as the rate at which models address issues raised in feedback, or how rigidly they hold onto their own answers. Finally, we study how the nature of feedback affects models' iterative refinement, showing that practitioners must carefully design and benchmark the feedback loops of iterative agentic systems. Together, these results establish how Seq@K offers a more faithful metric for intelligent systems that typically operate in such feedback loop, and the necessity to consider Seq@K in evaluating models for these systems.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.37852

Delta-Matching: Closing the Final Gap of Native 8-bit Training for LLMs

Haozhan Tang, Hao Kang, Han Cai, Song Han, Chenyan Xiong

原文摘要

Reliable FP8 attention remains a barrier to fully native 8-bit large language model training. We derive how forward-backward inconsistencies produce stale delta and empirically show how it distorts training dynamics. Our stale-delta hybrid runs show a modest loss gap at 569M parameters but substantial loss increases and downstream degradation at 1.67B and 5.29B. QK normalization, NoPE (no positional encoding), and lower-learning-rate context extension mitigate or delay degradation without eliminating it. This pattern suggests accumulated optimization error that smaller models and short runs can conceal. We propose Delta-Matching, proving that it restores the softmax gradient's zero-row-sum invariant under the stated numerical assumptions. It enables native block-scaled FP8 in every forward and backward attention-core matmul without architectural changes, smaller global batches, or auxiliary forward outputs. Across tested architectures, scales, and training stages, Delta-Matching matches BF16/FP32 mixed-precision training loss and overall downstream performance. We will release our implementation, trained models, and data recipes (https://jet-ai-projects.github.io/delta-matching).

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37851

Evaluating and improving AI agents for sequencing protocol understanding

Chi-Lam Poon, Michael Goneos, Zezheng Song, Xi Chen

原文摘要

Existing scientific-agent benchmarks rarely evaluate whether agents can reconstruct the exact molecular structures and generation workflows specified by sequencing protocols, a capability critical for analyzing customized sequencing assays. We introduce LibStructBench, a document-grounded benchmark for reconstructing sequencing-library structures and molecular workflows. Our experiments show that frontier agents often produce approximately correct reconstructions but remain unreliable at exact reconstruction, particularly in molecular-state representation and workflow connectivity. Switching the underlying language model produced larger average performance differences than switching agent harnesses, with a statistically significant difference only for molecular-state reconstruction. Additional knowledge improved oligo-family recovery in a small pilot without improving mean molecular-workflow scores. Autonomous accumulation of procedural rules and cross-protocol examples showed non-monotonic validation performance and no mean held-out molecular-workflow improvement in the tested trajectory. These findings highlight the need for more controlled and verifiable approaches to scientific reasoning about molecular processes in complex experimental protocols.

cs.AI · q-bio.GN

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.11087

Test-Time Gradient Guidance of Flow Policies in Reinforcement Learning

Zhiyuan Zhou, Andy Peng, Charles Xu, Qiyang Li, Jost Tobias Springenberg, Kevin Frans, Sergey Levine

原文摘要

Expressive continuous control policies, such as diffusion and flow models, form the backbone of recent advances in scaling imitation learning for simulated and real robot control. While they are known to scale stably in the supervised imitation learning setting, incorporating them into reinforcement learning (RL) pipelines for policy improvement has proven more difficult. It often requires specialized training objectives or backpropagating through denoising processes, which cause well-known issues with stability and affect scalability. In this paper we study the question of whether simple policy improvement schemes at test time alone, leaving stable supervised policy training intact, can be a competitive alternative which sidesteps these issues. To this end, we propose QGF (Q-Guided Flow), an RL algorithm that performs policy optimization entirely at test time. QGF works by pre-training both a reference flow policy (via a standard behavioral cloning objective) and a value function critic and, at test time, using the value gradient to guide the reference policy to generate higher-value actions without any additional policy learning. Empirically, QGF outperforms prior test-time RL methods on single-task and goal-conditioned offline RL benchmarks with high-dimensional action spaces, and is competitive with state-of-the-art training-time algorithms while being much cheaper to run. Moreover, it exhibits favorable scaling with model size by avoiding the instability of actor-critic training, offering a practical and effective alternative RL algorithm with expressive policies.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37849

Detecting Covert Collusion between AI Agents through Partner-Outsider Positive Listening

Kevin Yandoka Denamganaï

原文摘要

AI agents that share a secret convention can coordinate through messages that look innocent, so a monitor that reads only the messages can miss them. We propose a behavioural test: a partner that uses a code reacts to the exact wording of a message, whereas an uninvolved agent placed in its seat does not. Partner--Outsider Positive Listening (PoPLi) is the difference between the two agents in how much their action changes when the message is reworded with its meaning kept, and it is computed after the fact by replaying logged prompts. In a simulated market with five conditions (no collusion, a joint reward with neutral messages, the same with an openly stated intention, a covert first-letter code, and the code with a stated intention), PoPLi is between 0.48 and 0.59 whenever the code is present (95% intervals all above 0.29) and between -0.10 and -0.01 without it. Message-only monitors did not separate the conditions: one reading the speaker's messages answered "no" in all 50 markets, and one reading every seller's messages flagged 9 of 10 markets with no collusion. PoPLi detects the use of a private channel, not collusion as such, and it cannot detect collusion through incentives alone or codes carried by meaning.

cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.34662

StreamVibe: Proactive Video Agents for Evolving User Intent

Chengzhi Liu, Yuxiang Lai, Yuzhe Yang, Yanqing Liu, Jiheng Hou, Yue Cao, Haonan Wang, Ruixi Fan 等 16 位作者

原文摘要

Vision-language models are shifting from offline passive understanding toward online proactive interaction. However, prevailing methods largely rely on explicit requests while overlooking implicit user intents (e.g., "where should I click next?" when a user is navigating a website) and fail to continuously update their understanding as user intents evolve. These limitations make them less suitable for intent-aware interaction in real-world scenarios. To address these challenges, we introduce StreamVibe-Bench, a new benchmark that serves as a testbed for user intent understanding and interaction, comprising 4.1K evaluation samples and 85K training samples spanning explicit, implicit, and dynamic intents. Building on this benchmark, we develop StreamVibe-VL, a streaming proactive model that infers implicit user intents from continuous observations and dynamically adapts its interactions as these intents evolve. We further introduce StreamVibe-Harness, which maintains user intents as persistent states with flexible lifecycles through hierarchical memory, enabling it to track the latest user intents and environmental states. Our experiments reveal three key findings: (i) StreamVibe-VL preserves strong general video understanding capabilities while improving response timing and answer quality by 10.7% over existing baselines; (ii) existing proactive models remain limited in understanding user intents and determining when to respond, especially under implicit and dynamic intents; and (iii) StreamVibe-Harness further improves response consistency and adaptation during sustained interactions, resulting in a 12.3% gain in proactive interaction performance.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37845

An $Ω(T^{3/4})$ lower bound for projection-free online learning with linear minimization oracles

Julien Weibel, Pierre Gaillard, Wouter Koolen, Adrien Taylor

原文摘要

This work considers projection-free online learning algorithms with linear minimization oracles for handling the decision set. For Online Frank--Wolfe (OFW), regret upper bounds were already known for specific OFW tunings [Hazan and Kale, 2012, Hazan, 2016] which scaled as $T^{3/4}$ (where $T$ is the horizon length). However, it remained an open question whether the regret of all OFW tunings scaled as $T^{3/4}$. We answer that question, proving a universal worst-case regret lower bound $Ω(T^{3/4} m^{-1/4})$ for any projection-free algorithm that makes at most $m$ linear minimization oracle calls per round. The analysis suggests an extended OFW to resort to multiple linear optimizations per round, for which we prove a regret upper bound $O(\max \{ T^{3/4} m^{-1/4}, \sqrt{T} \})$.

stat.ML · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37844

Convex Potential Learning for Optimal Transport Between Medical Images

Hongyu Kan, Ivan Medri, Natasha Ironside, Kristofor Pas, Richard Corp, Shinjini Kundu, Gustavo Kunde Rohde

原文摘要

Computing optimal transport maps between medical images plays a fundamental role in morphological analysis. However, existing methods are either difficult to scale to large 3D medical images or rely on regularized formulations that provide only approximate transport maps. To improve the accuracy of downstream medical image analysis, we propose a novel approach for estimating optimal transport maps by parameterizing the convex potential function. By construction, the resulting transport map is guaranteed to be curl-free, consistent with Brenier's theorem. We evaluate the proposed method on both 2D and 3D medical imaging datasets. Experimental results demonstrate that our approach achieves lower transport estimation errors and produces higher-quality image reconstructions than existing methods.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37843

Where the Error Lives: Spectral Representations of Learned Kohn-Sham Hamiltonians

Fang Sun, Hekai Cheng, Ruoyan Li, Yuanzhou Chen, Wei Wang, Jason Cong, Yizhou Sun

原文摘要

Kohn-Sham density functional theory (DFT) is the standard method for computing the electronic structure of molecules and materials, but its self-consistent-field (SCF) iterations make it expensive for large systems and high-throughput screening. Machine-learned Hamiltonian models offer a shortcut: an equivariant network predicts the Kohn-Sham Hamiltonian matrix in one forward pass, and diagonalizing the prediction yields orbital energies, the HOMO-LUMO gap, molecular orbitals and the electron density. These models are trained to match the reference matrix entry by entry, yet a small entry-wise error does not guarantee accurate eigenvalues or eigenvectors. Two physics-informed alternatives go partway: a recently proposed wavefunction-alignment loss adds a spectral penalty without diagonalizing the prediction, and matching the electron density of the diagonalized prediction supervises it directly. Neither is complete: by representing the prediction error in the eigenbasis of the reference Hamiltonian, we show that each sees only part of the error, and that shifting the predicted orbital energies leaves the electron density exactly unchanged. The same analysis identifies a complete training signal: the cumulative local density of states (cumulative LDOS), the number of electrons at each point in space with energy below a given threshold. The cumulative LDOS is a single physical observable that contains the electron density as a special case, responds to every component of the error, determines the Hamiltonian uniquely, and yields gradients that do not vanish for large orbitalenergy errors. Fine-tuning three Hamiltonian networks on QH9 in this way, which we call FermiScope, reduces the HOMO-LUMO gap error without increasing the element-wise error. The gains carry over to out-of-distribution and molecular-dynamics splits, where the wavefunction-alignment loss helps less.

physics.chem-ph · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37842

Improving Data-Constrained Scaling with Hyperparameter Transfer and Ensembling

Ethan Baron, Shmuel Berman, Anirudh Satheesh, Akshay Vegesna, Samip Dahal, Andrew Gordon Wilson

原文摘要

As growing compute budgets outpace the growth of high-quality training data, large language models must be trained with both compute and data constraints in mind. Unfortunately, existing prescriptions for data-constrained scaling suffer from two important limitations. First, past works hold key hyperparameters such as weight decay fixed with scale, despite the fact that optimal hyperparameters vary wildly with model size and number of epochs. Second, past works neglect ensembling, a promising axis for scaling under data constraints. As a surprising consequence, prior prescriptions can lead to loss that increases with compute budget. We address both limitations by fitting power laws that prescribe how to transfer hyperparameters with scale and scaling laws that prescribe how to allocate compute with ensembling. Training on 100M tokens from FineWeb, our recipe reduces validation loss by over 0.15 nats compared to prior recipes, a 14% decrease in perplexity, and achieves monotonic improvements with compute through ensembling. These gains are achieved using prescriptions fit to smaller runs and validated at up to 12$\times$ larger compute budgets.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37838

TensorBound: Characterizing Tensor Binding Failures in AI Compiler and Runtime Stacks

Wen Li, Yongxi Sha, Baihong Chen

原文摘要

AI compiler and runtime stacks must preserve bindings between tensor values and their operations, storage, and execution state. These bindings can fail while the underlying objects remain present, with symptoms appearing in another layer. We present TensorBound, an empirical study of tensor binding failures in IREE and the XLA and PyTorch ecosystems. The study analyzes 264 reports and reconstructs 149 distinct repaired causes through source tracing and comparisons of pre-fix and repaired revisions. Each reconstruction connects the first invalid decision to its violated condition, physical effect, and repair. Missing eligibility checks, incorrect mappings or translations, and lost or omitted relations account for 69.1% of repaired causes. These patterns highlight the need to preserve binding facts and check the conditions for their use. The 101 first invalid decisions in compiler code identify candidate checking points before execution. Four archived IREE diagnostic attempts distinguish effect localization from source-based cause explanation. Together, these findings motivate transition-specific checks that preserve binding facts across representations and enforce the required conditions at consuming decisions.

cs.CR

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2506.23532

GViT: Representing Images as Gaussians for Visual Recognition

Jefferson Hernandez, Ruozhen He, Guha Balakrishnan, Alexander C. Berg, Vicente Ordonez

原文摘要

We introduce GViT, a supervised classification framework that uses patch-conditioned 2D Gaussian primitives as input tokens for ViT backbones. A ViT-S-sized encoder predicts each primitive's position, scale, orientation, color, and opacity in one forward pass. The same parameters are constrained to reconstruct the image through a differentiable renderer, as well as serve as classifier inputs. During training, classifier-gradient guidance shapes primitive geometry and appearance under an image reconstruction constraint. On ImageNet-1K, GViT-B achieves 76.9% top-1 accuracy, compared with 79.8% for ViT-B/16 trained with the same recipe. Gaussian tokens also provide explicit spatial support for explanation maps. Grad-CAM over Gaussians improves on patch-based Grad-CAM in segmentation and token-deletion probes, while other probe comparisons are comparable to a ViT. A covariance-based foreground diagnostic on the PASCAL VOC segmentation task further measures the geometry learned through supervised guidance. These results establish the feasibility of recognition from renderable Gaussian parameters and characterize how task supervision shapes this inspectable representation.

cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗