跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+979新增论文
+781其中 AI 相关
+119已有论文修订
+95新增 AI 导读

arXiv 最近完成扫描:2026-11-20 08:48 · 全站最近入库:2026-11-20 19:58各信源进度 →

统计口径与数据新鲜度

统计 2026-11-20 01:36 — 2026-11-21 01:36(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:2026-11-20 08:48最近发现新增版本:2026-11-20 19:58库内论文最新更新时间:2026-11-20 02:59

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。

28,961 已收录论文24,030 AI 相关8,912 有修订112 HF 社区发现

浏览论文库

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 21,358 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-20 08:46(北京时间)
新论文 · v1arXiv:2611.22274

GuardAgent: A Memory-Augmented Agentic Framework for Adaptive Detection of Adversarial Promotions in LLM-Based Recommendation

Shiyi Yang, Xinshu Li, Chen Wang, Xiwei Xu, Liming Zhu, Lina Yao

原文摘要

In traditional recommender systems (RSs), textual information typically serves as auxiliary signals for representation learning. In contrast, in LLM-based RSs, textual information becomes the primary medium for recommendation generation through semantic understanding and reasoning. This shift fundamentally changes the attack surface, making promotion-driven manipulations more feasible, effective, and harder to detect. However, effectively detecting such attacks remains largely unexplored. To fill this gap, we present the first systematic study on detecting promotion-driven attacks against LLM-based RSs, aiming to safeguard next-generation recommendation platforms. Specifically, we propose GuardAgent, a novel LLM-powered agentic detection framework that operates through a loop of Perception, Action, Reflection and Memory. In contrast to conventional LLM-based detectors that function in a static, one-off, and opaque fashion, GuardAgent continually learns and self-evolves to adapt to unseen threat patterns while generating explainable reasoning traces and outcomes. Extensive experiments on real-world datasets demonstrate that GuardAgent achieves state-of-the-art generalization performance, laying the foundation for robust and trustworthy recommendation in practical settings.

cs.IR · cs.CR

版本更新 · v3arXiv:2508.03162

An open dataset of gas adsorption in deformable metal-organic frameworks for direct air capture

Anuroop Sriram, Logan M. Brabson, Xiaohan Yu, Sihoon Choi, Kareem Abdelmaqsoud, Elias Moubarak, Pim de Haan, Sindy Löwe 等 16 位作者

原文摘要

Engineering economical and scalable processes for direct air capture (DAC) from humid air relies on atomistic modeling to search and identify promising sorbent materials from a vast chemical space. Machine learning has emerged as a powerful tool for predicting material properties in an efficient yet accurate manner, but these models require large sets of carefully curated training data. We present the Open DAC 2025 (ODAC25) dataset comprising nearly 60 million DFT single-point calculations for CO2, H2O, N2, and O2 adsorption in ~15,000 MOFs. ODAC25 introduces functionalized MOFs, high-energy adsorbate placements, and synthetically generated frameworks to maximize the versatility of models trained on the dataset. ODAC25 improves upon the accuracy of DFT calculations in previous works and applies engineering intuition from recent work regarding the treatment of adsorbate-induced MOF flexibility. We release state-of-the-art machine-learned interatomic potentials trained on ODAC25 and demonstrate their utility via Henry's coefficient predictions. ODAC25 enables MOF screening for DAC at a resolution previously unattainable.

cond-mat.mtrl-sci · cs.LG · physics.chem-ph

新论文 · v1arXiv:2611.22273

SARVIA: Fast-Adapting the Strong SAR Foundation Models That Are Already in Your MLLMs

Yuxuan Li, Zichen Tian, Qianru Sun

原文摘要

Synthetic aperture radar (SAR) foundation models provide transferable representations for diverse perception tasks in all-weather Earth observation. However, their development often relies on costly large-scale SAR pretraining, raising the question of whether such extensive domain-specific pretraining is necessary. We find that modern multimodal large language models (MLLMs) already provide visual encoders that can outperform dedicated SAR foundation models as downstream initializations. This motivates a new paradigm: reuse general visual capabilities and devote domain training to brief specialization. We therefore introduce SARVIA, an adaptive post-pretraining method that specializes modern MLLMs using self-supervised visual questions with computable answers. These questions are constructed from unlabeled observations through general image tasks that capture spatial relations and SAR-specific tasks that exploit native measurements and SAR--optical correspondence. A shared answer-prediction objective jointly trains low-rank adapters across visual and language components, with loss-driven task sampling. We then export the adapted visual encoder as a standalone backbone. With 600 adaptation steps and 2 GPU-hours, SARVIA outperforms the compared foundation models on all six SAR detection and segmentation benchmarks. Compared with dedicated SAR pretraining, SARVIA reduces domain-training costs by orders of magnitude while improving visual transfer across architectures and scales. This new paradigm shifts the emphasis from repeated, costly pretraining to a reusable specialization process that can benefit from advances in open MLLMs. Dataset and code: https://github.com/zcablii/SARVIA.

cs.CV

新论文 · v1arXiv:2611.22270

Teaching Language Models to Narrow Boolean Patent Searches from Search Feedback

Seiya Kawano, Koji Marusaki, Hirofumi Nonaka, Koichiro Yoshino

原文摘要

Patent prior-art searchers issue Boolean queries line by line, broadening to find relevant documents and narrowing until candidates can be screened. We distill 38,397 Japan Patent Office search reports into executable expert strategies, re-execute them, and evaluate generated strategies by citation recall and the smallest set containing each citation. Prompted models write valid, high-recall strategies but leave citations in sets too large to screen. We adapt a generator offline from scored rollouts in two forms: strategy-level learning from a screening-aware strategy score, and line-level learning from citation-preserving narrowing credit, which upweights the query lines keeping a found citation in a smaller set. On shared rollouts, line-level credit outperforms strategy-level scores on screening measures; iterated, it cuts the median citation-containing set from 768 to under 50 and places more citations in sets under 100 documents than experts, at lower recall. Strategy-level preference learning reaches near-complete recall; the two forms are complementary.

cs.IR · cs.AI · cs.CL

版本更新 · v2arXiv:2611.19032

A Multigrid Finite State Projection Algorithm For The Solution Of The Reaction-Diffusion Master Equation

Aditya Dendukuri, Linda Petzold

原文摘要

We develop a multigrid method for the finite state projection of the reaction-diffusion master equation (RDME). The RDME evolves the joint probabilities of molecular count configurations across well-mixed voxels coupled by local reactions and diffusive jumps. When fast diffusion or large reaction rates make this evolution stiff over long time horizons, implicit time stepping requires solving a large shifted linear system at every step. Grouping neighboring voxels and summing their molecular counts produces a hierarchy of coarser state spaces terminating at a one-voxel chemical master equation. Restriction sums residual entries with the same coarse counts, while multinomial prolongation preserves the RDME generator form on every level with explicit coarse reaction and diffusion rates. For reversible diffusion, the error omitted by coarsening is bounded by the graph Dirichlet energy of jumps inside the aggregates, with a constant independent of population. Numerical tests with standard multigrid cycles and point or block Gauss-Seidel smoothing reach 7.16 million states and resolve rare probabilities of order $10^{-7}$.

cs.CE

版本更新 · v3arXiv:2604.22774

When VLMs 'Fix' Students: Identifying and Penalizing Over-Correction in the Evaluation of Multi-line Handwritten Math OCR

Jin Seong, Wencke Liermann, Minho Kim, Jong-hun Shin, Soojong Lim

原文摘要

Accurate transcription of handwritten mathematics is crucial for educational AI systems, yet current benchmarks fail to evaluate this capability properly. Most prior studies focus on single-line expressions and rely on lexical metrics such as BLEU, which fail to assess the semantic reasoning across multi-line student solutions. In this paper, we present the first systematic study of multi-line handwritten math Optical Character Recognition (OCR), revealing a critical failure mode of Vision-Language Models (VLMs): over-correction. Instead of faithfully transcribing a student's work, these models often "fix" errors, thereby hiding the very mistakes an educational assessment aims to detect. To address this, we propose PINK (Penalized INK-based score), a semantic evaluation metric that leverages a Large Language Model (LLM) for rubric-based grading and explicitly penalizes over-correction. Our comprehensive evaluation of 15 state-of-the-art VLMs on the FERMAT dataset reveals substantial ranking reversals compared to BLEU: models like GPT-4o are heavily penalized for aggressive over-correction, whereas Gemini 2.5 Flash emerges as the most faithful transcriber. Furthermore, human expert studies show that PINK aligns significantly better with human judgment (55.0% preference over BLEU's 39.5%), providing a more reliable evaluation framework for handwritten math OCR in educational settings. Code is available at https://github.com/9115jin/PINK.

cs.CY · cs.AI · cs.CV · cs.LG

新论文 · v1arXiv:2611.22262

OfficePrism: Benchmarking Agents on Single-Domain Operations Across Enterprise Business Functions

Hanfeng Liu, Zhenyu Luo, Dongchao Zhang, Zexi Liu, Zulong Chen, Jinxin Hu, Jia Xu, Zeyi Wen

原文摘要

Broad workplace scores can mix competence within one business function with the extra cost of coordinating across functions and systems, making failures hard to localize. OfficePrism evaluates this prerequisite through 420 single-domain enterprise tasks spanning seven business functions under shared, benchmark-defined L1--L3 task-structure levels. Each task runs in a fresh environment combining a shared synthetic organization with one function-specific domain and yped state access. Our pipeline uses grounded records, business rules, and tool schemas to jointly construct a Chinese-language ticket, a hidden executable reference witness, and an expected response, followed by automated filtering and human curation. The same task set is evaluated through full-schema and search-and-dispatch packages. Across 124 model--harness--package configurations, the per-case joint natural-language-and-database pass rate ranges from 22.6% to 76.4%, with a median of 67.9%. L1 is highest in all 124 configurations, and L2 exceeds L3 in 122. Among 50 configurations sharing the same harness and model labels across both packages, search scores higher in 30, ties in one, and scores lower in 19.

cs.CL · cs.AI · cs.LG · cs.SE

新论文 · v1arXiv:2611.22261

Manufactured Authenticity: How Behavioral Signals Are Produced and Misread in Online Markets

Hou-Wan, Long, Yun Huang

原文摘要

Online platforms increasingly ask users to infer credibility from behavioral signals whose production conditions are opaque. We introduce manufactured authenticity: the platform-mediated production of observable activity that interfaces invite users to read as organic participation. Using 996,834 cryptocurrency tokens and 50,895 creator wallets from Pump.fun, a Solana-based token launchpad, we examine how legitimacy signals are produced in an automation-enabled online market. We identify four production strategies (high-velocity launching, passive launching, template-content creation, and organic-style creation) that generate distinct but interface-similar cues of activity, narrative plausibility, and participation. High-velocity and template-content strategies emerge as alternatives rather than cumulative layers: the former produces activity at scale, while the latter produces descriptions associated with higher reply engagement. Yet visible engagement does not imply broader diffusion: template-like content attracts replies without greater ownership dispersion, and tokens associated with non-organic production strategies exhibit more concentrated investor holdings than organic-style tokens. We argue that platform governance should move beyond detecting manipulation toward making signal provenance legible. We propose authenticity disclosure as a design approach for surfacing production conditions without requiring definitive claims about automation, AI authorship, or actor intent.

cs.SI

版本更新 · v2arXiv:2611.21126

IGRecon4D: Dynamic-Object-Aware Feed-Forward Reconstruction of Driving Scenes

Yifei Tong, Ziyang Huang, Yizhao Han, Xiaoxiao Long, Hao Zhu

原文摘要

Feed-forward 4D driving-scene reconstruction enables efficient modeling of dynamic autonomous-driving scenes, but current methods suffer from two complementary failure modes: semantic leakage of traffic participants into the static representation and geometric drift of Gaussian locations across viewpoints. We propose \textbf{IGRecon4D}, a feed-forward dynamic scene reconstruction framework that addresses these failures with training-time instance-prior distillation and LiDAR-anchored Gaussian positioning. Specifically, an instance-level semantic branch provides a potentially dynamic participant prior, which is distilled into dynamic-mask learning through the Instance-Dynamic Consistency Constraint to encourage high-recall localization of traffic-participant regions prone to dynamic-static leakage. In parallel, sparse LiDAR measurements guide dense depth estimation, and the resulting depths are back-projected to anchor Gaussian positions for improved multi-view geometric consistency. Experiments on the Waymo Open Dataset and zero-shot evaluation on nuScenes demonstrate improved full-image reconstruction on the main benchmark and stronger traffic-participant-region reconstruction under cross-dataset evaluation.

cs.CV

新论文 · v1arXiv:2611.22258

ALERT: Extending Humanoid Motion Trackers with a General and Lightweight Human Avoidance Pipeline

Zhaoyang Li, Chiyu Zhang, Chengxin Xu, Peng Yang, Zhonghao Guo, Wanting Li, Ziyu Chen

原文摘要

Whole-body motion tracking has enabled humanoid dancing, athletic motions, and teleoperation, providing a foundation for capability demonstrations and manipulation data collection. However, existing tracking policies lack awareness of nearby humans and proactive avoidance capabilities, while motion substitution and local constraint-based corrections may compromise reference motion integrity and tracking continuity. We propose ALERT, a general lightweight pipeline for extending motion tracking to shared human-robot environments. Through lightweight adaptation, it integrates human perception and proactive avoidance into pretrained tracking policies, balancing avoidance demands with reference motion tracking while preserving existing motion capabilities. Simulation and real-world experiments across tracking backbones demonstrate reliable collision-free execution through localized human avoidance, preserving whole-body coordination and enabling rapid recovery of reference tracking, while retaining the ability of pretrained policies to track unseen motions.

cs.RO

版本更新 · v2arXiv:2606.22945

Controllable Texture Tiling with Transformed RoPE-Enhanced Diffusion Models

Junrong Huang, Zhiyuan Zhang, Rui Tang, Hongbo Fu, Jing Liao

原文摘要

Realistic integration of user-specified textures into scene images is a fundamental task in computer graphics and image editing. While existing material transfer and reference-guided inpainting methods can edit surface appearances, they often fail to address the specific requirements of texture tiling. This task necessitates precisely repeating a reference pattern according to user-defined parameters such as frequency, orientation, and scale. Furthermore, current generative approaches often struggle to maintain the structural fidelity of the reference texture, limited by either destructive pixel-level resampling or the lack of fine-grained spatial information in semantic image encoders, and they frequently fail to preserve the coherent lighting and geometry of the original scene. In this paper, we propose a novel framework for controllable and high-fidelity texture tiling based on Diffusion Transformers. Our approach introduces two key technical innovations to decouple spatial manipulation from content generation. First, we propose a Coordinate-Transformed Rotary Embedding mechanism. By applying 2D affine transformations directly to the relative positional embeddings between the target latent and the image condition, we achieve precise control over tiling patterns without explicit pixel warping, thereby utilizing the full information of the reference condition without degradation. Second, a Disjoint Attention Mask is employed to shield reference features from semantic leakage. This preserves structural integrity while seamlessly blending the synthesized texture with the scene's original lighting and geometry. Extensive experiments demonstrate that our method outperforms state-of-the-art baselines in both control accuracy and texture fidelity.

cs.GR · cs.CV

版本更新 · v2arXiv:2611.07483

Signed but Not Safe: Requirement Integrity in Multi-Agent LLM Handoffs

Xiaobo Chen, Genliang Zhu, Ziyuan Wang, Chu Wang

原文摘要

Enterprise AI agents split requests across subagents, and each handoff can drop, alter or ignore a requirement. A preregistered study on synthetic, exactly scorable tasks compares free-text, structured JSON and signed requirement-manifest handoffs: the orchestrator extracts each requirement as a verbatim quote plus a checkable predicate, code signs it and deterministically verifies the merger's decision. With Qwen3-8B (1,440 trajectories, five threats), signed manifests cut unsafe commits under attack from 69.4% to 9.0% (60.4 pp, 95% CI [51.4, 69.4]) with no detectable utility loss versus structured handoffs (S2 -0.4 pp, 95% CI [-14.2, 13.3]). Signing defeats in-transit mutation: unsigned manifests violated 79.2 pp more often than signed ones, which never did; this replicated in gpt-oss-20b and gemma-4-12b. There, without an adversary, signed manifests were descriptively slightly worse than structured handoffs (11.1% vs 2.8%; 16.7% vs 8.3%; not tested) and lost utility overall (gpt-oss-20b, all threats: -28.7 pp). On identical Qwen3-8B trajectories, the deterministic verifier caught 78.7% of violating decisions versus 59.0% for an LLM checker, and an oracle manifest removed all remaining unsafe commits, so the residual risk is in extraction. A preregistered pre-signing injection confirmed this: one adversarial line raised signed-manifest unsafe commits from 14.6% to 37.5% (Qwen3-8B), 11.1% to 63.9% (gpt-oss-20b) and 16.7% to 97.2% (gemma-4-12b), and every such commit carried a manifest corrupted before signing. Signing protects transit; extraction is the trust boundary. A testable pre-signing specification (PSE), specified after the injection results and frozen before an offline evaluation, blocked all these injected commits (fixed templates) but refused 45.8%, 11.1% and 22.2% of benign requests, changing completions by -8.3 pp, -2.8 pp and 0.0 pp.

cs.CR · cs.AI · cs.MA

新论文 · v1arXiv:2611.22252

A Visual Information Extraction System Using Multimodal Large Language Models for Scanned Cognitive and Behavioral Assessments

Enshuo Hsu, Linh Nguyen, Sunyang Fu, Heath Goodrum, Sandra Stansberry, Kirk Roberts, Hongfang Liu, Yen-Chi L. Le

原文摘要

Objective. Paper-based assessments are common in patient care, but handwriting and scanning artifacts make these forms difficult to process at scale. This study proposes a modular, multimodal LLM-based system with human oversight for extracting fields and scores. We conducted a qualitative analysis of the use of LLMs for hand-drawing analysis. Materials and Methods. The system processes cognitive assessments (i.e., MMSE, MoCA, Mini-Cog) and the NICHQ Vanderbilt Assessment using two modules: 1) a form classifier that assigns a scanned page to a form type, followed by a corresponding 2) score extractor that extracts fields and scores into a schema. A human-in-the-loop design utilizing dual-model validation engages human annotators when two LLMs disagree, limiting manual review to challenging pages only. Results. End-to-end accuracy for cognitive assessments was 88%, with most form types exceeding 90%. For the NICHQ Vanderbilt, overall accuracy reached 97.5%, with all form types above 96%. The human-in-the-loop design further improved cognitive assessment accuracy to 97.5% while reducing manual work by 63.8%. In the Mini-Cog Clock Drawing task, qualitative analysis showed that 62.3% of all extraction errors stemmed from ambiguous drawing, in which cases the LLM provided reasonable readings. Discussion. Compared to current manual data extraction, our LLM-based system reduces processing time by 10 to 20 times and costs by over 12 times. The modular design allows seamless expansion to additional form types. Conclusion. Our system provides an accurate, scalable, and cost-efficient solution for structuring data trapped in handwritten paper forms for clinical decision support.

cs.AI

版本更新 · v4arXiv:2610.17833

PHastR: Faster Minimal Perfect Hashing with Rotated Layouts

Sebastiano Vigna

原文摘要

We present PHastR, a minimal perfect hash function of the PHast family. Like PHast+, the fast-to-build variant of PHast, PHastR finds feasible seeds with bit-parallel operations: its seeds move keys along rings of slots, and to evaluate the seeds of a bucket it cyclically shifts, for each key, a word recording which slots of its ring are used. Unlike PHast+, however, it is almost immune to self-collisions, which make two keys of a bucket collide for (almost) all its seeds: more than a third of the buckets bumped by PHast+ with wrapping and multiplier 3 contain one. With 8-bit seeds, PHastR uses $1.94$ bits per key, essentially the same space as the best variant of PHast+ with wrapping, but it is built in $37\%$ of the time, and its queries are $34\%$ faster on $10^9$ keys, as it bumps $0.5\%$ of the keys instead of $3.9\%$; they are faster also than those of PHast, which takes almost thirteen times as long to build, and than those of PtrHash, which uses more than one bit per key more. With a larger expected bucket size PHastR comes within $0.02$ bits per key of the space of PHast, using $1.90$ bits per key, and its queries are still about as fast. Its construction also scales better with the number of threads: with all the threads of a 96-core machine it is more than two and a half times faster than that of PHast+. An offline construction built PHastR on a trillion keys in $9.3$ hours on a single machine. Finally, we argue that when each key can be placed only within a range of $W$ slots, every placement of $n$ random keys on $n$ slots, however found, must bump on large key sets a constant fraction of the keys: we derive an asymptotic lower bound of about $0.1/W$ on the expected value of this fraction, and we prove that, in a Poisson model, the best placement bumps about $1/2W$ of the keys, which is about one tenth of the keys bumped by PHastR.

cs.DS

新论文 · v1arXiv:2611.22250

PCGRL for Complex Platformers: Synthesizing Playable and Diverse Levels via Inflated Envelopes and Forward Curricula

Di Wu

原文摘要

Procedural Content Generation via Reinforcement Learning (PCGRL) has emerged as a promising paradigm for automated game development. However, existing PCGRL frameworks still suffer from severe exploration bottlenecks and scaling limitations when faced with long-sequence generation tasks governed by strict rigid-body rules and non-linear kinematic boundaries (e.g., platformer constraints). Consequently, traditional approaches frequently fail to maintain reliable level solvability on large-scale canvases. To address these challenges, we present a physics-aware, curriculum-guided PCGRL framework. First, we construct an "Inflated Volume Envelope" mechanism, which provides a physics-constrained representation that incorporates continuous kinematic feasibility into the discrete state space of the MDP. Second, to alleviate the sparse reward challenge induced by extremely long decision sequences, we introduce intermediate state-transition feedback and a multi-stage forward extension curriculum learning framework, enabling informative value estimation and stable credit assignment over long-horizon trajectories. Finally, to resolve the issue where deterministic policies after convergence generate highly monotonous map paths with a lack of diversity, we activate high-entropy stochastic inference during the synthesis phase, regularized by a post-hoc parallel rejection filtering mechanism. Experimental results demonstrate that our framework significantly enhances structural diversity while maintaining high physical playability across multi-scale environments. Comparative evaluations across multi-scale canvases demonstrate that our framework maintains superior convergence stability and dimensional scalability, reliably synthesizing solvable levels where traditional PCGRL baselines degrade.

cs.LG · cs.AI

版本更新 · v2arXiv:2605.20730

Distributional Alignment as a Criterion for Designing Task Vectors in In-Context Learning

Jihoon Kwon, Jiwon Choi, Jy-yong Sohn

原文摘要

In-context learning (ICL) allows large language models (LLMs) to adapt to new tasks through demonstrations, yet it suffers from escalating inference costs as context length increases. While task vectors offer a promising alternative by compressing demonstrations into compact hidden-state representations, their quality has been evaluated only through downstream task accuracy. This indirect criterion provides limited insight into how to design more effective task vector extraction methods. In this paper, we posit that inference using task vectors should align their predictive distribution with that of ICL. To quantify this, we introduce $d_{\text{NTP}}$, a metric that measures the discrepancy in next-token probabilities between task vector-based and ICL-based inference. Our empirical analysis reveals that $d_{\text{NTP}}$ serves as a performance proxy, exhibiting a strong negative correlation with downstream accuracy. Motivated by this, we develop Linear Task Vector (LTV), a method designed to minimize $d_{\text{NTP}}$ via a closed-form linear mapping that estimates demonstration effects through regression. Across eight classification benchmarks and five LLMs, LTV consistently outperforms existing task vector baselines, improving average accuracy by 9.2\% while reducing inference latency. We further show that LTV outperforms the baselines on regression tasks. Moreover, we investigate the transferability of LTV across different model scales; an aspect that has remained nascent in task vector research. Specifically, we empirically show that task vectors from a larger model can enhance a smaller model's performance by 6.4\%, suggesting a new utility for extracted task representations.

cs.CL · cs.AI

新论文 · v1arXiv:2611.22248

OAK-Mind: Zero-Training Mental Health Change Inference from Passive Sensing via Knowledge-Grounded Multi-Agent LLMs

Yishu Ji, Zhihan Jiang, Will Ke Wang, Yuang Fan, Anind K. Dey, Xuhai "Orson" Xu

原文摘要

Wearable and smartphone sensors capture behavioral signals associated with mental health, yet inferring mental health outcomes from these signals has traditionally relied on supervised models requiring labeled data and offering limited insight into their predictions. Large language models (LLMs) offer new opportunities to reason over behavioral evidence, but existing LLM-based approaches to passive sensing have largely continued to rely on task-specific fine-tuning or sensor-specific pretraining. In this paper, we introduce \textbf{OAK-Mind}, a zer\textbf{O}-training, multi-\textbf{A}gent, \textbf{K}nowledge-grounded LLM pipeline for inferring mental health changes from passive sensing data. The pipeline organizes sensing data into behavioral dimensions including sleep, physical activity, location mobility, and smartphone use, and orchestrates specialized agents grounded in mental health literature to interpret longitudinal behavioral changes. It synthesizes their assessments and applies questionnaire-based symptom rating to infer changes relative to an individual's baseline assessment with human-readable rationale grounded in observed behavioral patterns and domain knowledge. Across datasets and prediction tasks, while without task-specific training, OAK-Mind achieves comparable or better performance than the most predictive supervised baselines trained on additional labeled samples. It also demonstrate consistent improvement upon direct prompting across four tested LLM backbones. Ablation analyses support the benefits of combining behavioral interpretation with symptom rating, distributing analysis across domain-specific agents, and incorporating domain knowledge. Our findings highlight the potential of knowledge-grounded, multi-agent LLMs for training-free inference of mental health changes from passive sensing data.

cs.MA · cs.AI · cs.HC · cs.LG

新论文 · v1arXiv:2611.22246

Multispectral-Polarization-Infrared Multi-Aperture Camouflaged Vehicle Detection

Shu Wang, Xiong Lin, Yuan Song, Junjie Wang, Feng Huang, Wenxi Liu

原文摘要

Camouflaged vehicle detection is challenging because camouflage suppresses discriminative cues across sensing modalities. Existing multimodal methods often require precise pixel-level registration and feature-level fusion, creating a trade-off between accuracy and latency. We propose a spectral-polarization-infrared tri-modal detection framework co-designed with a multi-aperture imaging setup to exploit complementary imaging physics. A consensus-guided decision-level fusion strategy combines cross-modal detections within bounded registration tolerances, reducing dependence on precise alignment while maintaining accuracy and real-time performance. We construct a tri-modal camouflaged vehicle dataset containing infrared, polarization, and spectral data. Experiments show that the proposed method achieves 82.7% mean Average Precision (mAP) with an end-to-end latency of 16 ms, outperforming representative feature-level fusion approaches. On the public MID-1K dataset, the framework generalizes to RGB-Depth-Infrared modalities without architectural modification and improves mAP@0.5 by 5.7% over state-of-the-art methods. These results demonstrate the potential of decision-level consensus fusion and multi-aperture sensing for robust and deployable camouflaged vehicle detection.

cs.CV

新论文 · v1arXiv:2611.22244

PhyVGGT: Feed-Forward Articulated Object Reconstruction from Monocular Videos

Qi Shao, Zhihao Cao, Shuhao Zhai, Anh Nguyen, Hong Liang, Baoru Huang, Liang Li

原文摘要

Reconstructing an articulated object with its 3D movable parts, joint parameters and unseen articulation states from an uncalibrated monocular video is essential for robot manipulation and interactive digital twins. Existing per-scene optimisation methods require minutes to hours and external depth or camera poses, whereas feed-forward 3D foundation models reconstruct dense point maps in one pass without segmenting movable parts or inferring joints. Even on these monocular point maps, regressing or fitting continuous joints directly fails on casual videos, since cross-frame attention blurs moving part boundaries in deep layers, underestimates motion along the viewing ray and leaves continuous axes ill-conditioned under small opening angles. To address these challenges, we propose PhyVGGT, a single-pass framework on a frozen 3D foundation model that anchors moving-part matching and closed-form joint estimation to the undistorted geometry of the stationary base. First, our Part and Motion Decoder fuses intermediate per-frame tokens with global tokens and references part queries to a static-base query to segment 3D parts, align point maps on the static base and predict learned Bingham priors. Second, our Kinematic Inference Layer fits an orthogonal Manhattan frame to static surface normals, selects the joint axis in closed form under a Bingham posterior combining pairwise motion scatter with the learned priors, and solves a linear system for the hinge pivot to drive unseen states. Trained solely on synthetic data, PhyVGGT achieves state-of-the-art monocular performance across five benchmarks, outperforming FAMOS and monocular ArtiPoint, surpassing posed RGB-D ArtiPoint in median error, and running in 6.8 s per 48-frame video against hours of per-scene optimisation in Articulat3D. Project page: https://phyvggt.github.io.

cs.CV

版本更新 · v2arXiv:2611.20090

Latent World Modeling for Point-Cloud Video Pretraining

Zhuoyue Zhang, Jian Liu, Jihua Zhu, Ajmal Saeed Mian

原文摘要

Masked modeling is the dominant self-supervised paradigm for point-cloud videos. However, it leaks the information it is meant to predict, whether it reconstructs masked points as in MAE-style methods or predicts their latent features. Because point-cloud tokens are anchored at points sampled from each frame, querying a target at its own position reveals where its geometry has moved, in reconstruction and latent prediction alike. For latent predictors, random spatio-temporal masks introduce a further shortcut, as visible frames on both sides of each target allow interpolation rather than forecasting. The pretext task thus reduces to completion. Once the target positions are withheld, a masked latent predictor performs only slightly better than copying the last frame. To remove this leakage, we propose PointWM, a latent world model that turns completion into forecasting by predicting the features and geometry of future frames from strictly earlier context. Each target is queried only with its last-seen position and timestamp, while a latent action learned without annotations is meant to capture the part of the future that the past leaves undetermined. On HOI4D action segmentation with a P4Transformer backbone, PointWM improves F1@50 over training from scratch by 24.9 offline and 29.1 under strictly causal inference. These results show the promise of latent world models as a leakage-free pretraining paradigm for point-cloud videos.Our code is publicly available at https://github.com/InitalZ/PointWM.

cs.CV

新论文 · v1arXiv:2611.22241

Where Does Hindsight Enter Clinical Agent Benchmarks? An Audit of Simulators and Case Construction

Meilu Zhu, Xiaohan Li, Axiu Mao

原文摘要

Benchmarks for LLM diagnostic agents are built from retrospective records: the case an agent reads is rewritten from discharge summaries, and unrecorded test results are generated by a simulator that often sees the final diagnosis. HindAudit separates three hindsight channels (the diagnosis given to the simulator, the retrospective context it conditions on, and the agent-facing case text) and measures each with judges trained only on real data. On 27,489 emergency admissions from MIMIC-IV, five registered tests found no leakage into simulated laboratory results: providing the diagnosis to five simulators had a negligible effect, and prompted gatekeepers diluted the diagnostic signal, although exploratory results suggest they can raise agent scores. The largest effect lay in the case text. Against a presentation-time reconstruction from triage records, benchmark-style summaries raised the zero-shot accuracy of four LLMs from 25.4% to 39.7% and discharge histories to 45.3%, and raised six interactive agents' scores while barely changing their ranking. The exploratory gap was reproduced in a registered replication on held-out patients. Masking diagnosis names left it unchanged. Because MIMIC lacks a contemporaneous bedside history, the gap is an upper bound on hindsight. We report all registered outcomes and recommend construction practices.

cs.CL

新论文 · v1arXiv:2611.22239

Solver-Free and Cost-Aware Online Scheduling of AI Data Center Tasks

Xin Qin, Dawei Qiu, Fei Teng

原文摘要

AI data centers receive computing tasks continuously, whereas solver-based optimization takes time to run and electricity is priced per settlement period. This paper bridges this timing gap through a solver-free online optimization rule inspired by dual decomposition. The rule assigns each task a start period upon arrival to optimize energy cost subject to operational constraints, shifting flexible tasks toward low-price periods while keeping high-priority tasks on schedule. Simulations on the A100 GPU trace (3,456 GPUs, 1,343 tasks) show that the proposed rule keeps GPU and CPU use within capacity while scheduling tasks at low cost. Compared with a multi-timescale optimization benchmark, it achieves a lower cost and, because it needs no solver, much less computation time.

eess.SY · cs.AI

新论文 · v1arXiv:2611.22238

Context Has a Price: Adding and Removing Context for LLM Coding Agents under Prefix Caching

Zerui Yang, Miaomiao Dong, Quan Xue, Chaorui Zhang, Xuanyu Zheng, Xiyuan Wang, Haolin Ruan, Xueyan Niu 等 12 位作者

原文摘要

Coding agents repeatedly send their conversation history to a language model. Adding useful code may reduce search, while removing old tool outputs may shorten later prompts. But do these changes reduce the cost of solving a task? We study this as a measurement problem in more than 20,000 runs of open models on SWE-bench Verified, SWE-bench and Loc-Bench. We account separately for uncached input, cached input and output tokens. Three findings emerge. First, in our main evidence-package experiments, retrieved code reduces read and search commands by 18--34%, but increases cost by 33--42% when cached input costs one tenth of uncached input, without a measurable improvement in resolution. Second, removing old observations can either save money or increase cost: the same approach saves 19--36% without a cache discount but increases cost by 38--116% with a tenth-price cache. Third, shorter prompts do not guarantee cheaper runs because agents may respond by taking more steps. We also find that concurrent experiments can share cached prefixes and distort cost comparisons. These results show why context-management methods should be evaluated using both token prices and the agent's subsequent behavior.

cs.AI

新论文 · v1arXiv:2611.22236

Spatially local mini-batching for implicit neural representations

Minseok Choi, Swarup Dhar, Heejae Kwon, Kookjin Lee, Donsub Rim

原文摘要

Neural surrogates based on implicit neural representations (INRs) are typically trained on mini-batches spread over the whole domain, since a generic INR loses accuracy when every point of a batch lies in one small region. We show that low-rank neural representations (LRNRs), INRs whose weight matrices are products of shared bases with coefficients emitted by a small hypernetwork, can be trained with spatially local mini-batches. Each step uses the points of one time snapshot of an adaptive-mesh numerical solution inside one small cell, with snapshots and cells drawn according to the refinement of the mesh. We posit that such training is enabled by the structural property of LRNRs, as a local step reaches the shared bases only through the $r$ coefficients of each layer, and keeps one cell from rewriting the network. By a Kolmogorov-width argument, we show that when restricted to a small cell, the hidden states of LRNRs lie close to a low-dimensional subspace, which suggests the local steps only affect low-rank subspaces of the shared bases. On six hyperbolic-conservation-law problems with solutions computed using adaptive mesh refinement, one local training recipe reaches 1.1-2.3% relative $L^2$ error with a tenth of the parameters of a dense network of the same width. Finally, we provide a comparison by training a hypernetwork-SIREN, a DeepONet, and a Fourier neural operator (FNO) of the same size with the same local batches and training budget. We observe that these baselines reach 16-78% where the LRNR reaches 4.9%. Interestingly, we also observe that local training has a significant effect on the per-cell low-dimensional structure even in a wide generic hypernetwork-SIREN.

cs.LG

新论文 · v1arXiv:2611.22235

CoSphere-SLAM: Multi-Agent Panoramic Gaussian Splatting SLAM with Spherical Loop Closure

Qi Shao, Zhihao Cao, Shuhao Zhai, Taoyu Wu, Zhuoxiao Li, Anh Nguyen, Long Hu, Xianzhi Li 等 11 位作者

原文摘要

Dense collaborative mapping is essential for search and rescue, building inspection, and warehouse automation, where panoramic cameras capture the entire surroundings in a single frame. Unlike pinhole agents that share views only at similar headings, panoramic agents observe overlapping scenes at any 3D orientation, yet searching full rotations also produces mutually consistent false loop closures across distinct symmetric rooms. Moreover, continuous monocular scale drift splits rigidly merged maps at revisited surfaces, while depth noise at short baselines distorts loop translation directions. To address these challenges, we propose CoSphere-SLAM, the first multi-agent Gaussian splatting SLAM framework for panoramic cameras, whose spherical loop closure aligns spherical features over $\mathrm{SO}(3)$ via fast Fourier correlation across arbitrary orientations and rejects symmetric false closures through global $\mathrm{Sim}(3)$ consensus. Building on these closures, directional global optimization solves a per-keyframe $\mathrm{Sim}(3)$ pose graph with log-scale regularization to correct scale drift while separating optical-flow translation directions from depth-based magnitudes. Finally, omnidirectional Gaussian fusion transforms each Gaussian with its keyframe similarity and renders Gaussians at their maximum ray response to jointly refine poses and maps. Experiments on indoor and cross-session multi-agent panoramic benchmarks demonstrate that CoSphere-SLAM achieves state-of-the-art trajectory accuracy and rendering quality among single-agent and multi-agent methods. Project website: https://cosphere-slam.github.io.

cs.CV

版本更新 · v3arXiv:2511.18820

A physics-constrained neural solver for incompressible flows without labeled data

Qifeng Hu, Inanc Senocak

原文摘要

We present a physics-constrained neural solver for incompressible flow that requires neither labeled data nor supervised pretraining. The solver enforces incompressibility and boundary conditions (BCs) to strict tolerances. We attribute the limited Reynolds numbers of existing physics-informed approaches to insufficient enforcement of these constraints, on which conventional finite-difference and finite-volume solvers depend. We therefore formulate incompressible flow as a constrained optimization problem within the physics- and equality-constrained artificial neural network (PECANN) framework: the pressure Poisson residual is minimized subject to the momentum equations, continuity equation, and BCs imposed as equality constraints on the primitive variables, while a conditionally adaptive augmented Lagrangian method enforces each constraint. The pressure Poisson objective proves critical. Across all benchmarks, replacing it with the momentum residual fails to converge to accurate solutions under identical architecture and constraint enforcement, which we attribute to the global elliptic coupling of pressure and velocity that local momentum-residual minimization lacks. For advection-dominated flows, we introduce an adaptive vanishing entropy viscosity that stabilizes training while leaving the converged solution unchanged. The solver predicts lid-driven cavity flow up to Re = 7,500 with centerline velocity profiles matching benchmark data, and is further validated on flow over a backward-facing step at Re = 800, 3D unsteady Beltrami flow, and steady and unsteady flow past a circular cylinder under an inflow-outflow configuration, for which an ablation study identifies admissible outlet BCs for velocity and pressure. From a randomly initialized network and without external perturbations, the solver captures the spontaneous onset of periodic vortex shedding in unsteady cylinder flow.

physics.flu-dyn · cs.LG

版本更新 · v4arXiv:2606.15867

CogCanvas: A Benchmark for Evaluating Multi-Subject Reference-Based Image Generation

Long-Bao Nguyen, Quang-Khai Le, Tam V. Nguyen, Minh-Triet Tran, Trung-Nghia Le

原文摘要

Multi-subject reference-based image generation requires jointly preserving multiple human identities, binding per-person objects and fashion items, and respecting a specified background scene, a regime where current diffusion models remain brittle. Existing benchmarks evaluate only one axis at a time and none jointly captures multi-identity composition with human-object interaction, background grounding, and spatial plausibility. We introduce CogCanvas, a benchmark of 1,952 curated reference images spanning 100 celebrity identities, 115 distinctive objects and fashion items, and 29 real-world background scenes including landmarks, from which we construct 1,361 compositional prompts covering 2-5 person group sizes. The curation pipeline combines DINOv2-based deduplication, two-stage aesthetic filtering, and automated derivation of structured interaction and position graphs that serve as ground-truth supervision. CogCanvas supports three tasks, reference-based multi-human-object generation (primary), text-to-image compositional generation, and reference retrieval, under a unified six-axis evaluation protocol. We introduce two metrics tailored to the multi-reference setting: BG-Sim, which scores background fidelity on SAM 3-masked regions via DINOv3 feature similarity, and Attr-VQA, which uses a multimodal LLM to verify per-subject attribute binding and inter-person interactions against the structured graphs. Benchmarking five SOTA methods reveals that every model degrades substantially as group size grows from 2 to 5, with near-complete failure on object/fashion binding beyond three subjects.

cs.CV

新论文 · v1arXiv:2611.22231

From Temperature-Limited to Battery-Limited Legged Locomotion

Raphaël Ségas, Balázs Opra, Léo Ghafari, Thomas Stewart

原文摘要

On legged robots, sustained locomotion often ends in thermal shutdown rather than battery depletion: the heat of walking concentrates in a few joint motors, which overheat long before the battery is empty. We train thermally aware locomotion policies by reinforcement learning without ever observing temperature, and demonstrate this on a Unitree Go2 quadruped. We first identify a coupled 13-node lumped RC thermal network, fitted on two runs of a single robot and calibrated against the measured electrical power, that predicts all twelve motor temperatures with a mean RMSE below 1 $^\circ$C across different robot instances, gaits, payloads, and speeds. Under a sustained gait, the temperatures the motors will settle at follow directly from the gait-averaged squared torques and joint speeds. Our core contribution is a reward that drives down the hottest predicted asymptotes: thermal time constants exceed the credit-assignment horizon of reinforcement learning by orders of magnitude, but predicted asymptotes respond to torque and joint speed within a single gait cycle, so the policy learns to lower and spread heat with no temperature input. On the robot, the policy turns sustained locomotion from temperature-limited to battery-limited: with a 5 kg payload at 1 m/s, a learned baseline reaches thermal shutdown after 19 minutes (1.1 km), whereas our policy runs the battery down after 174 minutes (10.0 km) with its hottest motor 14 $^\circ$C below the shutdown threshold in a 26 $^\circ$C room; on an unloaded factory circuit with stairs and ramps, the baseline overheats after 25 laps (6.2 km), while our policy completes 47 (11.2 km) on one battery with 22 $^\circ$C of margin.

cs.RO · cs.LG · eess.SY

版本更新 · v2arXiv:2610.33262

Not All Mislabels Are Equal: Efficient Task-Aware Auditing with Confidence Sequences

Fangyuan Lin, Noah Krever, Jakub Černý, Lily Xu

原文摘要

We study efficient, adaptive auditing of categorical labels in a fixed dataset, motivated by biodiversity credit programs in which expert verification of species records is costly and downstream scores (e.g., payment) are more sensitive to errors on certain labels than on others. Our proposed ATLAS framework couples anytime-valid inference with a task-aware adaptive auditing policy. Representing label corrections through a confusion matrix, we prioritize which data points to inspect next based on both label uncertainty and the influence of potential label corrections on the downstream score function. In our main case study on Kenyan biodiversity data, task-aware auditing reduces the expert review needed to estimate both the mislabel rate and the nonlinear biodiversity score while maintaining anytime-valid guarantees. We also evaluate ATLAS on public datasets for image classification and named-entity recognition. Across our experiments with linear and nonlinear scores, ATLAS generally reaches the same precision as competing anytime-valid methods with substantially fewer audits. When distribution-free guarantees are prohibitively costly, we develop a model-based Bayesian alternative that can further reduce the number of audits by relying on modeling assumptions. Our biodiversity case study highlights a gap between statistical validity and practical feasibility: generic methods such as Serfling's bound and existing confidence-sequence procedures are rigorous but can require prohibitively many expert reviews in practice. Together, these results show task-aware auditing can significantly reduce the number of expert audits needed while providing finite-sample, anytime-valid guarantees

stat.ME · cs.LG · math.ST · stat.AP · stat.ML

版本更新 · v2arXiv:2611.19345

Information Limits of Replay-Free Recurrent State Migration

Khizar Qureshi

原文摘要

When a recurrent model is replaced, its old state may not determine what the new model would compute from the same history. We characterize the information that must be retained before the replacement is known. For a time-invariant affine linear family, the minimum continuous causal memory for order-$k$ local migration equals the reachable dimension of a lifted coefficient system minus the information in the anchor state. A controllable $d$-state model with scalar input needs at most $kd$ additional real coordinates, even when arbitrary matrix replacement directions are revealed only after streaming. A single rank-one direction can already require all $kd$. Conditional singular values and auxiliary-bit bounds distinguish this local information law from recovery at a fixed tolerance. We also give invariant-subspace and future-output constructions. Controlled experiments compare the resulting representations. In a small language model, equal-memory cubic interpolation improves mean state fidelity over third-order coefficients but provides no meaningful predictive gain. An analytic history basis preserves useful adaptation more economically in a coupled identification task. With repeated slow poles, eight history coordinates meet normalized output error $10^{-4}$ across five fitted seeds despite substantial full-state error. Splitting the poles raises the smallest tested successful width to 64.

cs.AI · cs.LG