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

+406新增论文
+306其中 AI 相关
+55已有论文修订
+93新增 AI 导读

arXiv 最近完成扫描:2026-11-16 01:34 · 全站最近入库:2026-11-16 11:42各信源进度 →

统计口径与数据新鲜度

统计 2026-11-15 12:25 — 2026-11-16 12:25(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:2026-11-16 01:34最近发现新增版本:2026-11-16 11:42库内论文最新更新时间:2026-11-14 01:29

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。

23,754 已收录论文19,886 AI 相关6,892 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 65 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-16 01:33(北京时间)
新论文 · v1arXiv:2611.17955

WebArena-Pro: A Heterogeneous, Multimodal, Reproducible Benchmark for Web Agents

Imene Kerboua, Fatemeh Pesaran Zadeh, Xing Han Lù, Weijian Qi, Alexander Miller, Junyi Song, Yunjia Tian, Dongjin Kang 等 22 位作者

原文摘要

Web agents powered by large language and vision-language models are increasingly applied to realistic browser work that spans heterogeneous applications, multimodal content, and stateful workflows. However, existing reproducible web-agent benchmarks cover only a small number of web applications drawn from a few software categories, and restrict modality to text and vision. Live benchmarks broaden site coverage but sacrifice reproducibility, since pages and data drift between runs. Moreover, existing benchmarks do not meaningfully evaluate whether agents can understand and use audio and video content embedded within web tasks. To address these gaps, we introduce WebArena-Pro, a benchmark comprising 300 tasks across 20 self-hosted web applications in six domain categories, spanning distinct interface conventions, workflows, and data models. Across the evaluated agents, the best performance is achieved by both Codex with GPT 6.1 Sol and Claude Code with Claude Opus 5.5 at 62.3%, followed by OpenCode with Kimi 3.1 Pro at 60.7%. The strongest GenericAgent configurations, Gemini 3.1 Pro omni and Gemma4 31B, both achieve 30.3%. Among reproducible, human-curated web agent benchmarks, WebArena-Pro provides the broadest application coverage and the most comprehensive multimodal support to date. The benchmark treats audio and video as core observations alongside text and vision, with dedicated actions for extracting information from each. WebArena-Pro runs each task in isolation and supports reproducible, parallel evaluation. Tasks are authored through a dedicated annotator interface, filtered by LLM-assisted triage, and finally validated by humans before release. Project page: https://webarena-pro.github.io

cs.AI · cs.CL · cs.LG

版本更新 · v2arXiv:2602.09868

Free-GVC: Toward Retraining-Free Extreme Generative Video Compression with Temporal Coherence

Xiaoyue Ling, Chuqin Zhou, Chunyi Li, Yunuo Chen, Yuan Tian, Guo Lu, Wenjun Zhang

原文摘要

Building on recent advances in video generation, generative video compression has emerged as a new paradigm for achieving visually pleasing reconstructions. However, existing methods exhibit limited exploitation of temporal correlations, causing noticeable flicker and degraded temporal coherence at ultra-low bitrates. In this paper, we propose Free-GVC, a retraining-free generative video compression framework that reformulates video coding as latent trajectory compression guided by a video diffusion prior. Our method operates at the group-of-pictures (GOP) level, encoding video segments into a compact latent space and progressively compressing them along the diffusion trajectory. To ensure perceptually consistent reconstruction across GOPs, we introduce an Adaptive Quality Control module that dynamically constructs an online rate-perception surrogate model to predict the optimal diffusion step for each GOP. In addition, an Inter-GOP Alignment module establishes frame overlap and performs latent fusion between adjacent groups, thereby mitigating flicker and enhancing temporal coherence. Experiments show that Free-GVC achieves an average of 93.29% BD-Rate reduction in DISTS over the recent neural codec DCVC-RT, and a user study further confirms its superior perceptual quality and temporal coherence at ultra-low bitrates.

cs.CV

新论文 · v1arXiv:2611.17163

UAV-Flow++:面向语言引导无人机飞行的统一基准与学习套件

UAV-Flow++: A Unified Suite for Benchmarking and Learning Language-Guided UAV Flight

Donglin Yang, Xiangyu Wang, Yantong Zhong, Wenhao Zheng, Zihan Ding, Yue Liao, Hongsheng Li, Ke Xu 等 9 位作者

AI 速读 基于摘要

作者提出 Flying-on-a-Word(Flow)短程语言引导无人机飞行任务,并配套真实与仿真数据集、仿真评测环境及 FlowVLA 学习框架。

cs.RO · cs.CV

查看原文摘要

Language-guided UAV navigation has largely focused on long-horizon route planning, leaving short-range, object-relative flight maneuvers underexplored. To address this gap, we formulate Flying-on-a-Word (Flow), a task requiring a UAV to convert concise natural-language instruction, egocentric visual observation, and current state dynamics into continuous flight actions. Flow encompasses both primitive motion commands and complex object-interactive behaviors, assessing motion intent comprehension and spatial context grounding. To enable policy learning and closed-loop evaluation, we introduce UAV-Flow, a comprehensive dataset comprising 30,692 expert-piloted real-world trajectories across eight distinct motion categories, alongside 10,109 simulation trajectories in the UAV-Flow-Sim environment equipped with task-specific completion criteria. Furthermore, we develop FlowVLA, which undergoes imitation pretraining on mixed real-sim demonstrations and online post-training via Tail-Aware GRPO (TGRPO). By leveraging group reward distributions, TGRPO effectively reinforces high-reward action sequences. Evaluated on 273 held-out UAV-Flow-Sim episodes, pretrained FlowVLA achieves a mean success rate of 75.58%, outperforming the strongest baseline by 6.72 percentage points, which TGRPO post-training further elevates to 93.16% with superior sample efficiency. Physical UAV experiments demonstrate robust execution of object-relative commands in both indoor and outdoor real-world scenes. Together, Flow establishes a novel benchmark and learning framework for language-conditioned flight maneuvers.

新论文 · v1arXiv:2611.16588

CrossPloit: A Benchmark for Cross-Version PoC Migration in Python Web Applications

Hung Nguyen-Huu, Nguyen Anh Tuan, Ting Zhang, Yue Liu, Chengran Yang, Lwin Khin Shar, Eng Lieh Ouh, David Lo

原文摘要

Affected-version ranges in vulnerability databases decide which deployments scanners, patching pipelines, and incident responders treat as vulnerable, yet these ranges are often incomplete, so vulnerable releases are silently treated as safe. Auditing them requires executable evidence: given a proof-of-concept (PoC) exploit for a listed version, show that the same vulnerability can be triggered on an earlier, unlisted version. This cross-version PoC migration combines source-code analysis, environment repair, and execution-based verification. We introduce CrossPloit, a benchmark of 127 migration instances across 45 CVEs in the Python web ecosystem. Each instance includes a version-pinned container, a reference PoC, and a vulnerability-specific oracle; two validators check that the observed effect arises from the disclosed vulnerability. Benchmark construction confirms 149 vulnerable prior versions absent from the affected-version lists of four databases, 127 of which require migration. Across 18 agent configurations (nine models and two harnesses), the best configuration resolves 58.3% of instances, compared with 8.7% for an adapted trace-guided baseline. Attack-vector shifts are particularly difficult: no configuration resolves more than 37.9% of these instances. Higher resolve rates are associated with a smaller share of missed-API failures and a larger share of incomplete executions among the remaining failures. In one configuration, withholding the reference PoC and its environment specification reduces resolve rate from 50.4% to 15.0%, highlighting the value of the supplied reference package. CrossPloit provides an execution-based measurement of under-reported exposure and of how far its enumeration can be automated.

cs.CR · cs.SE

新论文 · v1arXiv:2611.16382

RADIANT: Redundancy-Aware Information Allocation for Universal Multi-Modal Fusion

Shenghai Wu, Yue Lin

原文摘要

Universal multi-modal fusion often fails not because modalities are insufficiently aligned, but because the fusion process allocates information poorly: redundant evidence is repeatedly amplified, modality-unique evidence is over-smoothed during alignment, and task-dependent synergistic evidence is insufficiently activated. We present RADIANT (Redundancy-Aware Dynamic Information Allocation Network), a task-general framework that organizes fusion around three complementary roles: suppressing redundant cross-modal overlap, preserving modality-unique evidence, and composing task-conditioned synergy through cross-modal interaction. Specifically, stable matrix-exponential projections are used to reduce interference among shared and modality-unique streams, while task memory with hard positive updates selects which synergistic interactions should be activated for the current fusion regime. Extensive experiments across six heterogeneous fusion tasks show consistent improvements over the compared methods. On FLIR, RADIANT improves downstream detection mAP@0.5 from 91.2% to 96.8%, a gain of 5.6 percentage points (6.1% relative) over GIF. RADIANT also exhibits strong direct cross-dataset transfer, with further gains from inference-time task-memory adaptation while keeping all network weights frozen. Additional ablations and sensitivity studies support the robustness of the allocation mechanism.

cs.CV · cs.MM

版本更新 · v3arXiv:2605.03327

TIDE: Token-Level Credit Assignment via Entropy-Gated Bounded Deviation

Qiaoman Zhang, Shunhua Min, Xiang He, Zhenghan Zhang, Yuting Zhang, Guangxian Li, Yunzhu Kuang, Rui Jiang 等 11 位作者

原文摘要

Reinforcement learning (RL) is central for aligning large language models (LLMs) with complex reasoning, yet the leading critic-free algorithm, Group Relative Policy Optimization (GRPO), broadcasts a single sequence-level advantage uniformly across long Chain-of-Thought (CoT) generations and constrains exploration with an unbounded Kullback-Leibler (KL) penalty, which dilutes token-level supervision and induces gradient instability and mode-seeking conservatism. We propose TIDE (Token-level Importance via Deviation and Entropy), a critic-free RL framework that reinterprets distribution deviation as a guiding signal rather than a rigid penalty. TIDE replaces the volatile reverse KL divergence with the bounded Hellinger distance, safely quantifying token-level exploration without risk of gradient explosion. To separate genuine reasoning breakthroughs from confident hallucinations, an entropy gating mechanism scales this deviation by the policy's predictive uncertainty, and the gated scores redistribute the sequence-level advantage across tokens. The resulting updates amplify exploratory steps while suppressing low-entropy deviations, without a value network and with negligible overhead. Across in-domain, held-out, and out-of-domain benchmarks, TIDE outperforms strong critic-free baselines: on the Qwen2.5-32B backbone it reaches 60.0% and 46.0% Avg@32 accuracy on AIME 2024 and AIME 2025, respectively, above competitive baselines such as DAPO. Token-level attribution, causal perturbation, and exploration analyses further support the interpretation that the entropy-gated deviation identifies pivotal reasoning steps rather than merely perturbing optimization dynamics.

cs.LG · cs.AI

新论文 · v1arXiv:2611.15538

Faithful in Steps: Improving Generalization and Citation in RAG via Query Decomposition

Yue Liu, Zhongying Ru, Shimin Di, Jipeng Zhang, Ruiyuan Zhang, Xiaofang Zhou

原文摘要

Retrieval-augment generation is a prevalent strategy to mitigate hallucinations of LLMs. The attributable RAG (RAGQ) generates quotes for its answers. The quotes indicate which input contexts support the RAG to derive the answers, enhancing the answer's verifiability and trustworthiness. However, existing RAGQs exhibit significant degradation when dealing with questions that require multi-hop reasoning and multi-modal understanding, suffering from over-citation, implicit entity identification failure, and poor generalization. In this paper, we propose a novel RAGQ framework, namely QDRAG. QDRAG breaks down the input question into atomic subquestions to identify the implicit entities. Then, the reranker prunes context distractors to eliminate the downstream over-citation. To facilitate query decomposition, we propose two zero-shot approaches: QD-C and QD-R, which guide the QD MLLM to decompose the question based on context knowledge and retrieval rewards, respectively. One interesting finding is that finetuning on the QD task shows better generalizability compared to directly finetuning on the downstream RAGQ task. Experiments on four multi-modal QA benchmarks demonstrate QDRAG's efficacy in grounding answers and generating faithful citations. The framework significantly outperforms all the baselines on both in-domain and out-of-domain tests, even surpassing Gemini-Pro.

cs.CL · cs.AI

新论文 · v1arXiv:2611.15491

What Makes a VLA Reactive? A Study of Execution Strategies for Dynamic Manipulation

Zhuoyue Li, Zhendong Han, Pankhuri Vanjani, Wenting Li, Rudolf Lioutikov

原文摘要

Vision-language-action (VLA) models predict chunks of future actions, and when objects move, those chunks go stale before they are executed. We study what makes a pretrained VLA reactive, using \pihalf{} on two dynamic simulation benchmarks and three real-robot tasks. We vary the prediction and execution horizons, compare synchronous and asynchronous inference, test methods that deliver actions sooner or keep successive chunks continuous, and adapt the policy with motion cues and latent-space reinforcement learning. The best prediction horizon is about one second, and the best execution horizon depends on the checkpoint. Short horizons help more with asynchronous execution, and methods that keep the trajectory continuous outperform those that only reduce latency. Adapting the policy repairs targeted failures, but on the conveyor task changing the execution horizon gained as much. Reactivity depends on the execution pipeline as much as on the policy, so both should be evaluated together.

cs.RO · cs.CV · cs.LG

版本更新 · v2arXiv:2611.12169

Transactional Data Change for Real-Time Analytics in Lakehouses

Dongyang Geng, Haoqiong Bian, Zinuo Li, Haoyue Li

原文摘要

Real-time data analytics has become a key demand for lakehouses. It requires propagating data changes from the data source to the lakehouse in real time, while ensuring ACID guarantees and minimizing resource consumption and impact on analytical query performance. This is highly challenging for a data system according to the RUM conjecture, especially given the read-optimized immutable file storage layer in lakehouses. Existing lakehouses offer only git-style catalog version control on a single table, and they trade data freshness, query performance, and/or resource efficiency to achieve a barely acceptable data-change throughput. In this paper, we propose a novel data synchronization framework, Retina, that enables real-time, cost-efficient, query-performant, and fully transactional data changes in lakehouses. We implement and open-source Retina. Evaluations show that Retina delivers 10-millisecond-level data freshness and over 3.2 million row/s linear-scalable data-change throughput with low resource consumption and query-performance overhead, significantly outperforming state-of-the-art lakehouse systems and lake-compatible HTAP databases.

cs.DB · cs.AI · cs.DC · cs.PF

新论文 · v1arXiv:2611.13945

Chem World: A Large-Scale Benchmark and Physics-Aware Framework for Trustworthy Molecular Property Prediction

Tianyou Bai, Huan Wang, Mingchen Gao, Tongrui Yang, Fangyue Lin, Pinze Ren, Zhenlin Zhao, Siming Dong

原文摘要

Molecular property prediction is fundamental to computational chemistry and drug formulation research, yet existing benchmarks remain fragmented across datasets, properties, and evaluation protocols, limiting systematic evaluation of model generalization. We introduce Chem World, a large-scale benchmark integrating 17 public datasets with over 800,000 molecular and chemical-system instances across 10 property tracks, covering single-molecule and multi-component systems, including drug solubility. Chem World provides a unified testbed for evaluating molecular representations and compositional modeling across diverse chemical properties. Building on the benchmark, we propose PACM (Physics-Aware Compositional Modeling), which combines molecular representations with composition-aware modeling and domain-specific physical constraints. Extensive experiments show that molecular language models provide strong and transferable representations, while PACM consistently improves prediction across diverse chemical systems. Chem World and our PACM-powered drug-property prediction Agent support generalizable chemical modeling and offer a foundation for AI-assisted biomedical research and drug formulation development.

cs.LG · cs.AI

新论文 · v1arXiv:2611.12557

WanderBench: Can World Models Explore Dynamic Worlds from Video?

Yuhang Chen, Jiheng Li, Jiale Wang, Zai Wang, Guangyue Liu

原文摘要

Video world models conditioned on an input video make it possible to explore real, recorded dynamic scenes, enabling re-shooting of footage, free-viewpoint replay, and real-to-sim environments for embodied agents. Such uses require the generated rollout to stay faithful to the recorded world, yet existing benchmarks start from a single image or a text prompt, and video-conditioned generation is evaluated mainly on perceptual quality and camera following. These evaluations do not directly assess whether exploration preserves subject identity, event progression, and scene consistency upon revisiting a location. We introduce WanderBench, a benchmark for exploring dynamic worlds from video. It comprises 745 single-shot source videos of real and AI-generated content in three difficulty tiers (3-25 s), paired with camera routes given as keyboard actions, and evaluates six dimensions with 24 human-validated sub-metrics. Benchmarking eight models, we find that as clips grow longer, models keep the static scene and visual quality but lose camera control and the source dynamics, and that none keeps revisited places consistent. We further propose WanderLand, a training-free framework that conditions each frame of a frozen model on the same-instant source and, on revisits, on its own earlier static content. WanderLand improves five models on every dimension, by up to 8.3 points in source-dynamics fidelity.

cs.CV · cs.AI

版本更新 · v2arXiv:2608.06875

QCORE: A Quantum-Computing-Oriented,Resource-Efficient Runtime Architecture with Lifecycle Coordination

Heyue Li, Shaolin Xiang, Tian Tian, Qichun Liu, Tiefu Li, Zhihua Wang, Yanshu Guo, Hanjun Jiang

原文摘要

As quantum processors scale, online calibration, quantum error correction (QEC), and measurement-driven feedback require continuous classical processing and parameter updates. Sharing on-chip resources reduces hardware cost, but computation completion, the last parameter read, and result consumption occur at different times. Their dependencies must be managed separately while preserving quantum operations' real-time requirements. We present QCORE, a quantum-computing-oriented, resource-efficient runtime architecture that coordinates these lifecycles for safe resource reuse and parameter consistency. QCORE models resource occupancy, parameter protection, and consumer dependencies as independent lifecycles and provides three mechanisms: pre-use checks and parameter binding to verify timing, identity, and dependencies; access-aware protection through value snapshots, version references, or active-configuration windows; and joint admission of resource reservations and parameter installation. After request submission, hardware autonomously handles admission, protection, installation, and reclamation, reducing fine-grained Host coordination and providing a foundation for one Host to manage multiple controllers. We implement synthesizable RTL and validate FPGA timing at 100 MHz. Independent release reduces whole-program execution time by 16.83% in Ramsey calibration and QEC replay. Joint admission increases on-time completions from 5/15 to 15/15 under contention across five arrival phases. Under identical external deadlines, a shared NN backend reduces LUT usage by 12.28%-13.81% and DSP usage by 39.39% compared with two statically assigned backends. These results show that lifecycle coordination exploits inter-task timing slack for on-chip sharing, increasing service capacity under limited resources.

quant-ph · cs.AR

版本更新 · v2arXiv:2610.04273

Integrated Imputation-Classification for Supervised Learning with Missing Data

Yue Liu, Ben Liang, Ali Tizghadam, Ilijc Albanese

原文摘要

We study supervised classification problems with missing feature values. Existing approaches often decouple imputation from classification, producing imputations that may be plausible but uninformative for prediction. Instead, we propose the Integrated Imputation and Classification Network (IICN), which jointly trains an imputer and an ${(n{+}1)}$-class discriminator adversarially with a single class-supervised objective, where the discriminator learns to distinguish among the $n$ true classes and an additional ``imputed'' class. We prove that it admits a global optimum where the imputer and discriminator together implement marginalization over missing coordinates and yield a Bayes-optimal classifier. We evaluate IICN on FashionMNIST, CIFAR-10, and tabular datasets with naturally occurring missingness. IICN outperforms classical impute-then-classify pipelines and recent generative baselines, showing strong robustness and accuracy in challenging settings.

cs.LG

新论文 · v1arXiv:2611.13001

One Table, Many Queries: Benchmarking Generalist Tabular Models Across Generation, Imputation, and Prediction

Yuanrui Wang, Kaifang Li, Xuanyue Li, Ziyun Li, Yan Lu, Xingxuan Zhang, Peng Cui

原文摘要

Generation, imputation, and prediction query different aspects of the same tabular distribution, but are usually evaluated separately. This leaves unclear which capabilities they share, how their training objectives interact, and whether one model can perform all three well. We introduce the One Table Benchmark (\ours{}), spanning 56 datasets, 46 registered methods, and 20 capability axes under aligned data splits and explicit task contracts. We compare task ranks on aligned support, train five backbones under all seven non-empty objective combinations on five datasets with three seeds, and contrast fixed-model profiles with specialist portfolios. Rank comparisons connect imputation and prediction through numerical recovery and dependence preservation, and link generation to both through predictive utility; distributional fidelity follows different, sometimes opposing, rankings. Objective interventions show the largest pooled gains from including the recipient's own objective. Generation has the broadest coverage of positive pooled auxiliary effects, while prediction shows potential to improve imputation and synthetic-data utility, with responses that vary across backbones. Cross-addition effects reveal that objective benefits need not add and depend on the objectives already present. Fixed-model comparisons expose corresponding utility--fidelity trade-offs: some generalists surpass specialist portfolios on utility, while fidelity continues to favor specialization. Frozen foundation models show strong prediction and numerical point imputation, together with promising synthetic-data utility, highlighting their potential across all three tasks. These findings motivate unified tabular models that share useful conditional information while improving categorical reconstruction and faithful joint sampling.

cs.LG

版本更新 · v2arXiv:2605.06978

Group of Skills: Group-Structured Skill Retrieval for Agent Skill Libraries

Kun Zeng, Yu Huo, Siyu Zhang, Haoyue Liu, Yuecheng Zhuo, Zi Ye, Yuquan Lu, Junhao Wen 等 9 位作者

原文摘要

Skill-augmented agents increasingly rely on large reusable skill libraries, but retrieving relevant skills is not the same as presenting usable context. Existing methods typically return atomic skills or dependency-aware bundles whose internal roles remain implicit, leaving the agent to infer the execution entry point, support skills, visible requirements, and failure-avoidance guidance. We introduce Group of Skills (GoSkills), an inference-time group-structured retrieval method that changes the agent-facing retrieval object from a flat skill list to a compact, role-labeled execution context. GoSkills builds anchor-centered skill groups from a typed skill graph, expands support groups through a group graph, bottlenecks the selected group plan into a bounded set of atomic skill payloads, and renders a fixed execution contract with Start, Support, Check, and Avoid fields, without changing the downstream agent, skill payloads, or execution environment. Across SkillsBench, ALFWorld, and Terminal-Bench 2 with six backbones, GoSkills attains the highest mean reward or accuracy among the evaluated methods in every benchmark-backbone setting, and matched controls show higher reward and fewer agent turns with group selection than with fixed-contract or post-hoc role-annotation alternatives.

cs.CL · cs.AI

新论文 · v1arXiv:2611.10715

From User Behaviors to Satisfaction Judgments: Reasoning about User Satisfaction with AI Overviews

Xingzhu Wang, Yitong Xu, Yue Li, Daiting Shi, Jingzhou He, Jiaxin Mao

原文摘要

The growing presence of AI overviews in everyday search makes their effective evaluation essential. Response quality has been the primary focus of existing evaluation research, with only a small number of studies examining the user perspective. These evaluations rely on queries and response content, leaving the information conveyed by user behavior insufficiently utilized. This work investigates satisfaction prediction for AI overviews from a user-centered perspective and incorporates behavioral signals into the prediction process. Applying existing behavior-based satisfaction prediction methods from traditional information retrieval to this setting, however, presents limitations. We address these limitations with STaRS, an LLM-based approach designed specifically for predicting satisfaction with AI overviews. At its core is a structured reasoning procedure: individual behavioral signals are interpreted first, and their implications then inform the prediction of user satisfaction. Reinforcement learning further optimizes this procedure, while a reward shaping mechanism alleviates reward sparsity during training. Evaluation on two real-world datasets demonstrates that STaRS outperforms the comparison methods in satisfaction prediction, providing search providers with a practical means of accurately estimating users' satisfaction with AI overviews.

cs.IR

新论文 · v1arXiv:2611.10562

ZARA: Zero-shot Animatable and Relightable 3D Avatar reconstruction from a single image

Yixiao Chen, Dongdong Weng, Chengfeng Zhao, Tao Gong, Zhihe Zhao, Zhe Zhu, Yue Liu, Yuan Liu

原文摘要

Recent large human reconstruction models create remarkable animatable 3D avatars from a single image, but their appearance remains entangled with the illumination and cannot be relighted. In contrast, existing 3D relightable-avatar reconstruction methods typically require person-specific optimization. We present ZARA, a zero-shot feed-forward framework that reconstructs an animatable 3D Gaussian avatar together with its intrinsic attributes from a single image. ZARA couples a pretrained large-scale human reconstruction model with a Material Transformer to inherit geometry priors while learning material-aware Gaussian representations. To preserve localized details, we introduce Gaussian-aligned material feature fusion strategy, which injects multi-scale material features onto individual Gaussians and combines them with geometry tokens. As most human-avatar datasets lack ground-truth material maps, we use pseudo-material labels as conditioning inputs and supervision targets during training. We further introduce MatFace regularization to preserve facial structure and color in albedo prediction under unreliable facial pseudo-material supervision. Extensive experiments demonstrate that ZARA reconstructs animatable and relightable humans within tens of seconds without person-specific optimization or post-processing, outperforming existing baselines in both relighting quality and materials generalization ability. As the ability of recovering the physically-based-rendering attributes of the human, ZARA also enables direct material editing of the avatar's appearance.

cs.CV

新论文 · v1arXiv:2611.10234

ScreenProof: Where Is This Screen Wrong? Finding UI Faults Without a Reference

Huiming Sun, Yue Li, Kangning Yang, Ruineng Li, Jie Cai, Lan Fu, Yunwan Fu, Jinlong Li 等 9 位作者

原文摘要

A phone screen can be wrong in ways that need no reference: a label that runs off the screen, letters that touch, a line that breaks one character before its end, one button with sharp corners among round ones. We ask whether a model can box every such fault on a screenshot, given no target design and no reference image. Such a critic could serve as a cheap first pass over generated pages before a designer reviews them, but only if it stays silent on clean pages. ScreenProof poses this target-free critique over three families of faults: general faults, local style faults (one element breaks the style its page sets) and text layout faults (letter spacing, line height, line breaks). A data engine makes each fault in page code and records the changed element's box, and hard negatives change every sibling alike. No frontier judge is reliable: frontier models flag 18-62% of clean real screenshots and 18-82% of clean generated pages, find 47-72% of text layout faults, and rarely find a foreign icon (5-19%). Our small critic ProofJudge (Qwen3.5-9B with LoRA), trained on code-made pages with one to four faults each and keeping a finding only when it is confident, reaches F1 0.48, the highest of all judges (Gemini 4 Argon 0.37; open models at most 0.15; 0.46 even without the confidence cut), and is the only fault-finding judge within 15% false alarms on clean pages (2% real, 9% generated), the property such a first pass needs, at about a hundredth of Argon's cost. It finds the most general faults (59%) but fewer local style faults than Argon (25% against 41%) and fewer text layout faults than the API judges (43%; Gemini 4 Argon 47%). Against a named brand the task is harder still: models know a design language about as well as its public documentation states it.

cs.AI · cs.SE

新论文 · v1arXiv:2611.09678

Calibrating demand models versus adjusting OD matrices with traffic counts: a controlled comparison

Yue Li, Shujuan Chen, Ying Jin

原文摘要

Traffic counts are routinely used to calibrate travel demand models, particularly when the origin-destination (OD) matrix is not observed directly. An important modelling decision is whether to adjust individual OD flows or the parameters of the demand model that generates them. The latter approach uses fewer parameters and preserves a relationship between zonal characteristics and demand, but its accuracy depends on the assumed model structure. We compare three established approaches using the same prior information, traffic counts and equilibrium assignment. They estimate five production-gravity coefficients, origin and destination adjustment factors, or individual OD flows. Synthetic experiments on the Eastern Massachusetts and Chicago Sketch networks allow recovery to be assessed against known demand under different forms of model misspecification. Calibrating the five-coefficient model gives better OD recovery and held-out link-flow prediction when demand follows its assumptions or a two-purpose gravity process. Its advantage declines or reverses when destination choice or production relationships vary across zones. Cellwise adjustment achieves the closest fit to calibration counts in 65 of 66 evaluated conditions, yet it recovers OD demand least accurately of the three approaches in 45 of them. These findings show that model parameterisation matters beyond calibration fit. For transport planning, traffic counts should be used alongside independent evidence on trip production and distribution when selecting and validating a demand model.

cs.CE · stat.ME

版本更新 · v2arXiv:2610.07062

Learning to Simulate Individuals from Macro Social Signals

Yining Zhao, Bushi Liu, Haofei Yu, Zhengyang Qi, Shanyong Wang, Chuyue Li, Yuxiang Liu, Jiaxuan You

原文摘要

Large language models are increasingly used to simulate how individuals respond to new situations, yet the behavioral reasoning behind these responses is either inherited from pretraining or learned from individual-level annotations, which offer limited behavioral diversity and little supervision of the reasoning itself. We propose to learn behavioral reasoning from prediction markets, whose price trajectories record how populations respond to real-world events at scale. We introduce macro2mind, which trains a language model with GRPO using market signals. A social behavioral decomposition makes behavioral reasoning an explicit step of forecasting: the model infers representative groups of market participants, predicts how each interprets the news and updates its beliefs, reasons about their interactions, and aggregates these responses into a price. A hindsight-regret curriculum with difficulty-aware sampling focuses training on transitions where hindsight-identified groups substantially improve the forecast while prioritizing examples that remain learnable for the current policy. The learned reasoning applies to user simulation without further training. On SWM-Bench, macro2mind achieves state-of-the-art directional accuracy and correlation on Polymarket. Trained on market data, it transfers zero-shot to four user-simulation benchmarks (Humanual, OvertonBench, PRISM, and CAD) and has competitive performance among zero-shot methods. Used as a data generator, macro2mind also raises a downstream simulator's accuracy on unseen users by 15.5 points, outperforming data generated by its backbone by 13.2 points.

cs.LG · cs.AI · cs.CL · cs.SI

版本更新 · v3arXiv:2608.22788

TailSieve: Partial-Rollout-Guided Tail Routing for LLM Rollouts

Tianqi Xu, Lu Lv, Haoyang Huang, Wenjie Huang, Zhanming Shen, Yuhao Shen, Baolin Zhang, Xinyi Hu 等 18 位作者

原文摘要

Large-scale rollouts have become a core component of modern LLM systems, spanning reinforcement learning (RL) post-training, on-policy distillation, and sampling-heavy evaluation. Unlike online serving, which typically targets request-level latency and throughput, synchronous rollouts must collect a complete batch before proceeding. A few long-tail generations can therefore dominate an entire rollout step, and uniform routing can slow these generations further by placing them in high-concurrency decoding batches. We present TailSieve, a partial-rollout-guided framework that jointly controls tail routing and replica allocation. Motivated by the observed persistence of prompt-level tail tendencies across policy updates, TailSieve uses partial-rollout completion status as a training-free signal for identifying candidate tail groups. Selected prompts are combined with newly sampled prompts, and all responses are generated from scratch under the current policy. A hierarchical controller uses response-work history and a serving model: a fast inner loop adjusts the number of isolated groups to balance completion times, while a slower outer loop adapts how many replicas serve these groups. The resulting low-concurrency execution also enables route-specialized speculative decoding with MTP or DFlash. Across the evaluated configurations, TailSieve achieves up to $1.67\times$ speedup with routing alone and $2.59\times$ with routing and speculation combined, both over uniform group routing.

cs.AI · cs.LG

新论文 · v1arXiv:2611.09045

When to Trust the BIM: Identifiability-Aware LiDAR-Inertial--BIM Fusion under As-Built Deviations

Yujie Zhang, Yuxuan Guo, Xinbao Sun, Chunlei Zhao, Langqi Miao, Xiaohui Jia, Jinyue Liu

原文摘要

Building information models (BIM) can provide a global geometric reference for robot localization with LiDAR-inertial odometry (LIO). However, as-built deviations from the as-designed model mean that a disagreement between a scan and the BIM may arise from a pose error, an offset wall surface (an as-built deviation or an unmodeled object in front of the wall), or a shifted room, and in some geometries these explanations produce identical observations. In this paper, we formalize this attribution problem as fault identification over three fault classes and derive a geometric criterion for when attribution is possible. Building on it, we propose an identifiability-aware method that reports an attribution only when the fault is attributable; otherwise, it retains the candidates, defers BIM updates and BIM-based pose corrections in the ambiguous directions, and recovers once new references arrive. In the pre-registered two-dimensional study, on cases whose fault is detectable but not attributable, the method's conditional error rate was 0.83%, against 31.67% for a baseline with uncertainty-based abstention at the same answer rate. On the 5,600 attributable cases, the method reported a unique attribution 5,574 times, with no incorrect attributions. In paired fault injections in a laboratory room with its IFC model and on three floors of the SLABIM dataset, it raised no off-target attribution (0 of 168 conditions in the laboratory; 0 of 1,302 on SLABIM) and attributed all eight laboratory faults predicted to be attributable, whereas both reproduced baselines raised off-target structural flags in every setting.

cs.RO

新论文 · v1arXiv:2611.09013

KnowEvo: Knowledge Evolution for Protein Optimization

Zijie Xing, Xingyue Liu, Runze Wang, Luoming Hu, Yanming Shen

原文摘要

Large language models (LLMs) have shown promise in scientific discovery, yet systematically accumulating and refining reusable scientific knowledge remains challenging. Existing approaches primarily improve LLM-based problem solving through parameter optimization or feedback-driven refinement of prompts, programs, and solution trajectories, leaving acquired expertise either embedded in model weights or scattered across iterative problem-solving processes. As a result,knowledge is difficult to systematically inspect, evaluate, and refine. We propose KnowEvo, a framework that treats externalized knowledge itself as the optimization target. Our key insight is that scientific knowledge is inherently modular: multiple interacting mechanisms jointly determine the design outcomes. This makes knowledge evolution fundamentally challenging, as improvements cannot be attributed to individual components in isolation. To address this, KnowEvo represents knowledge as executable expertise blocks and organizes their refinements into strategy mutation trees, enabling structured exploration over a combinatorial knowledge space. The framework combines a Thompson-style forward allocation strategy that adaptively distributes evaluation budgets across strategy variants with a backward revision process, in which a code agent operates in an isolated sandbox to translate rollout evidence into localized program updates. This design enables persistent accumulation, evaluation, and refinement of mechanistic expertise across iterative experimentation. We evaluate KnowEvo on protein optimization tasks including stability and solubility. Results show that knowledge evolution consistently improves over initial strategy blocks and outperforms monolithic program evolution and prior LLM-guided evolution baselines across metrics such as pass@k, MRR, MAP,and NDCG@5. Code is available at https://github.com/recynie/KnowEvo.

cs.LG

新论文 · v1arXiv:2611.08157

通过上下文正则化交叉熵提升卷积网络的上下文偏移鲁棒性

Improving Context-Shift Robustness of Convolutional Networks via Context-Regularized Cross-Entropy

Jinen Setpal, Chaoyue Liu

AI 速读 基于摘要

作者提出基于空间特征归因的 ContrastiveCAMs 与 Context-Regularized Cross-Entropy(CR-CE),引导卷积网络减少对上下文区域的依赖,以提升上下文偏移下的鲁棒性。

cs.CV · cs.LG

查看原文摘要

Image classification models often encounter objects in diverse and unpredictable contexts at test time, which may differ substantially from those seen during training. This phenomenon, termed context shift, exposes a key fragility in neural networks: when models rely on non-causal contextual cues for prediction, shifts in context can lead to significant performance degradation. In this paper, we propose a novel training framework to improve the robustness of convolutional neural networks under context shift. Our approach leverages spatial feature attribution to guide models toward making predictions that rely less on contextual regions and more on object-relevant features. As a first step, recognizing a theoretical limitation of existing feature attribution methods we introduce a new variant, ContrastiveCAMs, which produces more faithful attribution maps of model predictions. Building on ContrastiveCAMs, we further propose Context-Regularized Cross-Entropy (CR-CE), a modification of the standard cross-entropy loss that regularizes the model's attention by suppressing the influence of contextual regions, thereby improving robustness to context shift. We evaluate the effectiveness of our approach on several medium-to-large scale datasets (Waterbirds, Spawrious, ImageNet/ImageNet-BG, Hard-ImageNet), and report consistent improvements in context-shift robustness.

版本更新 · v3arXiv:2609.15545

The Token Before the Value Is the Key

Ke Cheng, Xin Xu, Zhichao Chen, Yixiao Chen, Lei Xin, Jianbo Zhao, Fanhu Zeng, Yue Liu 等 10 位作者

原文摘要

Induction circuits retrieve a value by matching a query to information carried from the token before that value. How this address forms, incorporates context, and supports sequential retrieval remains less clear. We use hybrid language models as a tractable testbed and identify the historical source key as a common causal interface between local preparation and global retrieval. Probes and restoration interventions connect this interface across controlled models, pretrained recurrent and sliding-window hybrids, and released language models. We organize the analysis by address context radius and sequential retrieval depth. First, shared local parameters couple predecessor Carrying to recurrent state processing; separating these demands or biasing initialization promotes address formation. Second, adapting input representations extends an established literal circuit to category matching, making semantically compatible records active competitors. Earlier context resolves this competition through the source key, with a sharp visibility boundary in a controlled single-read model and compositional relays across local layers. Third, fixed relations support memorization shortcuts, whereas sequential generalization requires learning an output-to-query bridge between retrievals. Controlled state-tracking and compositional in-context tasks demonstrate this requirement across stacked stages, looped recurrence, and intermediate-token generation. Together, these results connect circuit formation, contextual disambiguation, and sequential use through a shared retrieval interface. Code is available at https://github.com/ckpassenger/bind-match-copy.

cs.LG

版本更新 · v6arXiv:2603.20957

Alignment Whack-a-Mole : Finetuning Activates Verbatim Recall of Copyrighted Books in Large Language Models

Xinyue Liu, Niloofar Mireshghallah, Jane C. Ginsburg, Tuhin Chakrabarty

原文摘要

Frontier LLM companies have repeatedly assured courts and regulators that their models do not store copies of training data. They further rely on safety alignment strategies via RLHF, system prompts, and output filters to block verbatim regurgitation of copyrighted works, and have cited the efficacy of these measures in their legal defenses against copyright infringement claims. We show that finetuning bypasses these protections: by training models to expand plot summaries into full text, a task naturally suited for commercial writing assistants, we cause GPT-4o, Gemini-2.5-Pro, and DeepSeek-V3.1 to reproduce up to 85-90\% of held-out copyrighted books, with single verbatim spans exceeding 460 words, using only semantic descriptions as prompts and no actual book text. This extraction generalizes across authors: finetuning exclusively on Haruki Murakami's novels unlocks verbatim recall of copyrighted books from over 30 unrelated authors. The effect is not specific to any training author or corpus: random author pairs and public-domain finetuning data produce comparable extraction, while finetuning on synthetic text yields far little extraction, indicating that finetuning on individual authors' works reactivates latent memorization from pretraining. Three models from different providers memorize the same books in the same regions ($r \ge 0.90$), pointing to an industry-wide vulnerability. Our findings offer compelling evidence that model weights store copies of copyrighted works and that the security failures that manifest after finetuning on individual authors' works undermine a key premise of recent fair use rulings, where courts have conditioned favorable outcomes on the adequacy of measures preventing reproduction of protected expression.

cs.CL · cs.AI · cs.CY

版本更新 · v3arXiv:2512.12084

FloodSQL-Bench: A Retrieval-Augmented Benchmark for Geospatially-Grounded Text-to-SQL

Hanzhou Liu, Kai Yin, Zhitong Chen, Chenyue Liu, Ali Mostafavi

原文摘要

Existing Text-to-SQL benchmarks primarily focus on single-table queries or limited joins in general-purpose domains, and thus fail to reflect the complexity of domain-specific, multi-table and geospatial reasoning, To address this limitation, we introduce FLOODSQL-BENCH, a geospatially grounded benchmark for the flood management domain that integrates heterogeneous datasets through key-based, spatial, and hybrid joins. The benchmark captures realistic flood-related information needs by combining social, infrastructural, and hazard data layers. We systematically evaluate recent large language models with the same retrieval-augmented generation settings and measure their performance across difficulty tiers. By providing a unified, open benchmark grounded in real-world disaster management data, FLOODSQL-BENCH establishes a practical testbed for advancing Text-to-SQL research in high-stakes application domains.

cs.IR

版本更新 · v2arXiv:2609.32991

数据应该教什么?跨越电路、存储与使用的瓶颈迁移

What Should Data Teach? Moving Bottlenecks Across Circuit, Store, and Use

Yixiao Chen, Ke Cheng, Yue Liu, Jun Zhang, Jie Jiang

AI 速读 基于摘要

作者提出一种“电路视角”的数据诊断原则,将语言模型训练中的瓶颈分为计算形成、内容可用与路径选择三类,并报告相应数据干预在350M模型实验中的效果。

cs.LG

查看原文摘要

What should data teach a language model at a particular point in training? A circuit view reveals three distinct bottlenecks: forming a computation, making its required content available, and selecting among available routes. A shared diagnosis-to-data principle connects them: localize the missing operation, preserve its causal relation, vary shortcut-bearing context, and re-audit the residual. Formation-sensitive selection and prerequisite ordering accelerate a binding-matching-transport path; a brief early prefix from the same training multiset retains a validation advantage through 100B tokens. Availability counterfactuals then distinguish writing content from invoking available memory, while paired supervision and context-opportunity ranking improve matched route decisions and long-context answer likelihood. A continuous 350M-model experiment connects the three interventions on the same facts: early circuit training improves subsequent learning, and the complete sequence outperforms stage-replacement controls on facts withheld from Use teaching. Independent query surfaces and opposed-source decisions expose conditional arbitration as the remaining frontier. Together, these results show why a change in the limiting operation calls for a change in supervision, not merely a new ranking of difficult examples.

版本更新 · v4arXiv:2610.15884

RetryBench: Separating Retry Permission from Recovery Outcomes in GPT Tool Use

You Liu, Yue Liu, Quanchao Lu

原文摘要

LLM agents that call external tools must decide what to do when a tool call times out: retrying risks duplicate side effects, while not retrying can leave the task incomplete. We present RetryBench, an evaluation protocol for retry decisions and failure recovery in tool-using LLM agents. Each decision is scored on retry permission (is the retry justified by an idempotency-key guarantee or proof of non-execution?), settled effects (duplicates and omissions), and completion, by replaying it across all hidden execution worlds consistent with the observation. On four synthetic software-engineering tasks, we run two controlled prompt-sensitivity studies (1,728 decisions). Study 1 (idempotency-key descriptions): with the contract fixed, GPT-5.6 Luna reuses the valid idempotency key in 10/40 decisions when an extra key is described as a "Candidate recovery key" but in 39/40 when it is an "Alternative key string"; across three further phrasings per family the gap is 27/120 versus 113/120. GPT-5.6 Sol and Terra are at ceiling (40/40). Study 2 (action order): under underspecified lookup guarantees, retry rates are 17-27 points lower for GPT-5.6 Terra and GPT-5.4 when retry is listed first (option-order bias), mainly on two tasks; we make no claim about which behavior is better. Findings are limited to researcher-chosen phrasings, four tasks and unpinned model aliases. Code and all model responses are released.

cs.AI · cs.CR

新论文 · v1arXiv:2611.05667

Correct Robots Before They Make Mistakes: Proactive Human-in-the-Loop Intervention via Preference Learning

Xinkai Jiang, Jing Jiang, Hongyi Zhou, Pankhuri Vanjani, Ahmad Baki, Jakub Suliga, Ge Li, Zhuoyue Li 等 10 位作者

原文摘要

This paper presents Proactive Human-in-the-Loop (PHIL), a framework for proactive policy correction and preference-based post-training. PHIL enables operators to preview policy-predicted future motion and intervene before anticipated undesirable actions. During takeover, PHIL continues querying the policy and displaying its predicted trajectories in the physical workspace through an extended reality (XR) interface. PHIL pairs rejected policy predictions with corrective action chunks subsequently executed from the same physical state over the same horizon, and preference-based post-training encourages the policy to favor these corrections. This paper evaluates PHIL on four real-world manipulation tasks using a diffusion policy and a pretrained vision-language-action policy. With five correction episodes per condition, PHIL increases mean success rates across the evaluated tasks and demonstration budgets from 44.0% to 70.3% for the diffusion policy and from 57.8% to 76.9% for X-VLA, compared with HG-DAgger. Separately, policies trained with proactive corrections show fewer unnecessary recovery behaviors in successful episodes. Project page: https://intuitive-robots.github.io/PHIL-page/.

cs.RO