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

+1295新增论文
+1026其中 AI 相关
+111已有论文修订
+95新增 AI 导读

arXiv 最近完成扫描:2026-11-17 04:58 · 全站最近入库:2026-11-17 16:10各信源进度 →

统计口径与数据新鲜度

统计 2026-11-16 16:49 — 2026-11-17 16:49(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:2026-11-17 04:58最近发现新增版本:2026-11-17 16:10库内论文最新更新时间:2026-11-17 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。

25,122 已收录论文20,967 AI 相关7,309 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 4,484 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-17 04:57(北京时间)
新论文 · v1arXiv:2611.21608

Latent Lattice Language Models

Shivam Duggal, Zongze Wu, William T. Freeman, Antonio Torralba, Richard Zhang, Eli Shechtman

原文摘要

Language models typically increase per-token computation through deeper or looped layers and latent reasoning steps, while richer residual connections improve information flow across layers. We instead increase computational capacity: the number of active computational states a model maintains. We introduce the Lattice of Latents, a set of per-layer horizontal latent streams that run recurrently along time, alongside the vertical residual stream that flows through depth. Like hyper-connections, mHC, and attention or value residuals, the Lattice enhances the residual stream, but rather than adding or rerouting residual pathways through depth, it provides companion computational states that persist across tokens. Unlike hybrid Transformer-SSM architectures, whose recurrent states primarily serve as internal memory for sequence mixing, these latents directly condition the vertical stream's attention, KV-cache writes, MLP computation, and decoding. On Transformers trained on 20B FineWeb-Edu tokens, a 406M-parameter Lattice model lowers validation perplexity from 15.41 to 14.40 over a parameter-matched Transformer. These gains extend across architectural variants. The Lattice composes with prior residual-stream enhancements: with hyper-connections and input residuals, it lowers validation perplexity from 15.41 (base Transformer) and 14.22 (Transformer with the same enhancements) to 13.61. On Gated DeltaNet, Mamba-2, Triadic GDN, and GDN-Mamba-2 hybrids, it improves perplexity at every tested native state size, with Lattice-GDN and Lattice-Triadic-GDN variants outperforming pure baselines with 4x larger native states. These results identify persistent per-layer state as a complementary axis for scaling language-model computation.

cs.LG · cs.AI · cs.CL

新论文 · v1arXiv:2611.21607

ScaleVLA: Scaling Vision-Language-Action Models to 552 Billion Parameters

Ruixi Yu, Dairu Liu, Xuchuan Chen, Zekun Qi, Zekai Li, Zhuo Cao, Luyang Niu, Yingsheng Zhang 等 12 位作者

原文摘要

Frontier Vision-Language Models (VLMs) such as GPT-6 Astra have demonstrated remarkable capabilities in robot control, suggesting that broad pretraining provides knowledge valuable for physical action. Yet most Vision-Language-Action (VLA) policies still rely on much smaller VLM backbones, leaving this potential largely untapped. We ask whether frontier-scale representations can provide a stronger foundation for robot learning. We introduce ScaleVLA, which connects a 552B DeepSeek-V4.1-Flash backbone to a trainable action DiT, and systematically compare VLMs from 2B to 552B under a shared training setup. We evaluate three fundamental capabilities of robot foundation models. In sample efficiency, just 10 demonstrations outperform a 2B backbone trained with 50 (87.8% vs. 85.6%). In generalization, LIBERO-PRO success reaches 45.1%, compared with at most 31.3% for smaller backbones. In precise manipulation, real-world charger insertion improves from 4/10 to 9/10 successes, with gains concentrated in contact-sensitive alignment. Despite its scale, ScaleVLA achieves 216 ms median latency per action chunk. Our findings suggest that frontier VLMs can serve not only as reasoning agents, but also as powerful representational foundations for efficient and generalizable robot policies.

cs.RO

新论文 · v1arXiv:2611.21604

FaceJev: Direct Visual Decisions for Face Forgery Detection

Siran Peng, Tianshuo Zhang, Yibo Xue, Ajian Liu, Haoyuan Zhang, Weisong Zhao, Shuhuan Chen, Xiangyu Zhu 等 9 位作者

原文摘要

Face forgery detection methods often perform well on seen manipulations but generalize poorly to unseen ones. Multimodal Large Language Models (MLLMs) can recognize facial parts and assess their visual plausibility. Existing MLLM-based methods typically express these judgments through textual explanations, but seldom treat individual part decisions as explicit learning targets. We present FaceJev, an MLLM-based method for face forgery detection through direct visual decisions. Following the Jev formulation, FaceJev answers eight independent questions about facial parts using a shared image encoding and reads anomaly probabilities from the native answer logits. A face is classified as forged if any part is predicted to be abnormal, directly linking the detection result to the part decisions. We construct PartForensics, a dataset of approximately 160k images with binary anomaly targets for the eight facial parts, to supervise these decisions. We further propose FS-GRPO, which optimizes each part decision through an exact reward comparison with its alternative, using both detection and part rewards. FaceJev outperforms the strongest baseline by 7.25 percentage points on unseen manipulations. Extensive ablation studies validate our design choices and the effectiveness of the main components.

cs.CV

新论文 · v1arXiv:2611.21596

SADL: On the Demand-Supply Geometry of Representation Collapse

Junhan Sun, Yigui Feng, Mingzhe Liu, Haoyan Xu, Lei Ye, Ziqi Han, Hanru Bai, Yanzhao Zhang 等 10 位作者

原文摘要

In Joint-Embedding Predictive Architectures (JEPAs), a well-constrained projector output does not by itself prevent representation collapse. We find that, from initialization, the encoder representation is dominated by a component shared by different inputs. A batch-normalized projector removes this component, so regularization after the projector cannot correct it, and the differences between representations shrink until they collapse. We propose SADL (Supply And Demand Loss), which keeps the original training objective and constrains the encoder directly when needed. SADL compares the representation differences that the projector output demands with the differences the encoder can retain and pass on to the projector, and adds a constraint on the encoder only when supply falls short of demand. It works with different Demand Regularizers and introduces no auxiliary networks, additional trainable parameters, or architectural changes. In single-task and jointly trained four-task LeWorldModel (LeWM) and INTACT experiments, SADL lowers the collapse rate over ten random seeds from 50% to 0%. After one epoch of training, encoder effective rank is 3.4-6.4 times that of the corresponding baseline without SADL, and latent prediction error falls to 1/20-1/303 of it. Without additional tuning, SADL stays robust as its loss weight spans orders of magnitude, and with several Demand Regularizers INTACT exceeds 95% mean search-free control success. On four image datasets, SADL also consistently improves accuracy and stability across random seeds. These results show that matching the representation differences a regularizer demands with the differences the encoder can supply leads to faster and more stable representation learning in control and image classification.

cs.RO · cs.LG

版本更新 · v2arXiv:2607.01191

Perceive-to-Reason: Decoupling Perception and Reasoning for Fine-Grained Visual Reasoning

Hongxing Li, Xiufeng Huang, Dingming Li, Wenjing Jiang, Zixuan Wang, Haolei Xu, Hanrong Zhang, Haiwen Hong 等 14 位作者

原文摘要

Fine-grained visual reasoning remains challenging for vision-language models, especially when small but critical visual cues are buried in high-resolution images. Existing approaches rely on repeated cropping or test-time visual search to introduce local evidence, but they typically do not explicitly distinguish perception from reasoning. In this paper, we propose Perceive-to-Reason (P2R), a unified framework that formulates fine-grained visual reasoning as a two-stage process: the model first localizes question-relevant evidence as a Perceiver, and then answers the question as a Reasoner based on the annotated image and cropped regions. To better align training with this decoupled formulation, we further introduce Perception-Reasoning Alternating GRPO (PRA-GRPO), a role-aware reinforcement learning strategy that alternates between perception-focused and reasoning-focused updates using only final-answer supervision. Built on top of Qwen3-VL-Instruct-2B/4B/8B, P2R consistently improves performance across model scales. In particular, P2R-4B achieves 93.2% on V-Star, 81.9% on HR-Bench-4K, and 80.5% on HR-Bench-8K, substantially outperforming its corresponding backbone. Further experiments show that the benefits of P2R extend beyond high-resolution benchmarks to broader multimodal reasoning tasks. These results suggest that explicitly decoupling perception from reasoning provides an effective framework for fine-grained visual reasoning.

cs.CV

版本更新 · v3arXiv:2611.09822

Discovering formally verified quantum programs with AI

Sergey Shirobokov, Ben Jaderberg, Katerina Hristova, George Tsoukalas, Johannes Bausch, Eric Wieser, Francisco J. H. Heras, Nicholas C. Rubin 等 25 位作者

原文摘要

The timeline by which quantum computers can solve breakthrough problems in science depends on improved quantum algorithms as much as on better hardware. Such algorithmic advances are typically achieved through many years of expert human collaboration. In mathematics and computer science, large language models have accelerated progress through automated discovery loops. However, quantum algorithms can only be evaluated by classical computers on restricted or small instances. Here we demonstrate automated discovery of quantum programs beyond these regimes including order-of-magnitude improvements on scientific applications. To achieve this, we build a quantum program library in the Lean theorem prover in which Gemini 4 agents synthesize novel programs against formal problem specifications and verify their correctness and cost. Agent teams collaborate, sharing results and knowledge through wikis and discussing ideas at organized conferences. Our results improve on prior baselines for parallel search (up to 2.57x), quantum arithmetic (290x), and simulations relevant to fusion, photochemistry and drug-metabolism by 12x, 8x and 2.5x respectively. Combining human and artificial intelligence at scale, under the rigor of mathematical proof, lets researchers design algorithms that today's classical and quantum computers cannot test, shortening the path to practical quantum computation.

quant-ph · cs.AI · cs.PL

新论文 · v1arXiv:2611.21539

Seen but Unsaid: Locating and Repairing Cross-Image Comparison in Vision-Language Models

Zhaoning Zhang

原文摘要

Vision-language models (VLMs) often fail to match a point or an object across two images, even when the answer can be decoded from their own hidden states. We trace this failure from the visual tokens to the answer letter, in Qwen3-VL (2B-32B), InternVL3.5-8B, and Gemma-3-12B, on synthetic shape matching, same-instance point correspondence (HPatches), and semantic correspondence (SPair-71k), and find two distinct failure points, a small set of attention heads that carries the comparison, and a repair that touches 0.02% of the parameters. Two failure points: exact copies are compared but not read out. An answer-position probe exceeds the calibrated output by 15 to 25 points in every family, for nameable and unnameable shapes alike, and steering along the probe's direction moves no more answers than random directions. Semantic correspondences are present in the visual tokens but never reach the answer. One pathway: redistributing the cross-image attention of 16-32 heads, with its mass preserved, removes 17-22 points of synthetic and 15-32 points of HPatches accuracy, against at most 7 for random or attention-matched heads. A lever that training finds on its own: training only these heads' query and key projections raises SPair-71k accuracy by 28.3 points (Qwen3-VL-8B) and 25.1 points (InternVL3.5-8B), beats both layer-matched and attention-matched heads, and transfers to HPatches and BLINK. An unconstrained all-layer adapter routes 21-51% of its gain through the attention of the same heads, against at most 7% for random heads, and does so by changing what they read (83-86% of the effect) rather than their weights. Every decision rule was frozen before its run, and every reported number is recomputed by independent verification scripts.

cs.CV · cs.CL · cs.LG

新论文 · v1arXiv:2611.21533

Incentive Alignment for Electricity Data Assets in China: A Blockchain-Enabled Contribution-Credit Framework

Jiazheng Zhang, Shouwei Li, Yutian Deng, Wei Wei, John Cartlidge

原文摘要

Modern electricity markets increasingly rely on reported operational contributions to allocate incentives, recognise cooperation, and coordinate activities across multiple organisations. However, supporting evidence for many reported contributions becomes available only after subsequent metering, dispatch, settlement, or auditing processes, making it difficult to reward genuine contributions while discouraging strategic over-reporting. Existing approaches largely address data sharing, performance verification, blockchain record management, or incentive allocation in isolation, providing limited support for integrating delayed evidence into a unified incentive mechanism. This paper proposes a blockchain-enabled contribution-credit framework for truthful reporting under delayed evidence. The framework links authenticated evidence to contribution recognition through dynamic credit updating, escrow, report-linked penalties, and automated incentive execution. Developed using the Chinese electricity market as the primary setting, it is demonstrated through two representative coordination scenarios, with adaptations illustrating its applicability to UK and US electricity-market structures. A controlled heterogeneous-agent simulation evaluates the behavioural effects of the proposed mechanism, while security analysis, public-data workflow analysis, and blockchain implementation experiments assess its practical feasibility. The results show that integrating delayed evidence with dynamic credit, escrow, and report-linked penalties promotes truthful reporting while providing a transparent and auditable process for translating verified operational contributions into incentive allocation. The proposed framework offers a practical mechanism for improving accountability, coordination, and incentive compatibility in collaborative electricity markets.

cs.CY · cs.DC

新论文 · v1arXiv:2611.21530

DuoFlow: Towards Synchronized Speech and Motion Generation with Fine-Grained Control

Jun Dong, Ronghui Li, Zhongyuan Hu, Yunqi Zhao, Lijie Guo, Ruizhang Xu, Di Kang, Linchao Bao 等 9 位作者

原文摘要

An embodied speaker's expressiveness depends not only on what is said, but also on how the voice sounds and how the body moves. However, existing joint speech-motion generation models are largely driven implicitly by transcript semantics or intermediate speech representations, offering little explicit control over motion hierarchy, body parts, or vocal style. To bridge this gap, we construct MotionSpeech, a structured benchmark for controllable joint speech-motion generation that includes transcripts, voice-style descriptions, and motion conditions at two hierarchical levels. Building on this benchmark, we propose DuoFlow, a dual-stream latent flow transformer that jointly denoises speech and motion under a shared noise level and a unified second-based temporal coordinate. Modality-specific residual connectors inject structured conditions into the corresponding streams, layer-wise bidirectional cross-modal attention coordinates their generation, and a monotonic phoneme pathway combines normalized progress anchors with CTC supervision to strengthen speech temporal modeling. DuoFlow provides a unified interface for fine-grained motion and vocal-style control and demonstrates the ability to synthesize high-quality, synchronized, and instruction-consistent speech-motion sequences.

cs.CV

新论文 · v1arXiv:2611.21524

Algorithm Distillation for Safe In-Context Reinforcement Learning

Minjae Kwon, Amir Moeini, Shangtong Zhang, Lu Feng

原文摘要

Safe in-context reinforcement learning (Safe ICRL) asks a policy with fixed parameters to improve on an unseen constrained task from its interaction history while aiming to keep its cost within a budget. Prior work studied Safe ICRL on five benchmarks in three families: a grid world with a hidden goal and obstacles (DarkRoom), continuous navigation where goals and hazards stay invisible until reached (PointGoal, CarGoal), and locomotion with a hidden velocity limit (HalfCheetah, Ant). Safe Algorithm Distillation (Safe AD), trained on the learning histories of a safe RL algorithm, has shown adaptation failures in prior evaluations. For example, in the locomotion tasks its return stays below zero, and it rarely reaches the goal in CarGoal. We revisit two parts of Safe AD. First, we distill a budget-aware teacher with two phases. It searches for the hidden task, exploring more when more budget remains. After its first reward or cost, an expert policy exploits the task within the remaining budget. We collect the teacher's histories under fixed or dynamic budgets. Dynamic budgets increase the occupancy entropy of the return and budget inputs in every environment, and at test time they improve return and lower cost in DarkRoom and HalfCheetah. Second, we propose A-Lag, a test-time adjustment that reweights the distilled policy's actions by their predicted cost, with an adaptive Lagrange multiplier that is updated from the costs observed. In our experiments, A-Lag had lower mean episode cost than Safe AD in all five environments, with lower mean final return in four.

cs.LG · cs.AI

版本更新 · v2arXiv:2605.13487

Path-independent Flow Matching for Multi-parameter Generative Dynamics

Francisco Téllez, AmirHossein Zamani, Philippe Martin, Shuang Ni, Guy Wolf, Eugene Belilovsky, Sina Sanjari, Yanlei Zhang

原文摘要

Flow Matching is a powerful framework for learning transport maps between probability distributions. Yet its standard single-parameter formulation is not designed to capture multi-parameter variations where the resulting transport should be path-independent. Path independence is crucial because it ensures that transformations depend only on the initial and target distributions, not on the specific path. In this work, we introduce Path-independent Flow Matching (PiFM), a method for learning vector fields whose induced flows yield path-independent transport between distributions. We show that PiFM generalizes Flow Matching to higher-dimensional parameter domains while enforcing structural conditions that ensure consistency of composed transformations. In addition, we show that, under suitable assumptions, PiFM approximates the Wasserstein barycenter, linking the framework to a notion of distributional interpolation. To enable practical training, we propose a tractable, simulation-free objective that regresses onto multi-parameter conditional probability paths. We showcase empirically that PiFM outperforms other approaches on both synthetic and real world data in interpolating path-independent trajectories and generating desired out of distribution samples.

cs.LG

新论文 · v1arXiv:2611.21485

Lost in the Hallway: Benchmarking Persistent Spatial Memory Across Revisits

Henry Zheng, Weibo Gong, Yang Yue, Rui Huang, Yang Zhang, Gao Huang

原文摘要

Persistent spatial understanding is essential for embodied agents to operate reliably in environments they repeatedly encounter. It requires recognizing revisited places despite viewpoint changes, distinguishing them from similar-looking rooms, and updating memories as environments change. Yet existing evaluations often leave physical place identity across separated visits implicit. We introduce ReSpaceBench, a benchmark comprising 3,244 questions across 590 synthetic and real-home scenes, organized into 9 tasks spanning room association, persistent state tracking, and downstream reasoning. Controlled walkthroughs define visits by physical room entry and deliberately include same-type room distractors and cross-session object changes. Our evaluation of 32 models and 3 agentic video-understanding frameworks reveals substantial limitations: the strongest evaluated zero-shot model achieves 50.5% overall accuracy and 52.2% on a 450-question subset, compared with 90.1% for human annotators. The evaluated agentic frameworks offer no overall improvement over direct inference with the same base model. Analysis of agent execution traces reveals evidence omissions and incorrect cross-visit room associations as major failure modes, suggesting that iterative evidence seeking alone does not ensure consistent spatial memory. Further analyses expose a gap between recognizing familiar rooms and identifying the correct visited room, while annotation-guided sampling highlights the importance of preserving intervening visits and transitions. We also provide RS-30K, a separate training dataset from synthetic sources with no template, scene, route, or video overlap with the benchmark. Fine-tuning Qwen3-VL-8B raises overall accuracy from 35.5% to 60.4%, with the largest gains in association and improvements extending to real-life scenes.

cs.CV

新论文 · v1arXiv:2611.21479

LynnReal-Hand: Unlocking World Interaction with Hand Control

Shaohao Rui, Chaoyang Zhang, Xiaofeng Mao, Weijie Ma

原文摘要

Interactive video world models enable exploration through text and camera controls, yet direct object interaction requires finer control. Hands provide a natural interface, but translating continuous hand movements into coherent visual responses remains challenging because of complex hand-object dynamics and demanding real-time computation. To address these challenges, we introduce LynnReal-Hand, a hand-controlled video world model that unifies precise interaction modeling with efficient streaming generation. We curate 100K interaction clips spanning diverse real and synthetic environments and develop hand-aware supervision to improve fine-grained hand motions and object interactions. Building on this foundation, we learn a causal flow map for few-step generation and introduce region-aware score distillation that combines complementary video and image priors to refine interaction dynamics and visual appearance. To further reduce inference latency, we propose Ultra-Fast-VAE, a compact video decoder that preserves high reconstruction fidelity with substantially lower computational cost. Extensive evaluations on HandBench demonstrate superior hand-following accuracy and visual quality compared with existing approaches. Our full-sequence model achieves an FVD of 181.67 and a MANO Dice score of 93.02, while the three-step causal model maintains a MANO Dice score of 92.49. For real-time interaction, 540p streaming on a single H200 reaches 18.03 FPS with 741ms latency and an optimized peak GPU memory footprint of only 34.89GB. We will release the datasets, model weights, and the full training and inference code to support research on hand-controlled video world models.

cs.CV · cs.AI

新论文 · v1arXiv:2611.21478

Jetriever: Shifting Agent Memory Retrieval from Similarity to Utility

Ruizhe Li, Licheng Zhang, Mingxuan Du, Zhendong Mao

原文摘要

A useful memory need not resemble the question it helps answer. Jetriever ranks each stored memory by Jev's decision score for its usefulness to the current question, replacing similarity search with full-pool utility scoring. On InMind's 125 indirect-query tasks, it places the gold exchange first in 84.8% of cases; matched BM25 and MiniLM controls reach 1.6% and 0.0% when indexing user turns. A 20-question comparison separates finding evidence from ranking it: Jev and Qwen3.5 9B each find 90% of gold exchanges by rank 50, while Laya finds 30%; at rank one, Jev reaches 85% and Qwen3.5 9B 40%. On a dimension-proportional random sample of 60 MemoryAgentBench questions, Jetriever's four-dimension score is 55.4%, against 44.3% for ReFind on the same questions. Jev retrieval costs USD 0.00834 per InMind question and USD 0.03103 per MAB question on average. These results show the value of world knowledge, scores that rank decisive memories first, and affordable full-pool scoring.

cs.CL

新论文 · v1arXiv:2611.21461

ExRel: Learning Directed Reuse Relevance between Rich-Text K-12 Question Images with Executable Relation Contracts

Xuexin Liu, Zengyi Wo, Shiyu Zhang, Suqi Cheng, Daiting Shi, Xiuyi Chen

原文摘要

In K-12 education, question images combine text, mathematical expressions, diagrams, and diverse layouts. Variations in wording, conditions, answer options, or task scope can substantially alter their reuse utility despite visual similarity. We formulate this problem as directed reuse relevance, grading candidate utility as Strong, Medium, or Weak. However, generic similarity scores overlook task-specific reuse requirements, while natural supervision is dominated by Strong relations and lacks fine-grained coverage. We propose ExRel, an agentic, code-grounded framework for controllable and verifiable visual data synthesis. It reconstructs real questions into editable HTML/CSS seeds and compiles 15 relation subtypes into executable contracts specifying permitted edits, protected invariants, and query-candidate direction. Synthesized pairs undergo deterministic DOM/render validation and target-hidden, evidence-assisted review, with bounded repair before mild photographic degradation. Only rendered images are used for downstream training. Experiments show that ExRel supervision outperforms size-matched natural data and count- and class-matched replay, particularly on Medium relations, while maintaining comparable query-level ranking performance and improving robustness to visual degradation. Construction ablations demonstrate higher valid yield and fewer false admissions than less structured baselines. Human audits confirm 98.0% post-admission validity, while ExRel achieves a lower per-accepted-pair cost than outsourced annotation (0.70 vs. 1.10 RMB). Downstream answer routing further demonstrates the practical utility of the synthesized supervision.

cs.IR

新论文 · v1arXiv:2611.21454

Comments on "Deep Fréchet Regression"

Jianbin Tan, Anru R. Zhang

原文摘要

We discuss the Journal of the American Statistical Association (JASA) discussion paper "Deep Fréchet Regression" and explore an alternative perspective based on conditional flow matching. We propose learning covariate-dependent transport directly within the response space, avoiding separate manifold learning and reverse mapping. This perspective offers a potentially more flexible framework for incorporating geometric structure and modeling full conditional distributions.

stat.ML · cs.LG

版本更新 · v2arXiv:2610.15728

When Watermarks Turn Adversarial: Exposing Vulnerabilities in Document Understanding

Qingzhe Han, Fan Dang, Shengqi Chen, Xinyi Sun, Haoyu Xiong, Lingkun Li, Di Zhang

原文摘要

Visible watermarks are common in digital documents and persist during vision-language model (VLM) processing. We show that they can also serve as adversarial surfaces for document understanding. We propose Watermark-based Adversarial Surface Perturbation (WASP), a white-box attack that optimizes pixels inside fixed watermark strokes without requiring downstream questions, answers, or task-specific losses. We further introduce Balanced Aggregation Loss (BAL), which emphasizes visual token groups that remain highly similar to clean representations. Adversarial watermarks degrade performance substantially more than ordinary watermarks. On DocVQA, WASP achieves attack success rates of 96.81% and 71.93% against Qwen2.5-VL and InternVL2.5; BAL improves over a standard token hinge objective by 9.21 and 2.24 percentage points. On 1,651 OmniDocBench pages, WASP increases MinerU2.5's text edit distance by 0.7748 relative to ordinary watermarks. WASP also transfers within model families and across readers sharing a vision-tower architecture. Attack effectiveness depends on watermark geometry, model architecture, and preprocessing; in structured parsing, disrupted layout and routing can propagate errors downstream. These results expose an underexplored security risk in document understanding systems.

cs.CV

新论文 · v1arXiv:2611.21441

Learning to Reason with Predictive Gains for Generative Recommendation

Zhuoyang Li, Teng Shi, Jiakai Tang, Weijie Yu, Guofu Xie, Xiao Zhang, Lei Kou, Yang Yu 等 13 位作者

原文摘要

Reasoning-enhanced generative recommendation (GR) has attracted increasing attention for leveraging the reasoning capabilities of large language models (LLMs) to improve next-item prediction. However, existing methods primarily optimize reasoning through Group Relative Policy Optimization (GRPO) with rule-based rewards determined by final recommendation performance, which faces two key limitations: (i) unmeasured predictive contributions within reasoning, where the predictive contributions of individual reasoning steps are not directly reflected in optimization signals, and (ii) weakly discriminative learning signals within groups, where different reasoning trajectories within the group often receive indistinguishable rewards, limiting effective policy optimization. In this paper, we propose GainReason, a simple yet effective training framework that optimizes reasoning through Predictive Gain (PG). Specifically, PG measures changes in target Semantic ID (SID) log-likelihood induced by individual reasoning sentences, providing contribution-aware and discriminative rewards. We further theoretically establish the alignment between expected PG and the recommendation ranking objective. Building on this signal, we develop PG-based Reasoning Optimization (PGRO) to optimize reasoning generation with sentence-level rewards, supported by a custom causal attention mechanism for efficient PG computation. Additionally, an auxiliary PG-based Reasoning Utilization (PGRU) task adaptively strengthens reasoning-conditioned prediction to complement PGRO. Extensive experiments on three public benchmarks demonstrate that GainReason consistently outperforms competitive baselines and achieves substantial performance gains from reasoning.

cs.AI

版本更新 · v2arXiv:2611.16591

Singularity-Bench: Can Agents Build Agents?

Yang Zhou, Krish Agarwal, Zhuoming Chen, Zerui Wang, Zhenyu Zhang, Wenshuang Li, Xinpeng Wei, Zhichen Zeng 等 19 位作者

原文摘要

Frontier AI agents increasingly succeed on realistic, long-horizon tasks and are beginning to improve the systems through which they operate. Yet existing benchmarks often restrict agents to narrow action spaces, use simplified environments, or rely on verification methods that are unreliable for evaluating arbitrary agent-generated systems. We introduce Singularity-Bench, an open-ended benchmark for autonomous AI development with six end-to-end tasks spanning pre-training, mid-training, post-training, inference, the agent harness, and cluster orchestration. Each task requires agents to implement core systems from a minimal starting point and evaluates them against mature human-engineered baselines on identical hardware. Additionally, through extensive red-teaming covering 9 of the 10 categories in the OWASP Top 10 for Agentic Applications, we expose reward-hacking vulnerabilities in the conventional Harbor framework and develop Breakwater, an extension of Harbor that blocks all attacks tested in our study. Across 11 agents built from 7 frontier models and 2 harnesses, Opus 5.5 with Claude Code matches or outperforms the human baseline on all six tasks with a Singularity-Index of 1.25, suggesting it may have the skills needed to reach the singularity. The remaining agents average only 0.60. Our vision is for Singularity-Bench to track how much of AI development agents can already automate and when they may transition from assisting to taking end-to-end responsibility for building stronger successors.

cs.AI

版本更新 · v2arXiv:2611.12529

Perceived Agency During Agent-Avatar Control Transitions in Virtual Reality

Jingyi Zhang, Ruijun Sun, Klara Brandstatter, Nels Numan, Anthony Steed

原文摘要

Prior beliefs about whether a virtual human (VH) is controlled by a human or a computer can shape how users interpret and respond to its behaviour. As emerging hybrid VH systems allow control to transfer between human operators and computer programs during an ongoing interaction, it remains unclear whether perceived agency updates with the actual controller or continues to reflect users' prior beliefs and first impressions. We investigated this question in a within-subject VR study with 24 participants across four conditions: always computer-controlled, computer-to-human, human-to-computer, and always human-controlled. We designed an interaction task in which participants acted as interviewers, asking the VHs a fixed set of questions. Before each interaction, participants were informed whether the VH was human- or computer-controlled, matching the actual controller at the beginning, but were unaware of possible control transitions. We found that perceived agency was strongly influenced by the controller presented at the beginning of the interaction, with no evidence of updating following the control transitions. Social evaluations including likeability and co-presence were generally higher in conditions where human control occurred later and covered a greater proportion of the interaction. The results suggest that prior beliefs and first impressions continued to shape perceived agency, whereas social evaluations were more sensitive to the VH's actual behaviour over the interaction.

cs.HC · cs.AI

新论文 · v1arXiv:2611.21423

Emergent Steering Beyond Endpoint Alignment in Chemical Reaction Models

Yili Shen, Kehan Guo, Haomin Zhuang, Xiangliang Zhang

原文摘要

Machine learning models for chemical reaction prediction are usually evaluated by endpoint accuracy, but endpoint correctness alone does not reveal how a model represents chemical transformation or why it fails. We introduce UniRxnAxis, a unified forward-retrosynthesis framework that models both tasks as direction-conditioned endpoint redistribution in a shared latent space. By aligning source states, transformed states, and encoded target endpoints, UniRxnAxis enables directional auditing of learned latent updates. This shared latent geometry allows the learned displacement (from the encoder source state $S_0$ to the decoder-facing transformed state $S_1$) to be decomposed into an endpoint-parallel component and an endpoint-orthogonal residual, which we call emergent steering. Our evaluation shows that emergent steering is functionally important: in retrosynthesis, it recovers most of the model's utility, remains effective under random, shuffled, and prototype controls, and directly affects which bond edits are promoted or suppressed. The residual-over-parallel ordering persists across alignment strengths, after decoder-interface calibration, against angle-matched random axes, and in a second graph-edit architecture, although its magnitude depends on the reference axis and optimization. The decomposition also supports a proxy taxonomy of model-side failures, showing how reaction models can be audited beyond endpoint accuracy.

cs.LG · cs.AI

版本更新 · v2arXiv:2608.21847

CALE: Color-Adaptive Low-Light Enhancement via Learnable Intensity Coordinates

Yi Ai, Zheng Chen, Yuanhao Cai, Yulun Zhang, Xiaokang Yang

原文摘要

Small brightness differences in dark regions are difficult to recover, and their spacing in the coordinates used for restoration depends on the intensity mapping. A globally learned Box--Cox exponent controls the full response, coupling different brightness intervals and applying the same mapping to every image. We propose Color-Adaptive Low-Light Enhancement (CALE), which combines an image-conditioned intensity representation with structure-conditioned rectified flow (\mbox{SR-RF}). The representation, Box--Cox Intensity Adaptation (BIA), refines a normalized Box--Cox transform using a monotone piecewise-linear curve. Compact statistics of the low-light observation determine the output widths of brightness intervals, allowing the response to vary across images. Positive, normalized slopes preserve intensity order and endpoints and give the intensity mapping an analytic inverse. Combined with polar chromaticity, BIA defines the coordinates for the \mbox{SR-RF} network. The mapping and restoration network are trained jointly so that the reconstruction objective shapes the intensity response. Experiments on paired benchmarks and unseen datasets show competitive restoration performance across diverse low-light scenes, with qualitative comparisons illustrating the recovery of scene colors, contrast, and detail. Coordinate ablations separate the effects of interval flexibility and input conditioning, while Full and Tiny models offer quality--computation trade-offs.

cs.CV

新论文 · v1arXiv:2611.21402

Harmonic-Mean Aggregation of Continuous-Time Markov Chains with Reachability Error Bounds

Bingqing Hu, Landon Taylor, Zhen Zhang

原文摘要

Abstracting a continuous-time Markov chain by grouping its states into blocks raises a fundamental question: which rates should the abstract chain use when states within a block have different exit rates and transition probabilities? We study harmonic-mean aggregation, which matches the mean waiting time and next-block distribution of a local experiment that uniformly selects a state within the block and observes its next jump. Equivalently, the abstract transition rates are averages of the concrete rates with inverse-exit-rate weights. Since the aggregation does not preserve reachability probabilities in general, we derive theoretical error bounds for time-bounded reachability. We decompose the error into a blockwise mean and centered-within-block deviations, and show that the rate mismatch has zero weighted mean. Exploiting this cancellation and differences between abstract reachability values, we obtain bounds valid at every time horizon through a linear comparison system with two quantities per block, without computing concrete reachability values. All results are formalized and proven in Lean 4.

cs.LO

新论文 · v1arXiv:2611.21392

VideoNexus: Video Perception Beyond the Reasoning Context

Yancheng Long, Xuanyu Zheng, Wei Chen, Luoyuan Zhang, Haoyang Xu, Bin Wen, Tingting Gao

原文摘要

Understanding long videos requires locating evidence, resolving visual details, and integrating observations into an answer. Even when relevant evidence is present, performing these operations within long, dense visual sequences burdens both perception and reasoning. Video agents enable selective inspection, but returning frames to the planner still accumulates visual information in its reasoning context. Delegating perception reduces this burden, yet sparse sampling can miss decisive details, and per-frame descriptions can preserve context growth. We introduce VideoNexus, a training-free framework that separates detailed video perception from evidence-driven planning and reasoning. The planner controls where to inspect, what to resolve, and how densely to sample. Perception sub-agents process native audio-video in independent contexts and return compact, temporally grounded evidence for iterative search and verification. Using Gemini 3.8 Flash for both planning and perception, VideoNexus achieves 88.6% accuracy on full LVBench, exceeding same-backbone static ingestion and built-in agentic processing by 3.6 and 1.1 points, respectively, at 44% of the latter's measured API cost. A paired LVBench subset ablation shows lower planner input and higher accuracy. With Kimi K3 as the shared backbone, VideoNexus improves over the official Video-GAIA ReAct harness by 8.5 points in our evaluation. These results support compact evidence exchange for combining detailed observation with efficient planning and reasoning.

cs.CV

新论文 · v1arXiv:2611.21382

VisualArtifactSpec 1.0: Evaluating Visual Artifacts under Task Specifications

Shuyi Ouyang, Xiaojun Tang, Zijian Zou, Xintong Zhang, Mingli Song, Guannan Zhang, Hongwei Xue

原文摘要

Visual artifact tasks test agents' ability to translate task specifications and source materials into outputs that meet practical needs. Evaluation across artifact families helps distinguish broadly applicable authoring capabilities from strengths confined to a particular medium. We introduce VisualArtifactSpec 1.0 (VAS), a benchmark of 211 creation and modification tasks spanning presentations, static graphics, animations and videos, and web interfaces. Each task specifies authoring objectives, source materials, constraints, and deliverables. Existing benchmarks provide limited support for systematically evaluating how authoring choices suit different audiences, purposes, and media across artifact families. VAS evaluates two aspects separately: Task Fulfillment verifies explicit requirements and applicable functionality, while Artifact Performance assesses Content, Organization, Visuals, and Delivery. Task-specific rating anchors instantiate shared criteria for the intended audience, purpose, and medium, with judgments grounded in source materials and artifact inspection records. We evaluate nine model-harness configurations on all 211 tasks. Overall scores range from 42.12 to 70.52, with Artifact Performance accounting for 73.4% of the gap between the highest- and lowest-scoring configurations.

cs.AI

新论文 · v1arXiv:2611.21373

WeVisForensics: Self-Evolving Agent for Omni AI-Generated Video Detection

Yipeng Du, Yuxi Li, Ying Zhang, Chong Sun, Chen Li, Jing Lyu, Ying Tai

原文摘要

Recent advances in video generation call for reliable detection grounded in explicit forensic evidence. However, current methods primarily depend on single-pass chain-of-thought reasoning that overlooks brief or localized artifacts, or on predefined multi-agent workflows that offer limited flexibility in selecting relevant inspections. Even with adaptive investigation, optimizing the investigation policy alone does not directly improve the forensic capabilities of fixed experts. We introduce WeVisForensics, an agentic framework in which a main investigator agent coordinates a self-evolving library of forensic inspector sub-agents spanning visual and audio cues. The investigator learns which artifact type to examine, over which window, and when to conclude, and these interactions provide shared feedback for both levels of agents. Our dual-timescale policy optimization strategy, DTPO, closes this loop through fast reinforcement learning of the investigator and slower refinement of the inspectors, guided by annotated artifact intervals, to report subtle artifacts they once dismissed. Furthermore, we curate ForenCue-30K, combining role-specific forensic annotations and interaction trajectories to supervise individual inspections and their coordination, with an accompanying reinforcement-learning pool. Experiments show that WeVisForensics averages 95.2% detection accuracy across in-domain, out-of-domain and agentic benchmarks, 9.0% above the strongest prior detector, while grounding its verdicts in localized evidence.

cs.CV · cs.AI

新论文 · v1arXiv:2611.21372

Learning What Pairs Miss for Higher-Order Multimodal Alignment

Kunyu Zhang, Shenghui Feng, Xiangjie Shi, Zeqing Wang, Yingxu Wang

原文摘要

Contrastive learning beyond two modalities now scores the whole tuple with multilinear products, volumes, and fusion heads, critics that can represent the joint distribution. In practice these critics still behave like bags of pairs. Their negatives break at least two of the three pairs, a single pairwise check rejects them, and when most samples can be solved by pairs the higher-order term receives almost no gradient. To solve this problem, we propose CHORD (Contrastive Higher-Order Residuals with Decoys), which trains a residual against decoys drawn from a calibrated pairwise model, negatives that the pairwise model finds plausible, so that rejecting them often needs all three modalities. Drawing decoys costs one inner-product query over a memory bank, and the optimal residual is the log-ratio between the data and the pairwise model, so the decoy loss also bounds what that model misses. On M3-Mix, where one in ten training samples needs all three modalities, our CHORD improves accuracy on those samples by 21.2 percentage points over the strongest of eight baselines. CHORD also gives the best two-to-one results on every real dataset, and its residual improves other retrievers without retraining.

cs.LG

新论文 · v1arXiv:2611.21366

ALIVE: Making Streaming Video Models Interactive

Jinzhao Li, Yuan Xu, Jinxuan Wu, Yukun Wang, Yijia Lei, Hanyu Ji, Yinuo Chen, Zining Huang 等 16 位作者

原文摘要

Streaming video LLMs can continuously observe the world, yet often handle user requests in isolation. We introduce ALIVE, an interactive streaming video model supporting proactive monitoring, streaming task coordination, and feedback-seeking interaction. We construct ALIVE-SFT-288K and ALIVE-RL-3K for two-stage training. Contrastive supervised fine-tuning teaches when and how to respond, while reinforcement learning with Behavior-Aligned Credit Assignment (BACA) combines trajectory-level and local advantages to refine decisions, responses, and silence across multi-turn interactions. We also introduce FSI-Bench to evaluate feedback seeking and subsequent task completion. ALIVE achieves the highest overall scores among the compared models on four public benchmarks and FSI-Bench, demonstrating strong streaming understanding and interactive capabilities.

cs.CV

版本更新 · v6arXiv:2512.00324

MILE: A Mechanically Isomorphic Hand Exoskeleton and Visuotactile Robotic Hand for Data Collection in Dexterous Manipulation

Jinda Du, Jieji Ren, Qiaojun Yu, Ningbin Zhang, Yu Deng, Xingyu Wei, Yufei Liu, Guoying Gu 等 9 位作者

原文摘要

Dexterous robotic hands perform complex, contact-rich manipulation. Imitation learning provides a route to such skills, but collecting human demonstrations with accurate hand actions and rich tactile information remains a key bottleneck. We present MILE, a teleoperation-based data-collection system comprising the wearable MILE exoskeleton and the mechanically corresponding MILE-Tac robotic hand. Because human-hand anatomy and wearability place tighter constraints on the high-DoF wearable, our human-first design begins with the MILE exoskeleton, equipped with custom modular joint encoders for accurate joint-angle acquisition. We then design the MILE-Tac robotic hand to share the exoskeleton's selected kinematic topology and joint-axis arrangement while satisfying robot-side implementation constraints, and equip its fingertips with compact visuotactile sensor modules. This correspondence enables direct exoskeleton-to-robot joint-space command transfer without online task-space inverse-kinematics retargeting. During teleoperation, the system synchronously records task-specific visual observations, four fingertip visuotactile streams, robot-hand proprioception, and exoskeleton-derived action commands. In a four-task teleoperation benchmark, MILE achieved a mean success rate of 76%, compared with 28% and 8% for glove-based and vision-based baselines, respectively. For downstream imitation learning, we trained paired ACT and DP policies with and without tactile input on MILE-collected demonstrations. The tactile-input variants achieved higher success rates in all paired evaluations.

cs.RO · cs.CV · cs.HC

新论文 · v1arXiv:2611.21348

Representational Change Under Self-Consuming Training: A Sparse Autoencoder Analysis

Suchit Gupte, Zhongteng Cai, Xueru Zhang, Mohammad Mahdi Khalili

原文摘要

Large language models are increasingly exposed to model-generated text, raising the possibility that future models will be trained recursively on the outputs of their predecessors. Prior work on such self-consuming training loops has largely focused on output quality and downstream performance, leaving their effects on internal representations poorly understood. We study how representations evolve across five generations of self-consumption and whether sparse autoencoders (SAEs) remain reliable under this shift. At each generation, we compare a lineage trained on synthetic data with a matched control trained on real data under the same training settings. We evaluate how well SAEs trained before self-consumption transfer to later generations, measuring reconstruction and sparsity across SAE widths, architectures, and model layers. We then fine-tune the original SAE on each generation and use sparse probing to test whether task-relevant information remains concentrated in a small number of latents or becomes more distributed across the representation. We find that zero-shot SAE performance degrades progressively under self-consumption, with growing reconstruction and sparsity gaps that vary substantially across layers. Fine-tuning largely restores reconstruction, but not feature-level usefulness: task-relevant information remains accessible in the full latent space while becoming less concentrated in individual features. These results show that self-consumption induces representational drift and that reconstruction fidelity alone is insufficient to establish that an adapted SAE remains equally useful for interpretation.

cs.LG · cs.AI