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

+1085新增论文
+884其中 AI 相关
+130已有论文修订
+94新增 AI 导读

arXiv 最近完成扫描:2026-11-19 06:59 · 全站最近入库:2026-11-19 06:59各信源进度 →

统计口径与数据新鲜度

统计 2026-11-18 09:46 — 2026-11-19 09:46(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:2026-11-19 06:59最近发现新增版本:2026-11-19 06:59库内论文最新更新时间:2026-11-18 08:00

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。

26,871 已收录论文22,375 AI 相关8,156 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 102 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-19 06:57(北京时间)
版本更新 · v3arXiv:2611.10357

LEGIT: Live Eligibility Gating over Identifier Tries for Constrained Decoding of Heterogeneous Pages

Felix Fang, Zheng Liu, Robert Saliba

原文摘要

A generative recommender names each candidate with a short token sequence, a Semantic ID, and recommends by generating those tokens. Some generative recommenders, including the Uber Eats search engine we are building, write a whole results page, stores with their menu items, in one decoding pass. Every Semantic ID on such a page must name a real store or item that is eligible for the search, such as a store that delivers to the user's location, and that is not already on the page. Each item must also belong to the store above it. A trie over the catalog keeps identifiers real, but eligibility and repetition change with every request and token, and the grammar-constrained decoder we tried could not enforce these changing rules exactly and quickly. We call this constraint LEGIT, for live eligibility gating over identifier tries. Numbering trie leaves depth first turns each rule into a range lookup over one store trie and one item trie, and every generated page passes an independent catalog check. On one NVIDIA B200 GPU with one or two requests per decode step, a direct implementation that walks the trie on the GPU makes each token about 5 times as slow as unconstrained decoding. Across 36 implementations, hardware counters and ablations are consistent with kernel launches and CPU-GPU waits as the source of this slowdown. Our fastest implementation walks the trie on the CPU while the GPU runs the model, needs no custom kernel, and cuts time per output token by 65.9 percent against the direct GPU implementation, to about 1.7 times the unconstrained cost. This implementation is also the fastest on a page layout that puts each item before its store.

cs.IR · cs.LG · cs.PF

版本更新 · v2arXiv:2610.38754

Alpha-TCM: Auditable Knowledge Integration for Multimodal TCM Inference

Yucheng Liu, Everett X. Wang

原文摘要

Knowledge-guided multimodal systems need a way to measure how supplied knowledge affects predictions, including when that knowledge is wrong. Alpha-TCM addresses this problem for traditional Chinese medicine (TCM) through an implemented workflow that separates measurements, supplied knowledge, predictions, and reviewer decisions. Observations and contextual knowledge enter separately, and a replaceable prior allows controlled interventions with fixed modality encoders. Bayesian committee accounting removes the reference prior already contained in each encoder before inserting contextual knowledge. A fully simulated confirmation study uses ten paired seeds and four training sizes. Knowledge context reduces prediction error relative to knowledge-free fusion at 600 and 1,200 training cases; equal-information learned context is competitive at 600 and has lower error at larger sizes. Controlled corruption identifies overconfident and displaced priors as the most damaging challenges. Case-level conflict detection remains weak, and training-time prior regularisation shows no consistent benefit. Functional tests verify the connected workflow separately from predictive performance. The simulation demonstrates how Alpha-TCM measures knowledge dependence, separates it from gains due to additional context, and exposes harmful prior assumptions before clinical evaluation.

cs.LG

版本更新 · v2arXiv:2610.38774

Seeing Is Not Enough: Knowledge-Grounded Active Inquiry from Uncertain Visual Evidence

Yucheng Liu, Everett X. Wang

原文摘要

Similar tongue findings can accompany different syndromes in traditional Chinese medicine (TCM), with decisive symptoms absent from the photograph. We present a framework for tongue assessment in which image and pulse findings guide targeted symptom inquiry and acquired answers refine the syndrome shortlist before reporting. Image/pulse predictions guide selection from a sourced symptom question bank. Known answers update the assessment used to select the next question. A calibrated loss of support for the initial prediction triggers reassessment; a subsequent report requires fresh answers supporting a stable candidate. Question and answer records make these decisions inspectable. We construct 2,600 cases from distinct real tongue photographs, assigned syndromes, simulated symptom responses and rendered pulses; 2,599 enter five-fold source-disjoint evaluation and one is training-only. On clean images, image/pulse prediction alone achieves 46.4% fine-syndrome accuracy. At acquisition cost 12, inquiry without image/pulse evidence reaches 34.4%, whereas their combination reaches 65.8% accuracy and 90.8% top-three inclusion. A same-prior, training-optimized static order reaches 59.4% and 87.3%, respectively. In a 200-case visual-training intervention within the same bank, the first question changes in 46.7% of cases and the inquiry NLL-cost curve improves. Component comparisons distinguish these acquisition gains from the coverage-cost tradeoff of reassessment. These controlled results support image-guided acquisition of missing symptoms for ranked TCM decision support.

cs.LG

版本更新 · v2arXiv:2608.18903

When Candidate Pools Miss Active Constraints: Evidence from Electromagnetic and Thermal Design

Yucheng Liu, Chuncheng Zhao

原文摘要

Finite candidate pools can limit surrogate-assisted design when good designs lie near intersecting active constraints. For independent uniform candidates in a normalized box, the typical minimum sum of gaps to k active bounds scales as (k!/N)^(1/k) for a pool of size N. This geometric limitation persists even with an accurate surrogate. We examine it through a controlled synthetic study and two finite-element design problems with inexpensive analytic constraints: a seven-variable electromagnetic coil and an independent six-variable heat spreader. The budget permits 25 initial observations and 50 further evaluations. On ten matched seeds, replacing pool EI with continuous constrained EI refinement raises mean coil response from 0.9120 to 0.9745 mT and lowers mean thermal resistance from 12.688 to 11.905 K/W. Standard continuous LogEI performs better than this refinement on nine coil seeds and all ten thermal seeds, reaching 0.9770 mT and 11.860 K/W. GP-mean search has the highest nominal coil mean but exhibits a thermal outlier on one seed. Mesh and domain checks preserve the substantial continuous-search advantage over the pool; they do not establish a resolved physical ranking among the closely performing continuous policies. Together, the sampling analysis and matched simulations identify when finite-pool search restricts the use of an FEM budget. The results support continuous constrained acquisition search, with stable LogEI as an effective existing implementation, when finite pools poorly represent high-value boundary designs. Bayesian optimization; acquisition optimization; active constraints; simulation-driven design; finite-element method; Gaussian-process surrogate; electromagnetic coil design; heat conduction

cs.LG

版本更新 · v2arXiv:2512.12196

AutoMV: An Automatic Multi-Agent System for Music Video Generation

Xiaoxuan Tang, Xinping Lei, Chaoran Zhu, Shiyun Chen, Ruibin Yuan, Yizhi Li, Changjae Oh, Ge Zhang 等 13 位作者

原文摘要

Turning a full song into a music video (MV) requires interpreting its lyrics, which are often metaphorical, multilingual, and repeated across choruses, together with its musical character, and laying the resulting imagery out along the song's structure. Existing music-to-video systems produce short clips or audio-reactive visuals and make little use of lyric meaning. We present AutoMV, a training-free multi-agent framework in which LLM Screenwriter and Director agents plan a full-song visual narrative from time-aligned lyrics and music analysis, keep characters consistent through a shared character bank, and route each shot to cinematic or lip-sync rendering with verification. To evaluate full-song MVs, we build M2VBench: 30 released songs paired with their official MVs, objective audio--visual metrics, and a 12-criterion rubric rated by music-industry experts. Expert evaluation shows that AutoMV outperforms other baselines, although a gap remains to human-produced MVs. Ablation studies highlight the importance of time-aligned lyrics for musical theme alignment and storytelling. We further find that the selected multimodal judge, guided by our evaluation rubric, recovers the expert ranking of automatic systems, with some discrepancies in fine-grained assessments.

cs.MM · cs.CV · cs.SD · eess.AS

新论文 · v1arXiv:2611.22728

LoopZip: Visual Token Compression for Efficient Looped Vision-Language Models

Weizhong Huang, Zhicheng Liu, Yan Zhang, Fei Chao, Xiawu Zheng, Liujuan Cao

原文摘要

Looped vision-language models (VLMs) deepen computation by reusing shared layers, approaching larger models' capabilities with fewer parameters and easing the storage and deployment burden of stacking independent layers. However, repeatedly processing long visual sequences still incurs substantial compute and GPU memory costs. Visual token compression reduces these costs by shortening sequences. Existing methods mainly select original tokens directly or combine selection with aggregation. In looped models, the former may overlook changing token importance across calls and discard information needed later; the latter lack joint consideration of output changes across calls, limiting information preservation. We propose LoopZip, a training-free visual token compression algorithm addressing both issues. Visual aggregation builds a compact candidate pool before the looped backbone, and cross-invocation selection averages instruction attention from the first two existing calls of the same shared attention layer to retain tokens needed by both states. Weight-tied value correction then jointly fits shared visual-value adjustments to both pre-selection layer outputs, reducing output deviations across states. To validate LoopZip's effectiveness, we conduct extensive experiments covering two open-source looped VLMs, eleven benchmarks, and three pruning ratios. On LoopVL-1B, LoopZip retains 97.16% of the original model's performance at 50% pruning ratio and exceeds the strongest baseline by 5.36% at 87.5% pruning ratio. Across Hugging Face Transformers, vLLM, and SGLang, LoopVL-1B with LoopZip reduces peak allocated GPU memory by 58.36%-58.98% and achieves 2.01-2.47x end-to-end speedups over the original model.

cs.CV · cs.LG

新论文 · v1arXiv:2611.22727

SlopeGuard: Towards Generalizable AI-Generated Image Detection via Radial Spectral Slope Guidance

Cheng Fu, Yiheng Li, Yang Yang, Wenzheng Liu

原文摘要

AI-generated image detectors often overfit to generator-specific artifacts, hindering generalization to unseen synthesis pipelines. Existing frequency-based methods usually learn high-dimensional spectral patterns that may preserve generator-dependent variations. We explore Radial Spectral Slope, a compact descriptor of global spectral decay that captures transferable spectral trends while suppressing fine-grained variations. Our analysis shows that real and generated images exhibit systematic but generator-dependent slope differences, indicating that slope provides useful forensic evidence but is insufficient as a standalone decision criterion. This motivates combining spectral slope with semantic representations for more robust detection. Based on this insight, we propose SlopeGuard, which couples slope-aware data processing with slope guided feature learning to construct informative patch-based views, integrate Radial Spectral Slope with semantic features, and adapt prior preservation according to spectral atypicality. Extensive experiments demonstrate that SlopeGuard achieves state-of-the-art mean accuracies of 97.5% on AIGCDetectBench, 97.8% on GenImage, and 85.1% on AIGIBench, while maintaining competitive performance under blur, cropping, JPEG compression, and additive noise.

cs.CV

版本更新 · v3arXiv:2610.16859

ANCHOR: Assessing Naturalistic Constraint Hierarchies and Ordering in Repository-Grounded Agentic Coding

Wenqiang Zhu, Xinping Lei, Zhiyi Lai, Zhengshuo Gong, Tianzhuang He, Songwei Yu, Weihao Li, Jingxuan Xu 等 21 位作者

原文摘要

For repository-grounded coding agents, a functionally correct patch is not necessarily an acceptable one: developers also constrain how the task must be carried out-modification scope, workflow order, validation, tool use, and reporting. This capability, which we call engineering constraint following, remains largely invisible to current evaluations. We introduce ANCHOR (Assessing Naturalistic Constraint Hierarchies and Ordering in Repository-Grounded Agentic Coding), a benchmark built on naturalistic, multilingual repository tasks spanning eight language groups. ANCHOR combines (i) a hierarchical taxonomy of 10 categories and 78 leaf types distilled from real developer interactions, (ii) an automated pipeline that instantiates task-grounded atomic constraints and composes them into typed AND/THEN/PRIORITY relations, and (iii) a trajectory-grounded evaluation framework that checks both the code diff and the execution trajectory with rule-based and LLM judges. Across 19 agent configurations spanning 2 scaffolds and 10 foundation models on 358 tasks, the strongest measured system, Claude Opus 4.8 under Cline, reaches 70.1% atomic compliance and 63.7% relation compliance, while 19.0% of tasks pass every scored checklist item under the strict all-item FCCR criterion. A five-engineer audit of constraints from 50 instances reports 94% feasibility, 94% repository consistency, and 96% realism. In the primary paired set (14 configurations), the mean signed change in task completion after adding constraints is +0.7 percentage points; individual changes vary in both directions. These results distinguish functional success from constraint compliance, with failures concentrated in workflow ordering, tool-use discipline, and reporting, and substantial interactions between models and scaffolds.

cs.CL

新论文 · v1arXiv:2611.22141

CEVA: Complementary Evidence Verification via Frame-Level Reorganization for Short-Video Fake News Detection

Wenshen Yang, Junfeng Hao, Jing Li, Decheng Liu, Yangkunfei, Shuyu Jiang, Haizhou Wang

原文摘要

Short-video platforms are now a common way for the public to follow unfolding events. Their rapid, visually persuasive format also makes fake news easier to spread. Unlike text-image posts, short-video news interleaves multiple modalities and changing scenes, making it difficult to identify which frames verify a claim. Existing detectors either pool sampled frames homogeneously or select them by text-frame similarity. Both overlook that aligned frames may repeat a misleading claim, whereas less dominant context may challenge it. We present CEVA (Complementary Evidence Verification Approach), to our knowledge the first short-video fake news detection framework to explicitly organize frames by their evidential roles before multimodal fusion. Its Dual-Branch Complementary Reorganization (DBCR) module separates explicit-alignment frames from candidate complementary-context frames, and cross-modal fusion with bidirectional contrastive regularization operates on the reorganized evidence. On FakeSV and FakeTT, CEVA achieves the best overall results among the compared methods. Under fixed frame budgets and backbones, DBCR outperforms uniform, random, and similarity-based selection and improves two structurally different detectors. Together, these results establish pre-fusion evidence organization as an effective and transferable component of short-video fake news detection.

cs.CV

新论文 · v1arXiv:2611.20771

Nemotron 3.5 Bolt E4B 4GB: An Open and Efficient Small Language Model for Fast Conversational Agents

NVIDIA, :, Adi Margolin, Aditya Malte, Aishwarya Chhabra, Alex Hodson, Ameya Sunil Mahabaleshwarkar, Ambrish Dantrey 等 113 位作者

原文摘要

We introduce Nemotron 3.5 Bolt E4B 4GB, an open and efficient small language model further post-trained from Gemma-4-E4B-it and optimized for speed and intelligence per GB of memory used for fast conversational agents. The model carries forward Gemma's strong conversational capabilities and further improves multi-turn tool use, instruction following, and input grounding for fast, local voice/device assistants, interactive personas, and embedded/Edge interfaces. The model combines natural conversation with multi-turn agentic capabilities to power voice/device assistants, interactive characters and robotic/IoT interfaces running on GeForce RTX, Jetson, and RTX/DGX Spark. Experiments on 21 benchmarks show that Nemotron 3.5 Bolt E4B 4GB achieves the highest average accuracy while generating the fewest output tokens in both reasoning and non-reasoning modes, compared with Gemma-4-E4B-it and Qwen3.5-4B. The model is released with a DFlash drafter. With DFlash, Bolt E4B achieves $2.74\times$ the per-user decode speed of inference without speculative decoding at concurrency~1, and $1.21\times$ the generation throughput of Gemma-4-E4B-it with MTP at batch size 1.

cs.CL · cs.AI · cs.LG

版本更新 · v2arXiv:2601.02236

CD4LM: Consistency Distillation and aDaptive Decoding for Diffusion Language Models

Yihao Liang, Ze Wang, Ximeng Sun, Jiang Liu, Jialian Wu, Hao Chen, Xiaodong Yu, Emad Barsoum 等 10 位作者

原文摘要

Diffusion language models (DLMs) accelerate generation by decoding multiple tokens in parallel, but pushing them to fast decoding often sacrifices accuracy. We attribute this to a static-to-dynamic mismatch: training optimizes local denoising under fixed schedules, while fast inference skips steps and encounters irregular mask patterns. Existing accelerators largely address only one side of this problem. Training-free inference methods speed up decoding without changing the model, leaving the mismatch unresolved; training-side distillation methods adapt the model, but often tie the student to a specific decoding trajectory, limiting composability and still suffering accuracy loss. We propose CD4LM, a composable framework for accurate DLM acceleration. Its core training component, Discrete-Space Consistency Distillation (DSCD) trains a trajectory-invariant student on diverse masked states, reducing the mismatch without fixing a decoding policy. We pair DSCD with a lightweight ConfidenceAdaptive Decoder, while keeping the trained student compatible with external inference-side accelerators. On GSM8K, CD4LM preserves accuracy while achieving a 5.18x speedup; stacking CD4LM with per-step cache accelerators further pushes speedup to 9.73x at teacher-level accuracy, suggesting a scalable path for combining training-side robustness with future decoding advances. Code is available at https://github.com/yihao-liang/CDLM.

cs.CL

新论文 · v1arXiv:2611.20218

SWE-CoWork: Benchmarking Coding Agents as Digital Employees in Organizations

Xinping Lei, Minghao Liu, Ruijie Zhu, Xiaohui Hu, Xingqiao Li, Ao Zhang, Wenhao Chai, Han Li 等 26 位作者

原文摘要

A coding agent working within a software organization must establish what to build, collaborate with colleagues, and verify what it delivers. We introduce SWE-CoWork, a benchmark comprising 101 development assignments across 101 real repositories, 11 programming languages, and 12 application domains. Each assignment places an agent in a simulated engineering organization with 26 colleagues who have distinct responsibilities, bounded knowledge, and controlled collaboration behavior. Starting from a brief handoff, agents must recover requirements distributed across colleagues and workplace records, reconcile conflicting evidence, and implement changes evaluated by private executable tests. We evaluate eleven models and find a substantial gap between partial implementation and complete task delivery. The two leading models satisfy approximately 63% of fail-to-pass (F2P) tests but complete fewer than 8% of assignments. Providing complete requirements upfront improves F2P by approximately 16 percentage points for Seed Evolving and GPT-6 Astra, yet leaves complete task success unchanged. Requirement-level trajectory analysis reveals failures throughout the delivery process: Claude-Opus-5.5 directs a mean of 93% of first questions about queried cards to their accountable owners across runs but obtains only 64% of colleague-held requirements. Deferred questions go unfollowed, implementations remain incomplete even after requirements are acquired, and 31% of requirements reported as completed fail their tests. These findings highlight sustained requirement tracking, from clarification through implementation, verification, and handoff, as a key challenge for reliable autonomous software engineering.

cs.SE · cs.AI

版本更新 · v4arXiv:2509.22082

NL-SME: Enhancing Multi-Step Gradient Inversion through Adaptive Two-State Matching

Li Xia, Jing Yu, Zheng Liu, Sili Huang, Wei Tang, Xuan Liu

原文摘要

Federated learning (FL) enables collaborative model training among multiple clients without directly sharing their raw data.However, gradient inversion attacks can exploit the model updates exchanged during training to reconstruct clients' private data.With multiple local training steps, an observed update combines gradients evaluated at changing model states and potentially different mini-batches, while intermediate states remain hidden. Restricting gradient evaluation to a single state on the segment between the initial and final models can exclude states that better fit the accumulated update.We consider reconstruction from an individual client's endpoint models, assuming that the training labels are known.We propose NL-SME, a regularized two-state gradient surrogate for matching multi-step client updates without replaying local training.The surrogate adapts its evaluation center, regularizes its displacement, and averages raw parameter gradients at two shared symmetric states.We evaluate NL-SME against existing gradient inversion methods on FEMNIST and CIFAR-100 with varying numbers of local training steps.The results show improved reconstruction quality, highlighting the privacy risks of sharing individual client updates after multiple local steps.

cs.LG · cs.CR

版本更新 · v3arXiv:2510.08697

BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution

Terry Yue Zhuo, Xiaolong Jin, Hange Liu, Juyong Jiang, Tianyang Liu, Chen Gong, Bhupesh Bishnoi, Vaisakhi Mishra 等 40 位作者

原文摘要

Crowdsourced model evaluation platforms, such as Chatbot Arena, enable real-time evaluation from human perspectives to assess the quality of model responses. In the coding domain, manually examining the quality of LLM-generated content is extremely challenging, as it requires understanding long chunks of raw code and deliberately simulating code execution. To this end, we introduce BigCodeArena, an open human evaluation platform for code generation backed by a comprehensive and on-the-fly execution environment. Built on top of Chatbot Arena, BigCodeArena enables the execution of LLM-generated code and allows humans to interact with the execution process and outcomes. We collected over 14,000 raw code-centric conversation sessions across 10 widely used LLMs, spanning 10 languages and 8 types of execution environments. Among these conversations, we identified more than 4,700 multi-turn samples with pairwise human preferences. Further analysis uncovers underexplored preferences of LLMs in fine-grained domains characterized by tasks, languages, and frameworks. To systematically examine code understanding and generation capabilities of frontier LLMs, we curated two benchmarks based on the collected data, namely BigCodeReward and AutoCodeArena. For BigCodeReward, we post-processed the 4,700 conversations and evaluated the consistency between reward models and human preferences. The evaluation shows that most LLMs have superior performance in judging coding preferences when the execution results are available. Inspired by these findings, we propose AutoCodeArena, an automatic Elo rating benchmark designed to assess the coding quality of LLMs without human involvement. We find that proprietary LLMs like GPT-5, Claude-Sonnet-4, and Claude-Opus-4 still lead in code generation performance among recent emerging models.

cs.SE · cs.AI · cs.CL

版本更新 · v3arXiv:2607.12753

RFMSR: Residual Flow Matching for Image Super-Resolution

Shuwei Huang, Tianyao Luo, Jicheng Liu

原文摘要

Generative image super-resolution (ISR) methods typically sample from a standard Gaussian prior and transport the sample to the data distribution, where the low-quality (LQ) input serves only as an external condition. However, the LQ image already carries rich structural information about the target high-quality (HQ) image, which makes a distribution approximating the LQ image a more suitable starting point, an idea that has been validated by a series of diffusion-based restoration methods. In contrast, recent flow-matching-based ISR methods still adopt the standard Gaussian prior and thereby discard such structural priors; moreover, existing single-step acceleration techniques, such as distillation and consistency training, either depend on an additional teacher or sacrifice the model's multi-step inference capability. In this paper, we propose Residual Flow Matching for Image Super-Resolution (RFMSR), which defines the source distribution as a Gaussian centered at the LQ latent, so that the flow starts from the LQ image rather than from pure noise and preserves the structural priors already present in the input. To achieve high-quality single-step generation, we further propose a simple yet effective training strategy that combines the supervision loss on the single-step output with the conditional flow matching (CFM) loss, enabling high-quality restoration with an arbitrary number of steps without resorting to distillation or other acceleration techniques. Extensive experiments show that RFMSR achieves competitive results against state-of-the-art methods. The source code is available at https://github.com/Faze-Hsw/RFMSR.

cs.CV

版本更新 · v2arXiv:2610.20579

PingpongDuo: Agile Humanoid Table Tennis Doubles with Safe Team Coordination

Haoran Jiang, Yichao Zhong, Kai Zhang, Cheng Liu, Yixuan Pan, Zhenjie Yang, Jingbo Wang, Tianyu Li 等 9 位作者

原文摘要

Unlike singles, humanoid table tennis doubles requires teammates to strike in strict alternation while sharing a confined workspace. Rapid repositioning can compromise striking accuracy, while uncoordinated teammate movements introduce collision risks. We present PingpongDuo, a hierarchical framework for agile humanoid doubles with safe team coordination. At the team level, a planner jointly selects positioning targets and uses learned risk estimates to filter risky proposals, preferentially preserving the current striker's target. At the individual level, separate footwork and striking skills combine agile movement with precise racket control. The skills are guided by human motion references, including footwork collected from human doubles play, and trained from states produced by one another to support rapid transitions. A racket-arm residual further refines strikes after movement using return feedback from a simulator calibrated with real ball-flight and contact measurements. In simulation, PingpongDuo improves the ball-return success rate by 13.2% over the state-of-the-art baseline, while achieving approximately 2 cm positioning error during clearance. In real-world experiments, a robot completes a 2.15 m clearance-and-recovery cycle in 2.4 s with a peak speed of 2.23 m/s, while two robots sustain more than 10 consecutive strikes in strict alternation.

cs.RO

版本更新 · v2arXiv:2608.07314

TEMPO:面向视觉-语言-动作模型的语义-动作解耦强化学习后训练

TEMPO: Semantic-Action Decoupled RL Post-Training for Vision-Language-Action Models

Ziheng Liu, Quantao Yang

AI 速读 基于摘要

TEMPO 提出一种语义与动作解耦的双时间尺度强化学习后训练框架,冻结预训练视觉-语言主干,分别以不同频率更新语义投影层和动作专家,以缓解潜在动作漂移并提升策略性能。

cs.RO · cs.CV

查看原文摘要

Vision-language-action (VLA) models are commonly adapted to downstream manipulation tasks via supervised fine-tuning (SFT) or online reinforcement learning(RL) post-training. SFT is prone to distribution mismatch, and existing RL approaches typically optimize all trainable components within a single RL loop at a uniform update rate, although these components play distinct functional roles. We propose TEMPO, a semantic-action decoupled, two-timescale RL post-training framework for VLA models. TEMPO freezes the pretrained vision-language backbone and adapts two components with dedicated RL loops: the semantic projection layer, which produces the latent action conditioning the action expert, and the low-level action expert itself. The semantic projection layer is updated infrequently and the action expert frequently, which aims to limit latent-action drift while allowing the action expert to learn from online feedback. Our analyses show that, compared with equal update frequencies, less frequent semantic updates reduce latent-action drift and improve policy performance. Experiments on the CALVIN benchmark and real-world manipulation tasks demonstrate that TEMPO outperforms both pretrained state-of-the-art VLA models and the RL post-training baseline, while reaching and maintaining higher evaluation rewards on three real-world tasks.

新论文 · v1arXiv:2611.16589

STVLA: Spatial-aware and Temporal-memory forVision-Language-Action Models

Zhuo Han, Yeqiang Wang, Xinran Wang, Hongwei Han, Yi Xiong, Zunian Wan, Jianbo Mao, Huan Peng 等 11 位作者

原文摘要

Robotic manipulation often requires both spatial scene understanding and task history. However, many vision-language-action (VLA) policies rely primarily on current observations, without explicitly integrating spatial structure and task history. Appearance-based memories can be sensitive to occlusion and viewpoint changes, while spatial representations of the current scene alone do not preserve how the scene has changed during task execution. We introduce STVLA, a framework that incorporates features from a pretrained visual geometry foundation model into temporal memory alongside visual representations. This allows the policy to recall past scene structure as context for current action decisions. To select informative history, STVLA uses a mathematically grounded scoring rule that balances relevance to the current observation with complementary evidence from memory. Across evaluations on LIBERO, LIBERO-Mem, MIKASA-Robo, and SimplerEnv Bridge, STVLA achieves the highest average success rate among the compared methods on each benchmark. On real-world block stacking, object organization, and phone packaging, it improves success over $π_{0.5}$ by $58.33$, $30.00$, and $35.00$ percentage points, respectively. These results support integrating scene geometry into temporal memory to improve manipulation requiring both spatial precision and task history. Project website: \href{https://stvla.github.io/}{https://stvla.github.io/}

cs.RO

新论文 · v1arXiv:2611.16517

UniSpark: Exploring Hybrid Attention for Multimodal Understanding and Generation

Jiancheng Pan, Yuzheng Liu, Hengyuan Cao, Qiyuan Zhang, Yangyan Li, Biao Gong, Zheng Zhang, Ka Long Cheng 等 10 位作者

原文摘要

We present UniSpark-9B, a unified multimodal model that investigates hybrid attention for visual understanding and generation. Built on a Mixture-of-Transformer-Experts backbone with approximately 9B parameters in each branch, UniSpark combines full attention for explicit token interactions with GatedDeltaNet linear attention for compact context propagation. Autoregressive text prediction and visual flow matching jointly support visual question answering, text-to-image generation, instruction-guided editing, and interleaved text-image prediction. In interleaved generation, noisy visual targets are isolated from subsequent predictions, while clean visual representations provide context for later outputs. A blockwise protocol enforces this distinction through attention masks in full-attention layers and recurrent-state retention rules in linear-attention layers. The selected training sources contain 159.7M generation samples, 213.4M understanding samples, and 624.8K interleaved sequences. A four-stage curriculum jointly trains multimodal understanding and visual generation, refining answer accuracy and instruction following while extending image synthesis to 2K. UniSpark scores 2470.3 on MME-S and 0.83 on GenEval. Qualitative examples further illustrate its capabilities in interleaved image generation, video synthesis, and video editing. Together, these results demonstrate that hybrid attention provides an effective backbone for unified multimodal understanding and generation.

cs.CV

新论文 · v1arXiv:2611.15490

ActionCodec2: A Streaming Action Tokenizer

Zibin Dong, Yicheng Liu, Shiduo Zhang, Tianyuan Yuan, Baijun Ye, Jinqiu Wang, Hang Zhao

原文摘要

Most action tokenizers for autoregressive vision language action (VLA) models compress motion into chunks that must be decoded in full before their actions become executable. We introduce ActionCodec2, a non-neural streaming tokenizer that releases actions incrementally while keeping trajectory reconstruction error within a prescribed tolerance. Its encoder quantizes each step relative to the decoder's reconstructed state, so the selected motion primitive corrects residual error rather than allowing errors from independently quantized increments to accumulate. Finding the smallest such primitive set is a geometric covering problem; we derive the exact minimum for translation and constant-factor-tight bounds for rotation. Set-BPE then losslessly merges co-occurring primitive symbols across coordinates and neighboring steps, without a fixed coordinate ordering. A universal version fitted on 20k hours of data from 24 embodiments averages 8.8 tokens per second for 15 Hz end-effector motion on this corpus. With the same VLA backbone, ActionCodec2 outperforms the compared tokenizers on three simulation benchmarks and in zero-shot real-robot evaluation. Its streaming representation allows policies to incorporate state feedback within an action chunk, substantially improving performance over open-loop execution under randomized dynamics, external disturbances, and moving objects. The same tokens also can serve as a direct control interface for VLM agents, which compose successful action sequences into reusable macros. These agent-built macros reduce control decisions and thinking-token usage across attempts and transfer to a held-out task. More results are available at https://zibindong.github.io/actioncodec2-page/

cs.RO

新论文 · v1arXiv:2611.15234

Schedule-Calibrated Commitment Order in Blockwise Masked Diffusion Language Models

Gaurav Sarkar, Umang Pandey, Pratik Prabhanjan Brahma, Zicheng Liu, Emad Barsoum

原文摘要

Sequential block schedules can make token commitment in masked diffusion language models appear strongly left-to-right even when within-block order is random or reversed. For equal contiguous blocks processed without interleaving in positional order, with untied irreversible commitments, we use a Spearman-rank identity to express global position-commitment correlation as a deterministic schedule reference plus a weighted mean within-block correlation. In a reported paired study of LLaDA-8B-Instruct on 500 math and code prompts with 256 generated positions and updates, increasing block size from 64 to 128 lowers mean global correlation from 0.9845 to 0.9149. Uniform-random within-block references are already 0.9375 and 0.7500. After calibration, mean within-block correlations are 0.751 and 0.660, so the larger raw residual at block size 128 does not indicate stronger local positional ordering. We give sharp bounds and derive calibrated intervals from reported summaries, while documenting the limitations of the aggregate-only empirical release. The analysis supports schedule-aware interpretation of commitment order; its empirical scope is one checkpoint and two schedules, without evaluation of output quality or inference speed.

cs.LG · cs.CL

新论文 · v1arXiv:2611.15049

Science Prediction Universe

Zengji Tu, Xiang Liu, Jiarui Sun, Ruoyu Wu, Zhihui Qi, Chengda Wu, Yutao Zhou, Bo Yang 等 36 位作者

原文摘要

Humanity has long sought to explain natural phenomena. Reliable prediction of experimental outcomes is a central test of our understanding of the processes that produce them. If artificial general intelligence (AGI) is to surpass human scientific capabilities, it must also predict experimental outcomes more reliably than humans. Such capabilities could accelerate scientific discovery across disciplines, help address humanity's most pressing challenges, and improve human well-being. We introduce Science Prediction Universe (SPU), a benchmark of hidden experimental outcomes with 100 public verified tasks from chemistry, materials science, biology and medicine, and 16 private tasks from unpublished wet-lab experiments. Given an experimental setup and candidate conditions, an agent works with any resources it needs to rank the candidates by a measured outcome. We evaluate thirteen agent configurations spanning twelve frontier models across two harnesses (Codex and Claude Code). Current agents remain far from saturating wet-lab outcome prediction, with substantial performance disparities across models: on the public benchmark, configurations separate into two distinct tiers, with task-adjusted Spearman correlations ranging from 0.227 for the lowest-performing configuration to 0.478 for the best. Analysis of 1,155 scored public trajectories (227,103 tool calls) suggests that the bottleneck lies in scientific judgment rather than tool execution: agents rely on shared monotone priors, agreeing far more with one another than with experimental reality (0.52 vs. 0.33), and frequently compute trivial physical or chemical proxies that do not influence the final outcome.

cs.AI · cs.CL

版本更新 · v2arXiv:2603.01478

Contract-Theoretic Semantic Abstraction for Covert Communication in LAENets

Yansheng Liu, Jinbo Wen, Kun Zhu, Hui Li, Yang Zhang, Jiawen Kang

原文摘要

In Low-Altitude Economy Networks (LAENets), Unmanned Aerial Vehicles (UAVs) transmit task-related information to the Base Station (BS) under stringent low-probability-of-detection constraints. These constraints limit transmission resources, hindering reliable information delivery through conventional bit-level communication. Semantic Communication (SemCom) addresses this challenge by prioritizing task-relevant information over bit-level accuracy. However, semantic abstraction must balance information loss and redundancy to preserve task reliability and transmission efficiency. Moreover, the BS cannot directly observe or reliably verify UAVs' semantic processing capabilities and abstraction-dependent transmission costs, leading to information asymmetry. We propose an incentive-aware semantic abstraction framework for covert communications in LAENets. Specifically, we adjust UAV-side semantic abstraction levels to provide differentiated covert semantic services under fixed-dimensional transmission payloads. To address information asymmetry, we develop a contract-theoretic model and adopt Prospect Theory (PT) to capture risk-sensitive semantic abstraction decisions under uncertainty. We further design a Regularized Diffusion-based Soft Actor-Critic (RDSAC) algorithm for optimal contract design under PT, incorporating diffusion entropy and action entropy regularization. Numerical results validate the proposed framework and show that RDSAC improves average rewards by 6.77% over SAC and 31.78% over proximal policy optimization.

cs.NI

新论文 · v1arXiv:2611.14257

Elastic-WAM:面向高效机器人控制的自适应时空想象

Elastic-WAM: Adaptive Spatiotemporal Imagination for Efficient Robot Control

Haitian Li, Tianfu Li, Xuxi Zhao, Zizheng Liu, Yangcheng Yu, Yiwen Hou, Zeyu Xiao, Mutian Xu 等 11 位作者

AI 速读 基于摘要

提出 Elastic-WAM,用统一时空细化需求场自适应分配世界模型的计算,在降低推理开销的同时提升机器人控制表现。

cs.RO · cs.CV

查看原文摘要

World-Action Models improve robot control by predicting future visual dynamics, but iterative video denoising incurs substantial inference overhead. Recent approaches reduce this cost through partial future denoising, yet typically rely on fixed refinement budgets. Our empirical observations reveal that preferred refinement depths vary across tasks and states, while different future regions exhibit varying relevance to action generation. Motivated by these findings, we propose Elastic-WAM, which adaptively allocates world refinement computation across temporal denoising time and spatial future space. A unified spatiotemporal refinement demand field governs when to stop world refinement, how far to advance each denoising step, and which regions to refresh. We parameterize this field with a shared temporal basis and spatial amplitudes, and learn it through a three-stage action-grounded supervised procedure. At inference, the learned field guides recurrent sparse world refinement to improve task success while reducing inference overhead. Evaluations across diverse simulation benchmarks and real-world long-horizon manipulation demonstrate state-of-the-art control performance with reduced inference latency.

版本更新 · v2arXiv:2611.09672

ODEAction: From Predicting Chunks to Evolving Actions

Qishen Wang, Pengxiang Ding, Shifeng Bao, Mingyang Sun, Hengtao Li, Yi Gao, Baohua Yin, Yang Liu 等 17 位作者

原文摘要

Vision-language-action (VLA) models typically generate actions in chunks, dividing continuous robot execution into separately predicted action chunks, which can introduce discontinuities at chunk boundaries. We propose ODEAction, a chunk-free action generation paradigm that replaces action chunk prediction with Continuous Action Evolution. We use an ordinary differential equation (ODE) to describe the continuous evolution of actions, and define the vector field of this ODE as the Action Transition Field to characterize how actions evolve with respect to evolution time. During inference, the model takes the current action as the initial condition and numerically solves the ODE defined by the learned Action Transition Field, thereby recursively generating subsequent actions with explicit dependencies. ODEAction is implemented as a modular action head that can be integrated with different vision-language backbones. Experiments on LIBERO, EBench, RoboTwin, and real-robot tasks show that, compared with action-chunk-based baselines, ODEAction improves both task performance and trajectory quality, with particularly pronounced gains on fine manipulation tasks.

cs.RO

版本更新 · v2arXiv:2609.36630

A Comprehensive Survey of Agent Distillation across Models, Artifacts, and Harnesses

Ziluowen Luo, Senzhang Wang, Chaozhuo Li, Jun Yin, Hao Yan, Ming Cheng, Chenxu Wang, Songyang Liu 等 13 位作者

原文摘要

Knowledge distillation provides a teacher-student framework for transferring capabilities at reduced cost and has been widely studied for large language models (LLMs). As LLM-based agents move from response generation to sustained, closed-loop task solving, distillation expands beyond model parameters to knowledge retained in reusable resources and execution workflows. This shift from model-level to agent-level knowledge transfer supports efficient deployment, broader capability access, and continual self-evolution. However, existing surveys largely examine model distillation and agent system design separately, limiting comparison of transfer strategies across agent components. To bridge this gap, we formalize Agent Distillation as persistent knowledge transfer between teacher and student agents and present its first unified survey. Distinguishing experience used for transfer from knowledge retained for reuse, we develop a knowledge-substrate taxonomy based on where knowledge persists: models, artifacts, or harnesses. Building on this taxonomy, we analyze cross-substrate transfer paths and hybrid strategies. To assess the resulting capabilities, we review benchmarks and evaluation protocols for retention, causal attribution, and deployed utility without further teacher support. This survey provides a unified basis for studying agent knowledge transfer and developing efficient, adaptable, and self-evolving agents.

cs.AI

新论文 · v1arXiv:2611.12014

Benchmarking language models and agents for scientific reasoning in evolving materials laboratories

Xuyu Dong, Yixuan Li, Jianguo Huang, Feng Chen, Yiyun Zhou, Bo An, Zheng Liu, Da Shu

原文摘要

Large language models and the multi-agent systems built around them could accelerate materials discovery by connecting scientific knowledge with experimental decisions. Existing benchmarks establish capabilities in domain knowledge, multimodal interpretation and scientific tool use. As language models increasingly support materials research workflows, their ability to distinguish closely related material states and reason accurately with quantitative evidence remains insufficiently evaluated. These abilities are essential for comparing material responses, assessing mechanisms and maintaining reliable judgements as experimental evidence accumulates. We introduce MatScope to evaluate three connected capabilities. M1 tests unaided, condition-specific reasoning through 200 tasks spanning ten research functions, using aluminium and high-entropy alloys as representative material systems. M2 tests agent-assisted transfer of related knowledge to unresolved materials questions. MatEvoBench-20 tests initial forecasts across scientific dependency chains and revisions of still-hidden responses as observations accumulate. Across eleven model deployments, including GPT-6 Astra and Claude Fable 5.1, given-input calculations and many physical explanations are handled well. Fine-grained response estimates, comparisons between similar states and quantitatively supported choices remain substantially weaker. Related literature improves selected estimates, while condition and baseline mismatches limit transfer. Progressive observations calibrate some downstream responses and destabilize earlier accurate predictions. MatScope establishes measurable targets for developing reliable scientific reasoning in future self-evolving materials laboratories and materials-aware world models.

cs.AI · cond-mat.mtrl-sci · cs.CE · cs.LG

版本更新 · v2arXiv:2610.12289

TestPrism: Rethinking Test Evaluation Beyond a Single Reference

Han Li, Lingxiang Hu, Jiacheng Huang, Ziqian Jiang, Jingkai Luo, Wei Gao, Yunfan Tan, Zun Wang 等 9 位作者

原文摘要

Large language model (LLM) coding agents have advanced test generation across diverse programming tasks. However, the common practice of evaluating tests against a single reference solution overlooks alternative valid implementations and can overstate test quality. We introduce TestPrism, comprising 300 test tasks from 17 sources and 3000 candidate implementations, evenly split between valid and invalid solutions. Its primary metric, Joint Success Function, requires the generated tests to fail on the initial program state, accept every valid candidate, and reject every invalid candidate. Across fourteen baseline coding agent configurations, Joint Success Function reaches only 28.00%, whereas single reference success reaches 59.67%. Our analysis reveals missed behaviors, unsupported assertions, and faulty test construction. To address these weaknesses, we introduce TestHelix, which combines heterogeneous synthesis of test and repair pairs with peer cross validation and recursive self improvement (RSI). Across two models, TestHelix improves Joint Success Function by 8.67 to 9.00 percentage points over the native harness comparators in the TestHelix evaluation

cs.SE

新论文 · v1arXiv:2611.11355

Attacking Slide Puzzle CAPTCHAs Based on Time and Space Generative Adversarial Networks

Rui Guo, Xuelian Xie, Botao Xu, Kesheng Liu, Wenxian Wang, Haizhou Wang

原文摘要

CAPTCHAs can protect websites from malicious attacks. As a typical representative of behavior CAPTCHAs, slide puzzle CAPTCHAs have become increasingly popular in recent years due to their user-friendliness and high security. Previous attack methods on slide puzzle CAPTCHA mainly face challenges in the following four aspects. (1) The defense mechanisms of previous slide puzzle CAPTCHAs were relatively simple. The current slide puzzle CAPTCHAs have added complex interferences, detected slide trajectory features in the two-dimensional space, and added other defense mechanisms. (2) The previous notch detection methods were difficult to accurately locate the notch positions. (3) Previous attack trajectories were limited to the horizontal dimension, making them impossible to pass the existing detection. (4) The previous attack trajectories were generated by fitting functions, which were relatively simple and could not well simulate the slide characteristics of human users. In response to the above challenges, firstly, we systematically analyze the defense strategies of six most popular slide puzzle CAPTCHAs: Capy, Dingxiang, Geetest, Kyger, Shumei and Tencent. Secondly, for each type of CAPTCHA, we construct a notch detection dataset and a slide trajectory dataset separately. Thirdly, we use advanced YOLOv11 to detect the notch positions and train generative adversarial networks (GAN) to generate attack trajectories. As far as we know, we are the first to generate attack trajectories by directly learning human slide trajectory characteristic. According to the experimental results, this method cracked six most popular slide puzzle CAPTCHAs with success rates of over 90\%, and the attack time is only about 5 seconds, indicating that the security of existing slide puzzle CAPTCHAs is facing challenge. At the same time, we propose various methods to enhance the security of slide puzzle CAPTCHAs.

cs.CR

版本更新 · v2arXiv:2606.21023

Demystifying Numerical Instability in LLM Inference: Achieving Reproducible Inference for Mission-Critical Tasks with HEAL

Zhenting Zhu, Lucas Thai, Shan Yu, Yicheng Liu, Yifan Qiao, Chenxi Wang, Harry Xu, Junyi Shu

原文摘要

As Large Language Models (LLMs) deploy into mission-critical domains (e.g., finance, medicine, and law), output reproducibility has become a strict system requirement. While practitioners use greedy decoding to eliminate algorithmic stochasticity, empirical deployments with 16-bit precisions still exhibit catastrophic output divergence across heterogeneous GPUs. Through SASS-level profiling, we reveal that this inconsistency is fundamentally driven by truncation errors introduced during downcasting at kernel boundaries. However, achieving reproducibility via a global FP32 pipeline incurs prohibitive system penalties: bypassing 16-bit hardware accelerators hurts compute efficiency, while upcasting the KV cache doubles memory overhead. To bridge this gap, we propose Hybrid Error ALleviation (HEAL), a targeted intervention that approximates FP32 precision while resolving hardware constraints through two targeted mechanisms. First, recognizing that floating-point formats underutilize their bit-width for Q, K, V tensors, HEAL applies INT16 quantization that preserves numerical stability without expanding the KV cache footprint. Second, HEAL synthesizes high-precision matrix multiplications via an algebraic error compensation strategy, executing entirely on high-throughput 16-bit Tensor Cores. To evaluate our approach practically, we introduce MCR-Bench, a benchmark targeting reproducibility in mission-critical tasks. HEAL achieves the same level of reproducibility on downstream tasks as the FP32 baseline while reducing the performance overhead by up to 6.0$\times$.

cs.LG