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

+0新增论文
+0其中 AI 相关
+0已有论文修订
+92新增 AI 导读

arXiv 最近完成扫描:2026-11-23 01:07 · 全站最近入库:2026-11-21 12:19各信源进度 →

统计口径与数据新鲜度

统计 2026-11-22 04:08 — 2026-11-23 04:08(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:2026-11-23 01:07最近发现新增版本:2026-11-21 12:19库内论文最新更新时间:2026-11-20 02:59

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

29,158 已收录论文24,181 AI 相关8,992 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 8 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-23 01:05(北京时间)
新论文 · v1arXiv:2611.26385

超越汇点解释:基于流的VLA策略中的径向注意力

Beyond the Sink Interpretation: Radial Attention in Flow-Based VLA Policies

Yuxi Zheng, Yueqian Lin, Yudong Liu, Zijia Tang, Junyu Pan, Yiheng Wang, Hai Helen Li, Yiran Chen

AI 速读 基于摘要

作者在单个π0.5检查点上检验了流式VLA策略中首尾动作令牌的高注意力是否构成“汇点”,发现它们不符合汇点特征,而前缀BOS令牌才符合,且相对偏移路由能保持动作令牌的分散性和闭环成功率。

cs.RO

查看原文摘要

Prior work calls the high attention on the first and last action tokens of a flow-based VLA policy a radial action sink, and uses these tokens to set the execution horizon. In language models, a sink is a token with high incoming attention, a small value, and little effect on the output. We test whether that profile holds, not the horizon rule, in one $π_{0.5}$ checkpoint on five RoboCasa tasks. The two endpoints receive 5.4% of action-key mass, 1.4 percentage points above their uniform share, and rotary positional encoding produces this excess: directly in shallow layers and through upstream action-token RoPE deeper in the network. The endpoints do not fit the sink profile. Their value norms stay near the action-token mean in all 18 layers. On 250 paired episodes, masking them or zeroing their values changes success by less than 4 points, and replacing their value directions with those of another observation lowers it by 3.2 to 7.2 points across three donors, whereas the same replacement on two non-endpoint tokens in the executed prefix lowers it by 28.4 points. The token that does fit the sink profile on mass and value norm is the prefix BOS; on this checkpoint, zeroing its value raises success in two paired runs, by +13.2 points (95% CI [+7.0, +19.4]) and +6.0 points ([+0.2, +11.8]). Inside the action chunk, a relative-offset routing profile estimated on other tasks keeps 75% of action-token spread and keeps closed-loop success on three held-out tasks (42.7% against a 38.7% baseline), while uniform or shuffled routing drops success to 3-4%. High attention mass alone does not tell what a token does.

新论文 · v1arXiv:2611.25649

KeyMem: Temporal Occupancy Control for Robust Streaming VideoLLM Memory

Wei Song, Yuxin Cao, Xiao Cheng, Christy Jie Liang, Xi Zheng, Leo Yu Zhang

原文摘要

Streaming VideoLLMs retain a bounded cache of visual tokens. Yet score-based eviction lets the stream determine its own temporal occupancy, so a short salient segment can monopolize the cache and displace evidence needed later. We identify this uncontrolled temporal occupancy as a fundamental limitation and introduce KeyMem, a training-free wrapper that rank-normalizes any base score, divides the video stream into fixed-duration temporal buckets and limits how many visual tokens each bucket can retain, and optionally samples survivors with a secret key. This hard cap bounds a segment's memory share from its first chunk. On Qwen2.5-VL-7B, 20 s of burned-in captions occupies 84% of an 8 s memory and lowers accuracy over all clips from 79.4% to 58.3%. Across five natural stressors, three VideoLLMs and two budgets, temporal quotas raise the worst accuracy of attention-based retention at the smaller budget from 42.2% to 73.3-76.1% and exceed that of InfiniPot-V by 6.1-16.7% on two of the three models. Deterministic and keyed quotas perform comparably under natural stress. Under an adaptive adversary, a secret key preserves 4.4-9.5% more early-clip accuracy than a leaked key, but does not consistently beat the best deterministic quota. A decide-once variant keeps old evidence that fresh draws erode. Temporal allocation is the primary robustness control, with secrecy reserved for adversarial predictability.

cs.CY

新论文 · v1arXiv:2611.23996

ReSynth: Constructing Synthetic Supervision for Multi-Image Understanding

Yilin Wang, Xin Yu, Xinyi Guo, Xiangxi Zheng, Dongxing Mao, Linjie Li, Zhengyuan Yang, Alex Jinpeng Wang

原文摘要

People often understand the world by comparing different views of it. Vision-language models (VLMs), however, receive these views as separate images and still struggle to relate them. One problem is data. Training on these tasks requires groups of images with a known relationship: the same object from different viewpoints, or the same scene before and after a change. Such examples are hard to collect at scale from existing photo collections. We introduce ReSynth, which turns single-image perception and controllable image generation into cross-image relational supervision. Localized editing produces before-and-after pairs, viewpoint generation produces multiple views of the same instance, and verified scene contents support comparisons of counts and attributes. ReSynth combines Qwen3-VL-8B's captioning, grounding, and counting capabilities with Qwen-Image-2.1's generation and editing capabilities. It verifies single-image facts such as object counts and attributes, then combines these facts to construct multi-image QA. Using GRPO on approximately 440K ReSynth questions, with no real images during training, Qwen2.5-VL-7B and Qwen3-VL-8B improve by 17.73 and 6.10 average points on BLINK, MUIRBench, and VLM2-Bench, while single-image performance is broadly preserved on Qwen2.5-VL-7B and improves across all four evaluated benchmarks on Qwen3-VL-8B. Notably, this supervision enables the 8B perception model itself to outperform Qwen3-VL-235B on BLINK and MUIRBench.

cs.CV

新论文 · v1arXiv:2611.23954

SimplePro: A Simple Baseline for Proactive Video Understanding

Yilin Wang, Xiangxi Zheng, Dongxing Mao, Linjie Li, Zhengyuan Yang, Alex Jinpeng Wang

原文摘要

Proactive video understanding requires vision-language models (VLMs) to decide not only what to answer as a video unfolds, but also when newly arrived evidence warrants a response and when to remain silent. Although modern VLMs excel at offline long-video understanding, they struggle in proactive streaming settings, leading prior work to introduce task-specific reinforcement learning or auxiliary triggering modules. We find that explicit reporting rules and structured streaming context substantially improve a frozen VLM's proactive response performance. We exploit this observation to build SIMPLEPRO, a training-free baseline for proactive video understanding. At each decision step, the model combines recent high-resolution frames, bounded historical observations, and prior answer records to determine whether new information warrants a response and, when needed, generate a concise answer. The system then filters consecutive duplicate answers while retaining the raw outputs as context for subsequent decisions. Without any parameter updates or auxiliary triggers, SIMPLEPRO with a 4B backbone consistently outperforms specialized proactive systems across OVO-Bench, StreamingBench-PO, and ProactiveVideoQA. SIMPLEPRO shows overall performance gains as backbone size increases from 2B to 32B. We hope this simple yet effective method will serve as a strong baseline for proactive video understanding, and we will release our code and inference pipeline to support future research.

cs.CV

新论文 · v1arXiv:2611.07882

Compositional Loop Invariant Inference for Multiphase Programs via Structured Neurosymbolic Reasoning

Mingxiu Wang, Jiawei Wang, Shuangxiang Kan, Angela Huo, Yuekang Li, Xi Zheng, Xiao Cheng

原文摘要

Loop invariants are essential for deductive program verification, yet automatically inferring them for {multiphase programs}, whose loops contain conditional branches that induce multiple execution phases with distinct behaviors, remains an open problem. Existing LLM-based methods either reason about loops as a whole or use explicit branch information to generate atomic assertions jointly across branches, without maintaining complete candidate sub-invariants for independent generation and targeted repair. We present CLOVER, a structured neurosymbolic reasoning framework for multiphase invariant inference built on two interlinked mechanisms. First, compositional inference: CLOVER statically decomposes a loop into symbolic {loop branch sequences}, conjunctions of the loop guard and branch conditions that characterize distinct execution scenarios, and guides the LLM to generate candidate sub-invariants for each one independently, so that each LLM query focuses on a single execution scenario rather than the entire loop. Second, counterexample-guided localized refinement: when SMT verification rejects a composed disjunctive invariant, CLOVER traces the counterexample back through the branch structure to identify which specific loop branch sequence caused the failure and repairs only that sub-invariant, preserving all correct components. Both mechanisms are unified by a shared symbolic structure derived from the loop's branch semantics, which guides what the LLM generates, how candidates are composed, and where refinement is directed. We evaluate CLOVER on 316 linear arithmetic, 50 nonlinear arithmetic, and 54 multiphase benchmarks. CLOVER solves 35 of 54 multiphase benchmarks, outperforming the best LLM-based baseline (29) by 20.7\% and the best traditional method (22) by 59.1\%. On linear/nonlinear benchmarks, CLOVER remains competitive, solving 355 of 366 programs overall.

cs.SE

新论文 · v1arXiv:2610.39547

Assuring Learning-Enabled Cyber-Physical Systems with Foundation Models: A Neuro-Symbolic Agenda for Testing, Verification, and Runtime Assurance

Xi Zheng, Ivan Ruchkin, Hong Jin Kang, Tevfik Bultan, Vijay Ganesh, Taylor T. Johnson, Ziyang Li, Lei Ma 等 14 位作者

原文摘要

Learning-enabled cyber-physical systems (CPS), including autonomous vehicles and UAVs, increasingly incorporate foundation models, yet fragmented assurance practices provide insufficient support for system-level guarantees. We argue that restoring engineering control across stochastic neural, symbolic, and physical boundaries requires a shift from model-centric evaluation to system-level assurance. We introduce the Foundation Model Assurance Stack, connecting three directions: (i) neuro-symbolic architectures that constrain foundation models through explicit symbolic world models, reasoning layers, and interfaces; (ii) semantically grounded, conformance-based testing that combines formal specifications and symbolic world models with foundation-model-assisted specification mining, scenario generation, and test synthesis; and (iii) compositional verification and runtime assurance that target formally tractable components and interfaces through modular contracts, equivalence checking, verified synthesis, uncertainty-aware reasoning, and runtime monitoring and enforcement. Symbolic abstractions establish assurance boundaries between stochastic learning and formal reasoning, connecting testing, verification, and runtime evidence across the system lifecycle. Foundation models serve as constrained assistants whose outputs are independently checked wherever correctness can be formally specified. We identify research challenges in specification engineering, abstraction fidelity, evidence composition, and lifecycle certification, and outline a staged agenda toward trustworthy, deployable, and certifiable learning-enabled CPS.

cs.RO · eess.SY

版本更新 · v2arXiv:2511.12863

Rethinking Data Value: Asymmetric Data Shapley for Structure-Aware Valuation in AI Model Markets

Xi Zheng, Yinghui Huang, Xiangyu Chang, Ruoxi Jia, Yong Tan

原文摘要

Modern AI model markets assemble models from heterogeneous pipeline contributions, including raw data, derivative data, and data-related services, whose value can depend on upstream inputs and inherited model states. Conventional valuation approaches focus on data contributions without explicitly accounting for these production relationships. They can therefore misattribute value by evaluating contributions outside their upstream production context. We formalize this pipeline-context valuation mismatch and develop Asymmetric Data Shapley (ADS), a unified framework for structure-aware value attribution. ADS translates documented production relationships into ordered valuation groups and evaluates contributions among peers conditional on their upstream production context. We provide an axiomatic characterization of the resulting allocation and quantify allocation uncertainty when evidence supports multiple valuation structures. To support valuation at larger scales or with costly utility evaluations, we develop a Monte Carlo estimator (MC-ADS) and a surrogate-assisted estimator (SA-MC-ADS). Experiments show that ignoring production dependencies systematically shifts value toward redundant derivative data and away from useful upstream data and services. Moreover, experiments on derivative data selection and on dataset procurement during multi-stage large language model fine-tuning show that decisions guided by ADS improve downstream model performance relative to the respective benchmarks.

cs.GT

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.1145ACL Anthology · ACL 2026

CharTide: Data-Centric Chart-to-Code Generation via Tri-Perspective Tuning and Inquiry-Driven Evolution

Xiangxi Zheng Nanjing Nniversity, Kuang He Shopee, Jiayi Hu East China Normal University, Ping Yu Nanjing University, Rui Yan Nanjing University of Science and Technology, Yuan Yao, Peng Hou Shopee, Anxiang Zeng Shopee 等 9 位作者

原文摘要

Chart-to-code generation demands strict visual precision and syntactic correctness from Vision-Language Models (VLMs). However, existing approaches are fundamentally constrained by data-centric limitations: despite the availability of growing chart-to-code datasets, simply scaling homogeneous chart-code pairs conflates visual perception with program logic, preventing models from fully leveraging the richness of multimodal supervision. We present CharTide, a novel data-centric framework that systematically redesigns both training and alignment data for chart-to-code generation. First, we construct a 2M-sample dataset via a Tri-Perspective Tuning strategy, explicitly decoupling training into visual perception, pure-text code logic, and modality fusion streams, enabling a 7B model to surpass specialized baselines using only supervised data. Second, we reformulate alignment as a data verification problem rather than a heuristic scoring task. To this end, we introduce an Inquiry-Driven RL framework grounded in the principle of information invariance: a downstream model should yield consistent answers to identical visual queries across both original and generated charts. Moving beyond rigid rule matching or VLM scoring, we employ a frozen Inspector to objectively verify generated charts through atomic QA tasks, providing verifiable reward signals based on answer accuracy. Experiments on ChartMimic, Plot2Code, and ChartX show that CharTide-7B/8B significantly outperforms open-source baselines, surpasses GPT-4o, and is competitive with GPT-5.

cs.CL · cs.CV

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表