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 02:35 — 2026-11-23 02:35(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 22 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:2611.25566

Diagnosis is not a policy: a state-transition audit of caoability-conditioned test-time inference

Yuchong Hu, Zhao Zhang, Kainan Liu, Haoyu Wang, Siyan Zhang, Jing Xiao

原文摘要

Test-time actions can satisfy retrieval, state-realization, program-consistency, or rendering objectives without correcting an answer. Test-time Error Response and Realizability Audit (TERRA) is an evaluation/auditing protocol, not a new inference algorithm. It uses a unified decomposition of intervention outcomes into applicability, target-state realization, endpoint translation, harm, and resource/inference cost. Paired comparisons fix the incoming state and evaluation conditions; cross-model analyses vary the receiving configuration. Executable financial reasoning experiments yield three findings: the same context expansion can harm one configuration and benefit another; sufficient evidence does not ensure correctness because configurations differ in evidence-to-answer translation; and diagnostic headroom---accuracy attainable with idealized diagnostic information over the measured baseline---plus local consistency does not ensure practical gains. Action value is $V(a\mid x,m)$, not diagnosis alone; diagnosis is not a deployable policy $π(a\mid x,m)$.

cs.AI

新论文 · v1arXiv:2611.24276

When Shuffling Fails: Token Recovery from Obfuscated KV Caches

Chengzhi Yi, Xiao Cheng, Wei Song, Haoyu Wang

原文摘要

LLM serving systems store, offload, and share KV caches, exposing token-level representations to infrastructure operators and co-tenants. Shuffled obfuscation combines secret linear transforms with fresh permutations, claiming security from b! possible shufflings. We show that input symmetry invalidates this counting argument: security depends on distinguishable outputs under chosen inputs. Repeated tokens produce identical first-layer Value rows, making every row permutation leave the data unchanged. Only auxiliary structures such as a single-row recovery marker vary, reducing the effective state space from b! to b. We construct Repeat-to-Reveal. The attacker collects the b distinguishable states from its own probes and exploits their rank-one differences to recover an equivalent denoiser without knowing the defender's secret parameters. A one-time calibration transfers across requests sharing the same secret epoch, enabling passive token-multiset recovery from subsequently observed cache blocks through public-model dictionary matching. We instantiate the attack on official KV-Cloak and evaluate 3,000 real WildChat user prompts across nine models and eleven configurations. The attack recovers the secret parameters with high accuracy and achieves 100 percent token-multiset recovery on GPU. Refreshing row-level secrets between epochs interrupts cross-request transfer, confirming secret reuse scope as the operative vulnerability. We further confirm orbit collapse on two other open-source defenses: the sequence-permutation implementation of Thomas et al. and PermLLM. The KV-Cloak developers invited a detailed report through their private vulnerability reporting channel.

cs.CR

版本更新 · v2arXiv:2611.11995

Infrathon: Benchmarking Language Agents for Real-World, Long-Horizon AI Infra Optimization

Zhengyu Hu, Zheyuan Xiao, Yike Wang, Hamish Ivison, Haoyu Wang, Yige Yuan, Rulin Shao, Yuetai Li 等 21 位作者

原文摘要

In this work, we study whether frontier agents can continually improve real-world AI infrastructure over long horizons. We introduce Infrathon, a benchmark of diverse, long-horizon AI infrastructure optimization tasks across different levels. We evaluate six models across 150 runs with 24-hour budgets, totaling over 10,000 GPU-hours. Our results show that model rankings vary with the evaluation horizon, while 135 of the 150 runs achieve further improvements during the second half of their budgets. These findings indicate that shorter evaluations can overlook both optimization gains and changes in relative model performance. We also find agents can discover solutions that outperform human-designed baselines: Claude Opus 5.5 increases the mean KV-cache compression ratio from $6.82\times$ with the human-designed Quant-VideoGen codec to $19.86\times$. Analysis of agent trajectories identifies task violations, unreliable testing, and premature completion as barriers to sustained improvement. Together, our Infrathon framework provides resources for constructing long-horizon tasks, evaluating frontier agents, and discovering good infrastructure solutions. Code is available at https://github.com/InfrathonX/Infrathon

cs.AI · cs.CL

版本更新 · v2arXiv:2603.27460

Project Imaging-X: A Survey of 1000+ Open-Access Medical Imaging Datasets for Foundation Model Development

Zhongying Deng, Cheng Tang, Ziyan Huang, Jiashi Lin, Ying Chen, Junzhi Ning, Chenglong Ma, Jiyao Liu 等 126 位作者

原文摘要

Foundation models have demonstrated remarkable success across diverse domains and tasks, primarily due to the thrive of large-scale, diverse, and high-quality datasets. However, in the field of medical imaging, the curation and assembling of such medical datasets are highly challenging due to the reliance on clinical expertise and strict ethical and privacy constraints, resulting in a scarcity of large-scale unified medical datasets and hindering the development of powerful medical foundation models. In this work, we present the largest survey to date of medical image datasets, covering over 1,000 open-access datasets with a systematic catalog of their modalities, tasks, anatomies, annotations, limitations, and potential for integration. Our analysis exposes a landscape that is modest in scale, fragmented across narrowly scoped tasks, and unevenly distributed across organs and modalities, which in turn limits the utility of existing medical image datasets for developing versatile and robust medical foundation models. To turn fragmentation into scale, we propose a metadata-driven fusion paradigm (MDFP) that integrates public datasets with shared modalities or tasks, thereby transforming multiple small data silos into larger, more coherent resources. Building on MDFP, we release an interactive discovery portal that enables end-to-end, automated medical image dataset integration, and compile all surveyed datasets into a unified, structured table that clearly summarizes their key characteristics and provides reference links, offering the community an accessible and comprehensive repository. By charting the current terrain and offering a principled path to dataset consolidation, our survey provides a practical roadmap for scaling medical imaging corpora, supporting faster data discovery, more principled dataset creation, and more capable medical foundation models.

cs.CV · cs.AI

新论文 · v1arXiv:2611.20837

Evidence Diet: When Graph Evidence Helps LLMs Rank Competing Candidates

Yuchong Hu, Zhao Zhang, Ziyao Zhao, Haoyu Wang, Jing Xiao

原文摘要

When several candidates have graph support, does it matter which candidate receives which supporter and path counts? We study how LLM rankers use collaborative evidence on Amazon Books and MovieTV. Swapping user-level evidence degrades ranking, while matched item substitutions have little effect. On fixed clean-trained checkpoints, unrelated catalog text lowers Hit@1 from 44.77% to 38.70%, with 99.9% of rankings still valid. Across all three paired seeds, the NDCG@5 difference between count and path prompts was larger after count training than after path training. Degree matching preserves target paths while giving more rivals support. Across the full degree-matched development pools, adding candidate-level graph records to history improves NDCG@5 by 2.28 points on Books and 2.54 on MovieTV. When the target and a rival both have support, path- and count-trained rankers benefit from retaining counts. On these development queries, adding counts numerically to history scores outperforms presenting them as text. For count-trained rankers, exchanging intact count pairs among supported candidates preserves support and token length, yet lowers NDCG@5 by 4.06 points on 141 Books queries and 3.26 on 104 MovieTV queries. A frozen evaluation on 274 previously unused Books users with supported targets and rivals confirms the attribution effect: correct assignment improves pairwise accuracy by 6.07 percentage points (95% CI [4.18, 8.00]).

cs.IR · cs.AI

版本更新 · v2arXiv:2601.17089

GRASP: Guided Region-Aware Sparse Prompting for Adapting MLLMs to Remote Sensing

Qigan Sun, Chaoning Zhang, Jianwei Zhang, Xudong Wang, Jiehui Xie, Pengcheng Zheng, Haoyu Wang, Sungyoung Lee 等 11 位作者

原文摘要

In recent years, Multimodal Large Language Models (MLLMs) have made significant progress in visual question answering tasks. However, directly applying existing fine-tuning methods to remote sensing (RS) images often leads to issues such as overfitting on background noise or neglecting target details. This is primarily due to the large-scale variations, sparse target distributions, and complex regional semantic features inherent in RS images. These challenges limit the effectiveness of MLLMs in RS tasks. To address these challenges, we propose a parameter-efficient fine-tuning (PEFT) strategy called Guided Region-Aware Sparse Prompting (GRASP). GRASP introduces spatially structured soft prompts associated with spatial blocks extracted from a frozen visual token grid. Through a question-guided sparse fusion mechanism, GRASP dynamically aggregates task-specific context into a compact global prompt, enabling the model to focus on relevant regions while filtering out background noise. Extensive experiments on multiple RSVQA benchmarks show that GRASP achieves competitive performance compared to existing fine-tuning and prompt-based methods while maintaining high parameter efficiency.

cs.CV

版本更新 · v2arXiv:2605.24366

SA-RAG: Structuring Noisy Conversations for Retrieval-Augmented Generation

Kaiqiao Han, LuAn Tang, Renliang Sun, Peng Yuan, Wei Cheng, Haoyu Wang, Wei Wang, Yizhou Sun 等 9 位作者

原文摘要

Large Language Models (LLMs) have been widely adopted in conversational applications. However, their reliance on parametric knowledge limits reliability in real-world scenarios that require dynamic or domain-specific information. Retrieval-Augmented Generation (RAG) addresses this limitation by incorporating external knowledge during generation, but existing RAG methods often struggle with noisy or irrelevant contexts, as they typically assume that high-quality structures are already available. In this work, we propose Structure-aware Retrieval-Augmented Generation (SA-RAG), a principled structure induction and generation framework that constructs reliable intermediate structures directly from noisy conversational data. SA-RAG uses tables as compact and controllable structured representations. We introduce a quality-aware structure induction framework that jointly models semantic and structural consistency. Furthermore, we explore both training-free and training-based structure generation strategies to further improve structure quality while maintaining fidelity. Experiments on two noisy real-world datasets show that SA-RAG significantly outperforms existing RAG baselines. Further analysis highlights that high-quality structural representations are crucial for robust RAG applications.

cs.CL · cs.LG

新论文 · v1arXiv:2611.16219

GC-MoE on SM120: Overlapping Expert-Parallel Token Dispatch with Warp-Level FP8xFP4 Block-Scaled MMA on Consumer Blackwell

Yong Li, Haoyu Wang, Kan Liu, Tao Lan

原文摘要

Expert-parallel Mixture-of-Experts decoding is latency bound: each layer serializes a token exchange, a grouped GEMM over routed experts, and a combine, while only a few tokens per rank are in flight. Prior GC-MoE fused these phases into one persistent, Green-Context-partitioned CUDA Graph on Hopper (SM90) and datacenter Blackwell (SM100). This paper rebuilds the operator for SM120 (compute capability 12.0, e.g. RTX PRO 5000) over PCIe. SM120 exposes block-scaled tensor cores only through warp-level mma.sync.aligned.kind::mxf8f6f4: no tensor memory, no two-CTA MMA, no cluster multicast. We rebuild the kernel around a swap-AB warp-level block-scaled MMA with FP4 weights in the register A operand and FP8 activations in B, plus SM120-specific mechanisms: scale-byte selection through MMA immediates, a compact-weights path, an adaptive token-tile geometry, an expert-granular streaming dispatch with a batched bulk-pull engine and a 64-bit deduplicating pull cache, full-width BF16 returns drained by resident relay copiers over a position-major arena, and shared experts folded into the compute role. On 8xRTX PRO 5000 over PCIe the operator is 1.522x and 1.387x faster than the FlashInfer CuTe DSL W4A8 MegaMoE and the Cake MegaMoE across 18 decode points (18/18 wins each), and 1.388x faster than Cake with shared experts fused; all 94 numerical cases and 752 per-rank checks pass, at cross-operator cosine similarity of at least 0.9999997.

cs.DC · cs.LG

新论文 · v1arXiv:2611.13684

BypassGym: A Benchmark for Evaluating AI Agents' Endpoint Defense Evasion Capabilities

Weifeng Yuan, Zifan Chen, Yucheng Zhang, Feng Dong, Peng Gao, Haoyu Wang

原文摘要

Artificial intelligence agents increasingly automate cybersecurity tasks, including offensive operations. Frequent attacks across the web make endpoint detection and response (EDR) a critical defense, but whether AI agents can evade it remains unclear. Benchmarks evaluate the offensive capabilities of large language model (LLM) agents in areas such as penetration testing and vulnerability discovery. One important capability that these benchmarks do not address is defense evasion, specifically whether an agent can develop a program that executes a payload without being blocked or terminated by a deployed EDR. We introduce BypassGym, to our knowledge the first benchmark to systematically evaluate this capability on real endpoints. Given command-and-control (C2) shellcode, an agent must generate and compile a loader that executes the payload without being blocked or terminated. A supplementary evasion knowledge skill provides domain knowledge and supports comparisons with and without this input. BypassGym is built on Proxmox VE(PVE), so the evaluation environment runs real Windows systems and EDR products inside virtual machines and returns structured detection feedback to the agent. We evaluate 5 lightweight model backends against 6 EDR products and 3 payloads, and find that even these simple models generate successful submissions, with DeepSeek-V4.1 Flash reaching 17/18 successful runs and Bitdefender allowing only 5 of 15 runs to pass. These results provide a systematic measurement of current AI agents' endpoint defense evasion capabilities and identify areas for defenders to investigate.

cs.CR

版本更新 · v2arXiv:2608.14863

DDBench: A Benchmark for Agentic Debugging on Distributed Systems

Yibo Yan, Huijuan Wang, Junzhou He, Yizhuo Liang, Shaoyu Wang, Huanchen Sun, Seo Jin Park

原文摘要

LLM-based coding agents have advanced rapidly on single-process SWE tasks, with frontier models now clustering in the high-70s on SWE-bench Verified. Distributed-system debugging, however, remains an under-explored regime: bugs span processes, nodes, and protocol interactions, with root causes rarely recoverable from source alone and brute-force exploration intractable across non-deterministic interleavings. This leaves two gaps in LLM and agent evaluation: no code-repair benchmark targets distributed-system bugs, and no controlled study isolates how much externally provided debugging context changes agent success on them. We introduce DDBench, a code-repair benchmark of 60 historical bugs mined from 13 open-source distributed systems, partitioned into three reasoning-scope tiers. DDBench evaluates every case under two matched conditions: a symptom-only condition where the agent receives only the bug symptom and repository, and a context-augmented condition where it additionally receives bounded debugging context (logs, traces, runtime state, and targeted code-investigation notes), isolating the effect of debugging context from model capability. The evaluation of 10 LLMs on DDBench reveals several findings. First, distributed debugging exercises a reasoning dimension that single-process benchmarks do not surface: models' pass rates span 45 pp, and pairwise bootstrap separates 6 of 15 top-tier model pairs at p < 0.05 on DDBench's hardest case-set. Second, bounded debugging context lifts aggregate pass rate by +19.0 pp, and the lift is asymmetric: weaker models gain more in pass rate, while stronger models gain more in efficiency. Third, debugging context requires careful curation, as even faithful debugging context can anchor a strong model on the wrong layer of the system when its observation sits far from the fault.

cs.SE · cs.AI · cs.DC

新论文 · v1arXiv:2611.09872

测试时强化学习中多数投票伪标签的可靠性研究

On the Reliability of Majority-Vote Pseudo-Labels in Test-Time Reinforcement Learning

Haoyu Wang, Ru Wang, Yuanyuan Wang, Jiaxian Guo, Mingming Gong

AI 速读 基于摘要

该论文分析TTRL中多数投票伪标签的误差来源,并提出PC-Dr.DPO方法以缓解有限采样波动带来的负面影响。

cs.AI

查看原文摘要

Test-time reinforcement learning (TTRL) adapts pretrained language models to unlabeled target-domain data using self-generated pseudo-labels, whose reliability remains poorly understood. We analyze majority-vote supervision for TTRL with online Direct Preference Optimization (DPO) and decompose its error into population-majority bias and prompt-dependent finite-rollout variation. Because population-majority bias is generally unidentifiable without external supervision, we focus on mitigating the downstream effects of finite-rollout variation. We propose \emph{Prompt-Conditional Distributionally Robust DPO (PC-Dr.DPO)}, which conditions within-prompt robust reweighting on observed vote reliability to make updates from sampling-sensitive prompts more conservative. We further introduce a cache-based mechanism to reduce self-supervised forgetting during online adaptation. Across six mathematical and knowledge-intensive reasoning benchmarks and five model backbones, PC-Dr.DPO matches or outperforms the strongest TTRL baseline in 24 of 30 settings.

版本更新 · v2arXiv:2609.13734

PolicyMem: Geometric Policy Memory for LLM Governance

Yuanchen Bei, Zhengzhang Chen, Yanjun Zhao, Haoyu Wang, Hanghang Tong, Haifeng Chen

原文摘要

Effective LLM governance extends beyond detecting unsafe responses to guiding their correction through closed-loop assessment, revision, and verification. Learning-based guards provide strong semantic discrimination but often leave policy knowledge implicit in trained parameters, limiting its explicit reuse across stages. Programmable guardrails make policies explicit through prompts and workflows, but rely heavily on manual engineering to operationalize them. This motivates explicit policy representations that are both learnable and reusable across governance operations. To this end, we introduce PolicyMem, a geometric policy memory that compiles natural-language policies into learnable low-rank subspaces for reuse across governance stages. A policy assessor projects query-response representations onto these subspaces, producing evidence that directly mediates safety judgments and policy attribution. A response rewriter uses the implicated policies to revise unsafe responses, with the same assessor re-evaluating the revised responses. Beyond inference, the same memory constructs training data from model-generated candidates to supervise the rewriter without external teacher calls. Across five widely used benchmarks, PolicyMem achieves the best average unsafe-behavior detection performance among representative baselines while supporting effective policy attribution, rewriting, and post-intervention assessment through the shared policy memory.

cs.CL · cs.AI

新论文 · v1arXiv:2611.02896

Bridging Low-Level Image Fusion and High-Level Semantic Understanding

Guangyuan Dong, Lingdong Shen, Xudong Zhang, Haodong Jing, Haoyu Wang, Zihao Li, Zonghao Ying, Ziyu Song 等 11 位作者

原文摘要

Remote sensing image fusion and semantic interpretation are usually optimized separately, so reconstruction quality need not preserve downstream retrieval utility. We propose LANCE, which uses structured language as an explicit, indexable semantic state. A frozen vision-language model maps the input to a closed-vocabulary text record; a language-conditioned generator fuses the imagery; and a dense verifier with a differentiable continuous summarizer re-describes the output. Text-text consistency and anti-collapse contrastive text-mask losses with negative queries close the loop without dense annotations or VLM fine-tuning. A variational EM formulation yields a per-step contraction result under regularity assumptions, distinguishing semantic faithfulness from verifier overfitting. Across seven test sets on GF2, QuickBird, WorldView-III, and WorldView-II, LANCE improves reduced-scale reference metrics by up to 11.7% (median 2.1%) over the strongest learning baseline. Independent evaluation using a held-out VLM and a supervised aerial detector yields gains of +6.4 mAP and +0.072 open-vocabulary F1 over the closest competitor. Text perturbations, cross-verifier transfer, and pseudo-RGB ablations examine the mechanisms underlying these gains. The framework connects image fusion to verifiable semantic representations for multimodal retrieval and knowledge management.

cs.AI · cs.IR

新论文 · v1arXiv:2611.01996

Safety4DM: A Vision-Language Framework for Risk-Aware Dynamic Maps in Vehicle-Road-Cloud Collaborative Driving

Zhengshu Zhou, Shaoyu Wang, Lu Tao, Xinhui Hu, Jiaqi Gu, Tingting Zhao

原文摘要

Dynamic map (DM) is a core information infrastructure for vehicle-road-cloud (VRC) cooperative autonomous driving. It fuses perception data from multiple sources to overcome the inherent line-of-sight and field-of-view limits of single-vehicle perception. However, DM still falls short on driving safety in two ways. First, DM data specifications already define road conditions semantically, but no pipeline yet turns real-world road observations into fine-grained risk entities in the DM. Second, existing DM systems lack a natural language interface for driving risks. To close these gaps, we propose Safety4DM, a safety-oriented language system for VRC dynamic maps. We first build RoadRisk, a real-world road image dataset that covers four types of road conditions and four risk levels. On this dataset, we fine-tune a vision-language model (VLM) for road safety risk perception. The model outputs structured risk representations that the DM can ingest directly. We then introduce a Safety-aware Step-wise Prompting (SafeStep) mechanism as the natural language query interface of the DM. SafeStep answers queries accurately and also generates actionable driving advice. To build and evaluate this interface, we develop SafeVRC-Sim, a VRC cooperative simulation framework, and SafeDM-QA, a safety question-answering benchmark. Experiments show that even the compact Qwen3-VL-4B reaches 89.83% accuracy on risk perception after fine-tuning. SafeStep also plugs easily into multiple LLM families. With medium and large models (20B and above) from five families, it achieves over 93% natural language query accuracy in every case, which shows strong generalization.

cs.AI

新论文 · v1arXiv:2611.01970

Knowledge-Guided Floodwater Level Reasoning for Cloud-Edge Collaborative Monitoring

Zhengshu Zhou, Shaoyu Wang, Ziyi Geng, Lu Tao, Qian Long

原文摘要

Frequent urban floodwater poses a serious threat to the safety and efficiency of intelligent transportation systems. Existing vision-based methods for floodwater level detection face two main limitations. First, the lack of explicit reasoning leads to poor detection performance and little interpretability. Second, these methods struggle to generalize to the complex and varied real-world road scenes seen from different viewpoints. To address this, we reformulate the task as an explicit visual reasoning problem and propose HydroReasoner, a floodwater level reasoning framework designed for cloud-edge collaboration. HydroReasoner builds on Qwen2.5-VL and is trained with Group Relative Policy Optimization. To address the scarcity of reasoning process annotations, we build a floodwater domain knowledge graph HydroKG and design a novel KG path reward. Through deterministic graph traversal over HydroKG, this reward supervises the model's reasoning process at a fine granularity, which improves both reasoning and generalization. For edge deployment, we apply 4-bit quantization to the model, cutting GPU memory usage by 57% and inference latency by 43% while out-of-domain accuracy drops by only 0.2 percentage points. We also propose a confidence-based cloud-edge routing mechanism, which improves system safety and eases the computational load on the cloud. In addition, we build HydroLevel, a floodwater benchmark dataset of 3,000 images, for training and evaluating the model. Experimental results show that HydroReasoner achieves detection accuracy 4.0 and 13.6 percentage points higher than conventional vision baselines in the in-domain and out-of-domain evaluations respectively, with performance dropping by only 4.4 percentage points out of domain.

cs.CV · cs.AI

版本更新 · v2arXiv:2610.34928

Beyond Compilation Feedback: Refining Vulnerability Checkers with Program-Analysis Evidence

Chengzhi Yi, Shenao Wang, Yanjie Zhao, Xiao Cheng, Haoyu Wang

原文摘要

Recent work shows that LLMs can synthesize static-analysis checkers from security patches, but a compilable checker is not necessarily a correct one. A patch reveals what changed, not why the change is safe, so generated checkers often match only the surface edit and miss the deeper semantic condition. Existing refinement loops feed back compilation errors and validation reports, yet these signals describe symptoms without explaining what the checker misunderstands about the code. We observe that the analysis framework itself already computes the information needed to close this gap. Control-flow graphs, symbolic values, memory regions and checker callbacks are available inside the analyzer but unused by current refinement strategies. SemWeaver is a plug-in refinement layer that extracts patch-relevant analyzer evidence and assembles it with source context and validation feedback into a structured, provenance-labelled bundle. An iterative editing loop refines the checker on both the vulnerable and fixed revisions, guarded by a retention gate that accepts warning recovery or false-positive reduction while preventing over-pruning. We evaluate SemWeaver on 39 KNighter-derived CSA checkers from Linux kernel fixes. With analyzer evidence, refinement reaches 23 warning-positive vulnerable revisions (vs. 15 for KNighter's loop) and raises version-level $F_1$ from 0.448 to 0.575. An ablation removing internal evidence recovers fewer silent cases and produces different checker edits, indicating that the two evidence configurations address complementary recognition gaps. Additional experiments cover three editor models on a 12-subject subset, a CodeQL query refinement, and controlled source-form variations. A qualitative follow-up on all 11 non-tied comparisons traces each warning-count change to a specific checker repair, such as recognizing a lowered callback or unwrapping an expression cast.

cs.SE

新论文 · v1arXiv:2610.39439

Timbre: Reliability-aware harmonic consensus for label-free multimodal test-time rexinforcement learning

Haotian Lyu, Haoyu Wang, Ru Wang, Feng Ji, Ziwen Li, Jiaxian Guo, Mingming Gong

原文摘要

Label-free test-time reinforcement learning adapts vision--language models using rewards derived from their own predictions. However, misinterpreted visual evidence and sensitivity to textual formulation can produce a consistent but incorrect consensus that majority voting reinforces. Cross-view aggregation can expose such errors, but image and text transformations may themselves degrade task-relevant evidence to different extents. We introduce \method, a reliability-aware harmonic consensus framework for multimodal test-time reinforcement learning. \method constructs a $2\times2$ grid combining original and perturbed images with direct-solving and reframing modes, selects pseudo-labels through weighted harmonic aggregation, and adapts modality-level weights using batch-averaged, temporally smoothed shifts in pseudo-label confidence as a heuristic reliability signal. We formulate consensus as a weighted $χ^2$-barycenter problem whose unique minimizer is the normalized weighted harmonic aggregate, without requiring correct-answer invariance. An exact support--dispersion decomposition characterizes when harmonic aggregation preserves or corrects arithmetic rankings, while a sensitivity analysis establishes how modality reweighting changes pairwise ranking margins, informing interpretation of the heuristic updates. Across six benchmarks and three Qwen3-VL model scales, \method outperforms TTRV in 16 of 18 benchmark--model settings on adaptation instances and 17 of 18 settings on held-out instances under matched estimation and optimization rollout counts. These results demonstrate improved target-task adaptation and transfer to unseen instances without further updates.

cs.AI

新论文 · v1arXiv:2610.36682

An Empirical Study of Undisclosed Charges in Hook-Based Decentralized Exchanges

Kai Ma, Tianle Sun, Shun Zhou, Boyao Yang, Ningyu He, Haoyu Wang

原文摘要

Many decentralized exchanges use automated market makers (AMMs) to trade assets against liquidity pools. Modern AMMs allow third-party contracts, called Hooks, to customize this process. However, Hooks can impose additional deductions that fee breakdowns based on standard pool parameters do not itemize. We present, to the best of our knowledge, the first large-scale empirical study of the production Hook ecosystem, focusing on these undisclosed settlement charges. Our study covers 7,873 Hook deployments, 50,011 pools, and 296M pool events on Uniswap v4 and PancakeSwap Infinity across Ethereum and BNB Smart Chain (BSC) through August 1, 2026. We develop a bytecode analysis that reconstructs how Hooks change traders' payments and receipts, separating charges from exchanged assets and standard fees. We then reconstruct historical settlements to measure charging frequency and economic burden. We find that direct settlement adjustment is the dominant Hook capability, supported by 71.37% of registered Hooks. Charging capability is widespread and often exercised: 24.30% of Hooks can impose undisclosed deductions, and these deductions occur in 59.23% of accounted swaps involving such Hooks. These charges generate millions of dollars in revenue, with $3.97M recorded across Hooks with available token prices. These findings reveal a gap between standard fee displays and actual trading costs, motivating explicit disclosure of Hook deductions alongside standard fees.

cs.CR

新论文 · v1arXiv:2610.35491

S$^2$-RL: Sample-Set Dual Reinforcement Learning for Generative Semantic Segmentation Dataset Distillation

Haoyu Wang, Fei Zhou, Qingqing Qiu, Lei Zhang, Wei Wei, Chen Ding

原文摘要

While dataset distillation has witnessed significant advances in image classification, its extension to dense prediction tasks such as semantic segmentation is plagued by two core bottlenecks: bi-level optimization-based approaches suffer from prohibitive computational costs stemming from pixel-wise gradient unrolling, whereas proxy-based generative methods merely infuse visual textures into fixed semantic masks derived from real data, thus failing to condense rich semantic knowledge into a compact set of informative, novel scene generations. To address both bottlenecks simultaneously, we propose a novel Sample-Set Reinforcement Learning (S$^2$-RL) framework for generative semantic segmentation dataset distillation (SSDD). Specifically, S$^2$-RL formulates SSDD as a diffusion model based text-to-image generation paradigm, enabling flexible generation of images with informative, novel semantic distributions via a concise text prompt. Furthermore, we fine-tune a diffusion policy via Group Relative Policy Optimization (GRPO), leveraging a sample-set dual reward paradigm: for individual samples, it enforces semantic alignment with input text prompts and intra-class feature diversity; for sample sets, it maximizes inter-sample semantic distribution diversity by solving a contextual multi-armed bandit problem. These design choices enable S$^2$-RL to distill large-scale semantic segmentation datasets into a compact set of generated samples that encapsulate diverse, informative semantic knowledge without the need of pixel-wise gradient unrolling. Extensive experiments on the ADE20K and COCO datasets demonstrate that S$^2$-RL achieves substantial and consistent improvements over state-of-the-art baselines, establishing a new benchmark for SSDD.

cs.CV

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.246ACL Anthology · ACL 2026

Representation Interventions Enable Lifelong Knowledge Memory Control in LLMs

Xuyuan Liu Dartmouth College, Shengyu Chen NEC Laboratories America Inc and University of Pittsburgh, Xinshuai Dong, Yanchi Liu NEC-Labs, Xujiang Zhao NEC Labs America, Haoyu Wang NEC Labs America, Yujun Yan Dartmouth College, Haifeng Chen NEC-Labs 等 9 位作者

原文摘要

Large language models (LLMs) often produce incorrect or outdated content. Updating their knowledge efficiently and accurately without costly retraining is a major challenge. This problem is particularly challenging for complex, unstructured knowledge in lifelong settings, where many edits must coexist without interference. We introduce RILKE (Representation Intervention for Lifelong KnowledgE Control), a robust and scalable method that treats knowledge control as interventions within the model’s representation space. Leveraging representation-space expressiveness, we identify two key properties enabling RILKE to achieve fine-grained control over complex, unstructured knowledge while maintaining general utility with frozen base weights. During training, RILKE learns paraphrase-robust and edit-localized modules that limit each update to a low-dimensional subspace to minimize cross-edit interference. In inference, a query-adaptive router selects the appropriate module to guide the model’s generation. Across LLaMA and Qwen models, RILKE scales effectively to large-scale benchmarks, demonstrating high edit success and strong paraphrase generalization while preserving general utility with modest memory overhead. These results show RILKE is an effective and scalable solution for lifelong knowledge control in LLMs.

cs.CL

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

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.411ACL Anthology · ACL 2026

Evaluating the Expressive Appropriateness of Speech in Rich Contexts

Tianrui Wang, Ziyang Ma, Yizhou Peng Nanyang Technological University, Haoyu Wang, Zhikang Niu, Zikang Huang, Yihao Wu, Yi-Wen Chao Nanyang Technological University 等 29 位作者

原文摘要

Evaluating expressive speech remains challenging, as existing methods mainly assess emotional intensity and overlook whether a speech sample is expressively appropriate for its contextual setting. This limitation hinders reliable evaluation of speech systems used in narrative-driven and interactive applications, such as audiobooks and conversational agents. We introduce CEAEval, a Context-rich framework for Evaluating Expressive Appropriateness in speech, which assesses whether a speech sample expressively aligns with the underlying communicative intent implied by its discourse-level narrative context. To support this task, we construct CEAEval-D, the first context-rich speech dataset with real human performances in Mandarin conversational speech, providing narrative descriptions together with fifteen dimensions of human annotations covering expressive attributes and expressive appropriateness. We further develop CEAEval-M, a model that integrates knowledge distillation, planner-based multi-model collaboration, adaptive audio attention bias, and reinforcement learning to perform context-rich expressive appropriateness evaluation. Experiments on a human-annotated test set demonstrate that CEAEval-M substantially outperforms existing speech evaluation and analysis systems.

cs.CL

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

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.791ACL Anthology · ACL 2026

OpenRubrics: Towards Scalable Synthetic Rubric Generation for Reward Modeling and LLM Alignment

Tianci Liu, Ran Xu Google DeepMind, Tony Yu DeepLab, Ilgee Hong Georgia Institute of Technology, Carl Yang Emory University, Tuo Zhao, Haoyu Wang State University of New York at Albany

原文摘要

Reward modeling lies at the core of reinforcement learning from human feedback (RLHF), yet most existing reward models rely on scalar or pairwise judgments that fail to capture the multifaceted nature of human preferences. Recent studies have explored rubrics-as-rewards (RaR) that uses structured criteria to capture multiple dimensions of response quality. However, producing rubrics that are both reliable and scalable remains a key challenge. In this work, we introduce OpenRubrics, a diverse, large-scale collection of (prompt, rubric) pairs for training rubric-generation and rubric-based reward models. To elicit discriminative and comprehensive evaluation signals, we introduce Contrastive Rubric Generation (CRG), which derives both hard rules (explicit constraints) and principles (implicit qualities) by contrasting preferred and rejected responses. We further remove noisy rubrics via preserving preference–label consistency. Across multiple reward-modeling benchmarks, our rubric-based reward model, Rubric-RM, surpasses strong size-matched baselines by 8.4%. These gains transfer to policy models on instruction-following and biomedical benchmarks.The model weights and datasets are publicly available at https://huggingface.co/OpenRubrics.

cs.CL

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