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

+1084新增论文
+883其中 AI 相关
+130已有论文修订
+59新增 AI 导读

arXiv 最近完成扫描:2026-11-18 04:28 · 全站最近入库:2026-11-18 19:45各信源进度 →

统计口径与数据新鲜度

统计 2026-11-17 23:58 — 2026-11-18 23:58(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:2026-11-18 04:28最近发现新增版本:2026-11-18 19:45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。

26,870 已收录论文22,374 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 42 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-18 04:27(北京时间)
新论文 · v1arXiv:2611.22403

BehaVerify: A Formal Verification Tool for Behavior Trees

Serena S. Serbinowska, Ben Wooding, Diego Manzanas Lopez, Luke Nam, Anne M. Tumlin, Nicholas K. Potteiger, Hongchao Zhang, Taylor T. Johnson

原文摘要

This paper presents BehaVerify, a verification toolbox for behavior trees (BTs) and Neuro-Symbolic BTs. BTs are a graphical language for planning and sequencing behaviors - similar to extended state machines - and are increasingly used in safety-critical domains. BehaVerify enables users to specify a BT using a Domain Specific Language (DSL) with formal syntax and semantics. This language further includes Linear Temporal Logic and Computation Tree Logic specifications. BehaVerify uses an efficient encoding into nuXmv, called fastforwarding, to quickly verify if a specification holds over the BT. Additionally, BehaVerify can generate implementations of the BT in Python and Haskell. Through Python, BehaVerify has been integrated with PyTrees and Robot Operating System (ROS) and has been deployed to several autonomous robotic systems, including for verifying runtime monitors. While prior works have developed the underlying theory, this manuscript focuses on the toolbox usage, functionality and implementation. BehaVerify is open source: https://github.com/verivital/behaverify

cs.SE · cs.LO · cs.RO

新论文 · v1arXiv:2611.22262

OfficePrism: Benchmarking Agents on Single-Domain Operations Across Enterprise Business Functions

Hanfeng Liu, Zhenyu Luo, Dongchao Zhang, Zexi Liu, Zulong Chen, Jinxin Hu, Jia Xu, Zeyi Wen

原文摘要

Broad workplace scores can mix competence within one business function with the extra cost of coordinating across functions and systems, making failures hard to localize. OfficePrism evaluates this prerequisite through 420 single-domain enterprise tasks spanning seven business functions under shared, benchmark-defined L1--L3 task-structure levels. Each task runs in a fresh environment combining a shared synthetic organization with one function-specific domain and yped state access. Our pipeline uses grounded records, business rules, and tool schemas to jointly construct a Chinese-language ticket, a hidden executable reference witness, and an expected response, followed by automated filtering and human curation. The same task set is evaluated through full-schema and search-and-dispatch packages. Across 124 model--harness--package configurations, the per-case joint natural-language-and-database pass rate ranges from 22.6% to 76.4%, with a median of 67.9%. L1 is highest in all 124 configurations, and L2 exceeds L3 in 122. Among 50 configurations sharing the same harness and model labels across both packages, search scores higher in 30, ties in one, and scores lower in 19.

cs.CL · cs.AI · cs.LG · cs.SE

新论文 · v1arXiv:2611.20243

Achievable Information Rate for FTN under a Reduced Complexity BCJR Receiver

Zichao Zhang, Gokhan M. Guvensen, Melda Yuksel, Halim Yanikomeroglu

原文摘要

The capacity of faster-than-Nyquist (FTN) signaling in additive white Gaussian noise (AWGN) channels has been established and is achieved by Gaussian inputs. However, the capacity of FTN signaling with finite-constellations is not yet fully characterized. The achievable information rate (AIR) provides a lower bound on this constrained capacity by quantifying the rate supported by a specified input distribution and receiver. This paper investigates the AIR of FTN signaling with finite constellations using full-state and reduced-state Bahl-Cocke-Jelinek-Raviv (BCJR) receivers, with bidirectional decision feedback incorporated into the reduced-state receiver. Especially, the detection problem is formulated in a reproducing kernel Hilbert space (RKHS), where a geometric foundation is established to understand FTN under severe time packing. The formulation establishes that the Ungerboeck metric remains valid even when the noise covariance is singular. We further characterize detection errors geometrically using RKHS distances between competing sequences. We also study outage probability for reduced-state detection, which occurs when AIR is zero, in addition to deriving the zero-AIR outage criterion for reduced-state detection. Unlike ISI-free Nyquist signaling, reduced-state FTN detection can retain residual ISI that causes the receiver to assign excessive confidence to incorrect symbols, leading to outage even at high signal-to-noise ratio (SNR). Our results confirm both the spectral efficiency gains and the feasibility of FTN systems employing finite constellations and realistic receiver architectures.

cs.IT · eess.SP

新论文 · v1arXiv:2611.20050

Clinician Assessment of Laryngeal Disease with Auditory AI before Laryngoscopy: A Paired Reader Study

Siyuan Hou, Shuting Yang, Zengrui Jin, Liyu Cheng, Siyin Wang, Yunhan Shi, Xueyan Li, Rong Hu 等 16 位作者

原文摘要

Background: Before laryngoscopy, clinicians assess the likely cause of hoarseness and whether to suspect a precancerous or malignant lesion. Whether voice-based artificial intelligence (AI) supports pre-laryngoscopic categorization is unknown. Methods: We developed an auditory large language model that generates a patient-level assessment card (provisional category, voice-quality ratings, and rationale) and a prespecified malignancy alert from voice recordings, patient information, and acoustic measures obtained before laryngoscopy at one center. We evaluated both in a held-out test set and a later cohort. In a sequential reader study, 32 otolaryngology clinicians categorized held-out cases without AI and, 1 to 2 weeks later, reviewed their initial categories with the card (without the alert). Results: Across 800 paired assessments, reader accuracy was 49.8% before and 56.8% after review (difference, 7.0 percentage points; 95% CI, 1.7 to 13.5; P < 0.001); 99 categories changed from incorrect to correct and 43 from correct to incorrect (ratio, 2.30; 95% CI, 1.22 to 5.31). Accuracy rose 14.7 points when the model was correct and fell 8.7 when incorrect. Provisional-category accuracy was 72% in held-out testing and 67% in temporal validation. The malignancy alert flagged 85.7% and 86.8% of precancerous or malignant lesions. Sensitivity for precancerous or malignant lesions increased from 53.9% to 75.0% after AI-assisted review (difference, 21.1 percentage points; 95% CI, 4.3 to 42.0). Conclusions: In this single-center study, clinicians' pre-laryngoscopic categorization accuracy was higher after reviewing the AI assessment card, although the sequential design cannot fully separate AI assistance from reassessment; gains depended on model correctness without clearly selective adoption. Randomized and external evaluations, including of the malignancy alert, are needed.

eess.AS · cs.AI

版本更新 · v4arXiv:2610.35581

Integrate the Reward, Don't Sample It: Window Likelihood for Interruptions and Backchannels in Full-Duplex Speech Models

Guoqiang Hu, Lichao Zhang, Yizhou Peng, Yuhao Luo, Haifeng Hu, Zhongqian Sun, Wei Yang, Eng Siong Chng

原文摘要

When a user talks over a full-duplex dialogue model, it must decide whether the user is interrupting (stop) or backchannelling (carry on). Post-training can improve this discrimination or change how readily it stops. In our GRPO runs the second dominates: no configuration lowers both error rates on more than one model, and two released checkpoints discriminate no better than their bases. We trace this partly to how the reward is estimated. The probability of stopping inside a short window is a known function of a few stop probabilities the policy emits, yet GRPO estimates it by sampling. A group of rollouts that all agree gives no gradient, even when all fail; the push on the stop threshold is strongest where the model is unsure, whichever outcome is right; and whole-rollout credit reaches decisions the reward never judges. Confining the credit to the window removes only that leakage. Window likelihood (WL) samples the words but integrates over the stop decisions, so the probability of the correct outcome is computed exactly and its logarithm maximised. On HumDial-FDBench, across four open models, WL gives the best F1 and lowers both error rates by more than their confidence intervals, without talking into silence.

eess.AS · cs.CL · cs.SD

版本更新 · v3arXiv:2605.19541

Optimising Neural Speech Codecs for 300bps Communication using Reinforcement Learning

Junyi Wang, Chi Zhang, Jing Qian, Haifeng Luo, Hao Wang, Zengrui Jin, Chao Zhang

原文摘要

In bandwidth-constrained communication such as satellite and underwater channels, speech must often be transmitted at ultra-low bitrates where intelligibility is the primary objective. At such extreme compression levels, codecs trained with acoustic reconstruction losses tend to allocate bits to perceptual detail, leading to substantial degradation in word error rate (WER). This paper proposes ClariCodec, a neural speech codec operating at 300 bits per second (bps) that reformulates quantisation as a stochastic policy, enabling reinforcement learning (RL)-based optimisation of intelligibility. Specifically, the encoder is fine-tuned using WER-driven rewards while the acoustic reconstruction pipeline remains frozen. Even without RL, ClariCodec achieves 4.64% WER on the LibriSpeech test-clean set at 300 bps, already competitive with codecs operating at higher bitrates. Further RL fine-tuning reduces WER to 3.55% on test-clean, corresponding to a 23.5% relative reduction while preserving perceptual quality. In addition, we adapt ClariCodec to a streaming configuration and show that the proposed RL-based optimisation remains effective under streaming constraints, achieving 4.53% WER on test-clean with a theoretical latency of 374 ms.

cs.SD

版本更新 · v2arXiv:2610.06900

ASAP: Assembly-Source Aligned Pseudocode Refinement For Binary Decompilation

Yujian Zhuang, Dehong Gao, Qichao Zhang, Qijing Lai, Jiaxin Wang, Libin Yang, Xiaoyan Cai

原文摘要

Large language models (LLMs) are increasingly used in binary decompilation to refine the C-like pseudocode produced by traditional rule-based decompilers. While this pseudocode is useful, it is a heuristic and lossy abstraction rather than a faithful copy of the source code. It often contains decompiler errors, especially for aggressively optimized binaries where critical low-level details are obscured. We present ASAP, an Assembly-Source Aligned Pseudocode refinement framework for binary decompilation. ASAP learns source-aligned assembly representations from paired source and binary functions using joint function-level and snippet-level contrastive alignment. A Q-Former then compresses chunk-level assembly features into a fixed number of assembly tokens. These tokens and the decompiler-produced pseudocode jointly condition the decompilation LLM. During refinement, we use stochastic pseudocode masking and a relative assembly-advantage loss to discourage the model from relying solely on pseudocode. On two decompilation benchmarks across multiple compiler optimization levels, ASAP improves the average re-execution rate from 64.7% to 71.9% and the average recompilation rate from 91.6% to 96.6% compared with the strongest baseline. Our approach offers both a new perspective and a practical solution to binary decompilation.

cs.PL · cs.CR · cs.SE

版本更新 · v2arXiv:2606.09323

TRL-Bench: Standardizing Cross-Paradigm Representation-Level Evaluation of Tabular Encoders

Wei Pang, Xiangru Jian, Hehan Li, Zhixuan Yu, Alex Xue, Jinyang Li, Zhengyuan Dong, Xinjian Zhao 等 13 位作者

原文摘要

Tabular encoders are usually evaluated inside task-specific end-to-end pipelines, so models from different training paradigms are difficult to compare directly even when they operate on similar tabular signals. We introduce TRL-Bench, a multi-granular tabular representation learning (TRL) benchmark that standardizes cross-paradigm representation-level evaluation: each encoder exports row-, column-, or table embeddings through its supported wrapper, and shared lightweight heads probe them across three suites: TRL-CTbench (column/table), TRL-Rbench (row), and TRL-DLTE (compositional Data-Lake Table Enrichment spanning all three granularities). To support this standardized setting, we release curated benchmark assets and task reformulations, including 50 OpenML tables with 123 verified targets, 16 row-pair linkage rewrites, and a 47,772-table DLTE lake derived from 1,379 parent tables. Across 20 models and 16 tasks, TRL-Bench shows that once downstream conditions are standardized, encoder quality is capability-specific rather than captured by a single leaderboard. In TRL-CTbench, generic text encoders often lead on tasks with strong surface-text signal, while tabular specialists win where their pretraining objective aligns with the task. In TRL-Rbench, within-table prediction and cross-table linkage favor different training regimes, with atomic linkage performance correlating strongly with the row-matching stage of DLTE pipelines. In TRL-DLTE, the strongest pipelines combine capability-matched specialists rather than reuse a single encoder, and top end-to-end quality depends on non-additive compositional fit rather than per-stage marginal rank alone. TRL-Bench provides a common protocol for measuring reusable signal in exported tabular representations under shared downstream conditions. Code: https://github.com/LOGO-CUHKSZ/TRL-Bench; data is released on Hugging Face.

cs.AI · cs.DB

版本更新 · v2arXiv:2606.16175

PAL-Bench: Evidence-Grounded Profile Reconstruction from Longitudinal Personal Albums

Qiwei Yan, Zhiqiang Yuan, Zexi Jia, Nanxing Hu, Kailin Lyu, Jie Zhou, Jinchao Zhang

原文摘要

Longitudinal personal albums are weak-schema multimodal databases: noisy perceptual records whose key facts require joins across faces, text, timestamps, locations, and repeated events. Existing visual, video, document, and lifelog benchmarks test sub-problems, but not album-scale profile reconstruction with social identity binding and evidence citation. Benchmarking this task is difficult because the ground truth needed for evaluation--owner profiles, social graphs, face-name maps, and evidence provenance--is private state that real albums cannot safely release. We introduce PAL-Bench, a controlled benchmark for evidence-grounded reconstruction under a public-record contract. Its Evidence Compiler builds latent private worlds, programs target-level evidence paths, renders album pixels, re-measures them through perception pipelines, and exports audited public/private views. Agents receive only perception-derived public records; targets, identifier maps, and evidence paths remain hidden. PAL-Bench contains 50 synthetic users, 36,659 public photo records, and 2,799 targets over owner facts, identities, and relations. A privacy-preserving audit with 10 participants confirms that PAL-Bench evidence structures match real private albums, though equivalent releases remain privacy-prohibitive. Across seven systems and two compute-matched diagnostics, a seven-metric protocol reveals a gap between plausible profile summarization and faithful social reconstruction: systems recover some owner facts but struggle with recurring identities and evidence citation. PAL-TRACE, a reference framework that freezes identity bindings before owner-fact mining, performs best but leaves hard identity resolution far from solved. PAL-Bench provides a testbed for perceptual entity resolution, multimodal data integration, temporal evidence aggregation, and provenance-aware structured prediction.

cs.AI

版本更新 · v2arXiv:2611.10693

Machine Hearing: Can Audio LLMs Generalize Beyond Human Auditory Perception?

Liwei Liu, Jun Tao, Xingyuan Li, Xuenan Xu, Chen Zhang, Junyi Wang, Boya Zhang, Xiaoyu Yang 等 11 位作者

原文摘要

Multimodal LLMs have made remarkable progress in perceiving the physical world, while their perceptual scope remains largely human-centric, focusing on what humans can directly see or hear. This progress raises the prospect of perception beyond human limits, such as extending hearing to sounds that are inaudible to humans. More broadly, the physical world is full of waves, vibrations, and oscillations, only a small fraction of which are directly audible to humans. This invites the extension of multimodal LLMs toward a broader form of machine hearing, which remains largely underexplored. To investigate this direction, we introduce the Machine Hearing Benchmark (MHB), comprising 6,128 instances across 13 tasks and seven domains. MHB spans highly heterogeneous input regimes, with sampling rates from approximately $10^{-5}$ to $10^6$ Hz, sequence lengths from $10^1$ to $10^6$ samples, and both single- and multi-channel inputs. Evaluations of current open-source and proprietary Audio LLMs (ALLMs) reveal limited zero-shot transfer to machine hearing. Supervised adaptation on machine-hearing data alone does not close this gap, suggesting that the challenge extends beyond data exposure to a systematic mismatch between existing audio front ends and machine-hearing inputs. To address this mismatch, we introduce MachEar, a lightweight encoder extension that complements the pretrained Audio LLM for machine-hearing inputs. The results show that MachEar equips a pretrained Audio LLM with stronger machine-hearing capabilities while largely preserving its existing audio understanding performance.

cs.SD · cs.CL

版本更新 · v2arXiv:2610.40658

Explain, Then Forget: Recommendation Unlearning under Asymmetric Access Constraint

Haichao Zhang, Chong Zhang, Wen Wang, Shi Qiu, Peiyu Hu, Jia Wang

原文摘要

Recommendation unlearning aims to remove the influence of specific historical interactions that should no longer affect future recommendations, such as noisy clicks or outdated user preferences. However, performing recommendation unlearning becomes much harder in modern Machine-Learning-as-a-Service (MLaaS) architectures, where the recommendation model is remotely hosted by a model provider (MP) and accessed by service operators (SO) only through APIs. In this setting, a service operator serves end users but cannot access or modify internal model parameters. As a result, existing unlearning methods are difficult to apply because they require access to model internals for retraining, fine-tuning, or other parameter updates. To address these challenges, we propose Causal Explanation-based Unlearning (CEU), a novel unlearning framework tailored for MLaaS environments. Instead of modifying internal model weights, CEU operates through a two-step output-level score intervention. First, it estimates how the forgotten interaction causally contributes to the current recommendation. Second, guided by this causal signal, the system removes the influence of the forgotten interaction by adjusting the final ranking scores of affected items. Because CEU leaves model parameters untouched, it naturally supports continuous unlearning requests while avoiding the error accumulation that can result from repeated parameter updates. Extensive experiments on three public datasets show that CEU achieves unlearning effectiveness comparable to full retraining while preserving recommendation utility and significantly reducing computational cost. The source code is available at: https://github.com/zhang-haichao/Explain-and-Forget.

cs.IR

新论文 · v1arXiv:2611.13009

Instance-preserving graded semantic reporting for surgical action triplets

Yanchong Xue, Wanting Zhang, Lingtao Yu, Guochao Zhang

原文摘要

Complete-or-reject reporting of surgical action triplets can discard a correctly identified instrument and action when the target is uncertain. We introduce instance-preserving graded semantic reporting, which separates instance selection from the choice of semantic detail. Each selected instance retains its predicted mask and labels while hierarchical correctness scores guide instrument (I), instrument-verb (IV), or complete instrument-verb-target (IVT) reporting. The utility-increment rule DELTA weighs the expected gain from finer reporting against its error cost. We compare three decision rules on 5,641 test frames from eight surgical videos using fixed predictions and scores. At the 10% development calibration target, DELTA retains correct partial reports for 80.0% of candidates rejected by a matched complete-or-reject baseline (5,329/6,662). Adding IV increases source-normalized weighted correct-report yield by 19.13 to 23.13 per 100 frames across all three rules relative to separately recalibrated I/IVT controls. Weighted reporting risk changes by -0.77 to +1.01 percentage points, with complete correct-triplet counts unchanged or reduced. Graded reporting makes partial surgical predictions available as localized descriptions, with an explicit trade-off between report utility and completeness.

cs.CV

新论文 · v1arXiv:2611.11273

Task-adaptive anonymisation enables privacy-preserving sharing of clinical speech data

Ziyun Cui, Haoyu Niu, Wen Wu, Hao Sun, Sihan Zhang, Chang Lei, Yun Zhang, Chunyun Sun 等 15 位作者

原文摘要

Clinical speech is increasingly used for disease screening and clinical assessment, but directly distributing speech recordings poses privacy risks because they contain both speaker-identifying voiceprints and sensitive spoken content. Existing speech anonymisation approaches are primarily developed for general speech applications or task-specific clinical speech and overlook that different clinical tasks rely on distinct speech characteristics, necessitating task-adaptive anonymisation strategies to protect patient privacy while preserving clinical utility. Here we introduce CASA, a clinically adaptive speech anonymisation agent that transforms anonymisation from a fixed processing procedure into a task-guided optimisation process, dynamically tailoring voiceprint and content anonymisation to task-specific privacy and clinical utility requirements. Through recursive self-improvement (RSI), CASA iteratively evaluates and refines anonymisation strategies against task-specific privacy and clinical utility requirements, while learning from these outcomes to guide more efficient planning in subsequent clinical tasks. CASA is validated across 14 clinical tasks encompassing five languages, diverse elicitation paradigms, and mental health, cognitive and voice disorders. CASA preserved disease-related classification performance while meeting speaker-anonymisation requirements across all clinical tasks, versus only 8/14 for the strongest fixed method. Assessments of resistance to speaker re-identification by external attackers and identification and redaction of sensitive personal information in clinical speech further demonstrated CASA's dual protection of speaker identity and sensitive spoken content. Clinical expert assessments further supported the preservation of clinically relevant information and the acceptability of anonymised speech for controlled research sharing.

eess.AS · cs.CL

新论文 · v1arXiv:2611.10632

Latent-WAM++: Shaping World and Action Representations for End-to-End Autonomous Driving

Yichen Zhang, Yupeng Zheng, Linbo Wang, Pengxuan Yang, Zebin Xing, Junli Wang, Shiwei Li, Kangwei Liu 等 13 位作者

原文摘要

We introduce Latent-WAM++, a representation-centered World Action Model (WAM) for end-to-end autonomous driving. Existing WAMs are primarily trained to predict future states or final actions, leaving the intermediate world and action representations that connect prediction to planning only indirectly constrained. Latent-WAM++ matches the supervision of each representation to its role in planning. World Representation Construction combines scene-ego future prediction, SIGReg-based distribution stabilization, and frozen geometric priors to learn a temporally predictive, non-degenerate, and geometry-aware world representation without an EMA target encoder. Trajectory MeanFlow Planner directly predicts multimodal trajectory proposals while being optimized with an Improved MeanFlow velocity-space objective, enabling one-step sampling. Visual-Action Representation Alignment further aligns the resulting pre-output action features with a stop-gradient target derived from current visual semantics. Latent-WAM++ achieves state-of-the-art performance on NAVSIM v2 and under zero-shot evaluation on HUGSIM, reaching 90.1 EPDMS on NAVSIM v2 and 47.0 average RC and 30.1 average HD-Score on HUGSIM. Training the planner end to end costs 190 GPU-hours for Latent-WAM++ versus 1,600 for Latent-WAM, a reduction of 88.1%.

cs.CV

新论文 · v1arXiv:2611.10511

CALFA-KV: Joint Calibration and Fisher-Guided Anchors for 1-Bit KV Cache Compression

Xiancai Tian, Leichao Zhang, Shenhui Zhang, Yi Shan, Hailong Li, Feng Lin, Xiaotian Yu, Aijun Li

原文摘要

1-bit key-value (KV) cache compression can combine quantizer calibration with selective high-precision storage to reduce reconstruction error. We propose Calibration and Fisher-guided Anchors for KV cache compression (CALFA-KV). Offline, we jointly fit a key center, radial normalization parameters, and K/V vector codebooks to match the frozen model's projected attention output. We also estimate channel-wise Fisher-type sensitivities from squared gradients of a reference next-token cross-entropy loss. Online, we use these sensitivities to weight the squared reconstruction errors of each KV state. Here, a KV state is one token's key-value pair within one layer and KV head. We retain the highest-scoring states at high precision under a per-layer, per-KV-head budget. Under exact restoration, we bound the excess risk of score-based anchor selection relative to the optimum at the same anchor budget, where risk is the conditional mean square of the first-order loss change. With a budget of 56 additional FP16 anchors per layer and KV head, CALFA-KV (d8b8) outperforms all evaluated nominal 1-bit baselines on the mean score across seven benchmarks for each of the three models. At the same anchor budget, CALFA-KV (d8b10) uses a nominal index rate of 1.25 bits per channel and narrows the gap to BF16 to 0.90--2.01 points on the same metric.

cs.LG

新论文 · v1arXiv:2611.10096

Coordinated Mixed-Precision KV Cache Quantization for Efficient LLM-based Multi-agent Systems

Weizhong Huang, Jinchao Zhang, Xiawu Zheng

原文摘要

LLM-based multi-agent systems solve complex tasks through collaboration, but their growing, simultaneously resident key-value (KV) caches create a memory bottleneck. Applying single-model quantization policies independently ignores differences in agents' precision needs, potentially degrading collective reasoning. We introduce Coordinated Mixed-Precision KV Cache Quantization (CoMixKV), which combines online sensitivity estimation with joint agent-layer bit-width allocation under a shared memory budget. To our knowledge, CoMixKV is the first mixed-precision KV-cache quantization framework to jointly allocate precision across simultaneously resident agent caches under such a budget. The estimator derives sensitivity from a local attention-error bound using recent queries, keys, and values, without calibration data, trial quantization, or additional model passes. A shared controller combines these scores with remaining quantizable capacity and byte-level storage costs to minimize total estimated error. Allocations are refreshed as agents start or finish and new observations become available. Selected widths apply only to newly quantized blocks; recent states retain native precision and previously quantized blocks remain unchanged. Across four benchmarks and three LLM backbones at average 2-bit, 3-bit, and 4-bit settings, CoMixKV achieves strong accuracy against the evaluated quantization baselines. At the average 3-bit setting on Gemma-4-31B-it, it achieves 68.35% average accuracy, exceeding the strongest quantized baseline by 0.59%. On Qwen3-32B, it reduces peak KV-cache memory by 32.08% and achieves a 1.38x inference speedup over FullKV.

cs.LG

新论文 · v1arXiv:2611.09026

Beyond a Single Commit: Anchor-Guided Reconstruction of Multi-Commit Patches

Jialiang Dong, Willy Susilo, Xu Gai, Liuhuo Wan, Chao Zhang, Elisa Bertino, Siqi Ma

原文摘要

Vulnerability patch identification plays a critical role in software security by linking reported vulnerabilities and the corresponding fixes, enabling reliable vulnerability analysis, mitigation, and automated security tool development. As software systems evolve in complexity, vulnerability remediation has increasingly shifted from single-commit fixes to multi-commit fixing processes. Although many studies have been proposed to identify fixing commits associated with target vulnerabilities automatically, they often suffer from inaccurate semantic analysis or excessive workload for language models. These limitations reduce both the effectiveness and comprehensiveness of fixing commit identification. To improve patch identification, we propose an effective and comprehensive patch identification framework, HARPOON, which not only enhances the accuracy of identifying individual fixing commits, but also investigates dependencies among commits to achieve comprehensive commit recognition for target vulnerabilities. Experimental results show that HARPOON significantly outperforms the state-of-the-art approaches. HARPOON successfully identified 895 vulnerability patches that were not previously maintained in public vulnerability databases. Among them, 663 are previously unrecorded fixes associated with 323 CRITICAL- or HIGH-severity vulnerabilities.

cs.CR

新论文 · v1arXiv:2611.07879

Network Effect Decomposition for Causal Effect Estimation under Network Interference

Zhirong Huang, Wenzhen Zhang, Guangquan Lu, Boyan Chen, Debo Cheng, Shichao Zhang

原文摘要

Estimating causal effects from observational network data requires accounting for both individual treatment and neighborhood exposure. Existing outcome models commonly incorporate these intervention variables into a joint predictor and estimate causal effects through prediction contrasts, leaving the corresponding response components implicit. We propose the $\underline{N}$etwork $\underline{E}$ffect $\underline{D}$ecomposition $\underline{Net}$work (NEDNet), which parameterizes the conditional outcome response as a query-invariant pre-treatment baseline plus separate treatment- and exposure-response pathways. Path-specific neighborhood contextualization supplies local pre-treatment information to the two pathways. We characterize the fitted response through a unique reference-normalized decomposition, which is equivalent to a zero mixed treatment--exposure contrast. Experiments on semi-synthetic benchmarks derived from BlogCatalog and Flickr show that NEDNet achieves the lowest PEHE among the compared methods for individual, peer, and total effects across homogeneous and covariate-heterogeneous response settings.

stat.ML · cs.AI

版本更新 · v3arXiv:2605.06597

UniSD: Towards a Unified Self-Distillation Framework for Large Language Models

Yiqiao Jin, Yiyang Wang, Lucheng Fu, Yijia Xiao, Yinyi Luo, Haoxin Liu, B. Aditya Prakash, Chao Zhang 等 11 位作者

原文摘要

Self-distillation (SD) offers a promising path for adapting large language models (LLMs) without relying on stronger external teachers. However, SD in autoregressive LLMs remains challenging because self-generated trajectories are free-form, correctness is task-dependent, and plausible rationales can still provide unstable or unreliable supervision. Existing methods mainly examine isolated design choices, leaving their effectiveness, roles, and interactions unclear. In this paper, we propose UniSD, a unified framework to systematically study self-distillation. UniSD integrates complementary mechanisms that address supervision reliability, representation alignment, and training stability, including multi-teacher agreement, EMA teacher stabilization, token-level contrastive learning, feature matching, and divergence clipping. Across six benchmarks and six models from three model families, UniSD reveals when self-distillation improves over static imitation, which components drive the gains, and how these components interact across tasks. Guided by these insights, we construct UniSDfull, an integrated pipeline that combines complementary components and achieves the strongest overall performance, improving over the base model by +5.4 points and the strongest baseline by +2.8 points. Extensive evaluation highlights self-distillation as a practical and steerable approach for efficient LLM adaptation without stronger external teachers.

cs.CL · cs.AI · cs.LG

版本更新 · v4arXiv:2603.25251

Does Explanation Correctness Matter? Linking Computational XAI Evaluation to Human Understanding

Gregor Baer, Chao Zhang, Isel Grau, Pieter Van Gorp

原文摘要

Explainable AI (XAI) methods are commonly evaluated using functional correctness metrics, also called faithfulness or fidelity, which estimate how closely an explanation reflects the model's reasoning. Higher correctness is assumed to produce better human understanding, but this link has not been tested with controlled levels. We conducted a user study (N=200) that manipulated explanation correctness at four levels (100%, 85%, 70%, 55%) in a synthetic time series classification task where participants could not rely on domain knowledge or visual intuition. Explanations were constructed to resemble feature attributions, with correctness defined against a known ground truth rather than estimated from a trained model. Participants predicted a simulated AI's decisions from these explanations (forward simulation), and we used their forward simulation accuracy as a proxy for understanding. Correctness affected forward simulation accuracy, but not at every level: accuracy dropped at 70% and 55% relative to 100%, with no further reduction below 70% and no conclusive difference between 85% and 100%. Lower correctness reduced how many participants predicted accurately rather than lowering accuracy uniformly, and even with fully correct explanations, only a subset of participants predicted well above chance. In exploratory analyses, some participants predicted decisions accurately but described the wrong pattern when asked what the AI used, and self-reported ratings correlated with forward simulation accuracy only when explanations were fully correct. These findings suggest that, for feature-attribution-style explanations, not all differences in functional correctness translate to differences in human understanding, highlighting the need to validate functional metrics against human outcomes.

cs.HC · cs.AI · cs.LG

新论文 · v1arXiv:2611.06911

BEAKER:面向自驱动化学实验室具身大脑的专家精选基准

BEAKER: An Expert-Curated Benchmark for Embodied Brains in Self-Driving Chemical Laboratories

Fei Lin, Tengchao Zhang, Ziyang Gong, Xiaotong Yu, Bohan Zhang, Yifan Zhou, Qihao Yang, Ji Dai 等 18 位作者

AI 速读 基于摘要

作者提出并构建了专家人工标注的 BEAKER 基准,用于评测多模态大模型在自驱动化学实验室中的执行导向具身能力。

cs.AI

查看原文摘要

Self-Driving Chemical Laboratories (SDCLs) are moving chemical experimentation toward embodied automation, where machines must perceive laboratory scenes, reason about experimental states, and act under physical, procedural, and safety constraints. Although Multimodal Large Language Models (MLLMs) are increasingly considered as embodied brains for such systems, existing laboratory benchmarks mainly focus on safety, anomaly detection, or general scientific understanding, leaving their execution-oriented embodied capabilities underexplored. To fill this gap, we introduce BEAKER, a Benchmark for evaluating Embodied Actionability, Knowledge, Experimentation, and Reasoning in SDCLs. BEAKER contains 1,000 expert-curated question-answer samples across 11 image and video task types, covering key judgments required for chemical laboratory execution, including affordance grounding, trajectory planning, equipment, state, and safety recognition, apparatus setup, operation and step reasoning, and temporal procedure reasoning. All questions and annotations are manually created and reviewed by chemistry and embodied Artificial Intelligence (AI) experts, without AI-assisted generation or annotation. We evaluate 28 general-purpose, science-oriented, chemistry-specialized, and embodied MLLMs in an offline, single-turn setting. Results show that current models can follow coarse experimental procedures in videos, but still struggle to ground actions into operable regions and feasible trajectories, to recognize fine-grained laboratory apparatus, states, and safety norms, and to order steps in mid-length procedures. BEAKER thus reveals a clear gap between coarse procedural understanding and the precise, action-grounded perception required for laboratory execution, providing a diagnostic benchmark for future MLLMs in SDCLs.

版本更新 · v3arXiv:2508.12035

ToxiEval-ZKP:面向分子毒性修复任务的结构隐私验证框架

ToxiEval-ZKP: A Structure-Private Verification Framework for Molecular Toxicity Repair Tasks

Fei Lin, Tengchao Zhang, Ziyang Gong, Fei-Yue Wang

AI 速读 基于摘要

作者提出将零知识证明引入分子毒性修复任务的评估流程,使模型开发者能在不披露分子结构的前提下向外部验证者证明生成分子满足多维毒性修复标准。

cs.CR

查看原文摘要

In recent years, generative artificial intelligence (GenAI) has demonstrated remarkable capabilities in high-stakes domains such as molecular science. However, challenges related to the verifiability and structural privacy of its outputs remain largely unresolved. This paper focuses on the task of molecular toxicity repair. It proposes a structure-private verification framework - ToxiEval-ZKP - which, for the first time, introduces zero-knowledge proof (ZKP) mechanisms into the evaluation process of this task. The system enables model developers to demonstrate to external verifiers that the generated molecules meet multidimensional toxicity repair criteria, without revealing the molecular structures themselves. To this end, we design a general-purpose circuit compatible with both classification and regression tasks, incorporating evaluation logic, Poseidon-based commitment hashing, and a nullifier-based replay prevention mechanism to build a complete end-to-end ZK verification system. Experimental results demonstrate that ToxiEval-ZKP facilitates adequate validation under complete structural invisibility, offering strong circuit efficiency, security, and adaptability, thereby opening up a novel paradigm for trustworthy evaluation in generative scientific tasks.

版本更新 · v5arXiv:2506.10912

打破坏分子:多模态大语言模型准备好进行结构级分子解毒了吗?

Breaking Bad Molecules: Are MLLMs Ready for Structure-Level Molecular Detoxification?

Fei Lin, Ziyang Gong, Cong Wang, Tengchao Zhang, Yonglin Tian, Yining Jiang, Ji Dai, Chao Guo 等 12 位作者

AI 速读 基于摘要

该论文提出首个面向通用多模态大语言模型的分子毒性修复基准任务ToxiMol及自动评估框架ToxiEval,并系统评测43个主流模型。

cs.AI · cs.CL

查看原文摘要

Toxicity remains a leading cause of early-stage drug development failure. Despite advances in molecular design and property prediction, the task of molecular toxicity repair, generating structurally valid molecular alternatives with reduced toxicity, has not yet been systematically defined or benchmarked. To fill this gap, we introduce ToxiMol, the first benchmark task for general-purpose Multimodal Large Language Models (MLLMs) focused on molecular toxicity repair. We construct a standardized dataset covering 11 primary tasks and 660 representative toxic molecules spanning diverse mechanisms and granularities. We design a prompt annotation pipeline with mechanism-aware and task-adaptive capabilities, informed by expert toxicological knowledge. In parallel, we propose an automated evaluation framework, ToxiEval, which integrates toxicity endpoint prediction, synthetic accessibility, drug-likeness, and structural similarity into a high-throughput evaluation chain for repair success. We systematically assess 43 mainstream general-purpose MLLMs and conduct multiple ablation studies to analyze key issues, including evaluation metrics, candidate diversity, and failure attribution. Experimental results show that although current MLLMs still face significant challenges on this task, they begin to demonstrate promising capabilities in toxicity understanding, semantic constraint adherence, and structure-aware editing.

新论文 · v1arXiv:2611.05739

PersonaCodeBench: Evaluating Coding Agents in Persona-driven Human-Interactive Sessions

Haixin Wang, Jianheng Hou, Hongyu Shen, Wenzhe Fan, Wei-Chieh Huang, Qianyu Zhu, Weichen Li, Taoran Li 等 30 位作者

原文摘要

Coding agents must deliver correct software while respecting users' expertise, preferences, and working conditions. Existing benchmarks increasingly incorporate interaction, yet personalized requirement fulfillment remains underexplored. We introduce PersonaCodeBench, which turns user characteristics into verifiable obligations in persona-driven multi-turn coding sessions. Our persona pool spans roles, technical abilities, interaction preferences, and practical constraints, yielding task-grounded evolved requirements for implementation, permissions, testing, explanation, and delivery. At runtime, a controller governs user simulator responses and requirement disclosure, using online requirement evaluation to provide feedback and advance the interaction. Requirements emerge progressively, with their content, disclosure conditions, and acceptance criteria fixed before evaluation. A completion verifier and a personalization verifier separately assess native correctness and persona fulfillment. Joint pass requires both adherence to the declared budget and compliance with validity conditions. We evaluate all major frontier agents, establish a comprehensive leaderboard, and conduct detailed experimental analyses to validate effectiveness. PersonaCodeBench supports reproducible evaluation of coding agents' ability to meet explicit, personalized user expectations alongside coding objectives.

cs.AI

新论文 · v1arXiv:2611.04814

Think Less, Locally: Local Preference Learning for Reasoning Compression

Muyao Yuan, Liyan Xu, Weizhan Zhang, Muyan Jiao, Jiangnan Li, Jinchao Zhang, Jie Zhou

原文摘要

Large reasoning models achieve strong performance on challenging tasks, but their long chain-of-thought often incurs substantial inference costs by continuing to deliberate after sufficient information has been obtained. Existing reasoning compression methods primarily operate on reasoning trajectories, paying less attention to the local decision of whether further reasoning is necessary given the current state. We propose LoCo, a local preference learning method for reasoning compression. LoCo detects candidate overthinking states from the model's own traces, freezes the corresponding reasoning prefixes, regenerates shorter verified continuations from the same states, and trains on the resulting state-conditioned preference pairs with DPO. This formulation teaches the model when to continue reasoning and when to conclude, rather than simply encouraging shorter trajectories overall. We construct training data entirely from self-generated mathematical traces and evaluate LoCo on five mathematical and three code generation benchmarks. LoCo reduces completion length by 41.7\%--45.4\% on mathematics and 23.4\%--36.3\% on code, while maintaining or improving accuracy and achieving the best AUC across all code benchmarks. LoCo consistently improves the accuracy-efficiency trade-off on mathematics and transfers effectively to code generation despite math-only training, demonstrating the cross-domain generality of local preference learning for reasoning compression. The code and model will be publicly released at https://github.com/MuyaoYuan/LoCo.

cs.AI · cs.CL

新论文 · v1arXiv:2611.03634

WebHarbor: Docking Real Websites for Evolving GUI Agent Environments

Zhaoyang Wang, Qianhui Wu, Boyu Gou, Demi Wang, Jiacheng Zhang, Peichun Hua, Qize Li, Shi Qiu 等 57 位作者

原文摘要

GUI web agents require realistic and interactive environments that remain stable during both evaluation and training. Live website evaluation suffers from changing content, access restrictions, and limited coverage of authenticated workflows, while existing synthetic environments for training often lack functional depth and visual fidelity. We propose WebHarbor, a suite of 153 executable and dockerized website environments that faithfully reconstruct the visual interfaces, content, and functional workflows of real-world web services under deterministic control. We build WebHarbor through task-driven human-agent collaboration, where environments evolve as new tasks expand their functional scope, coding agents implement the required changes, and human contributors audit visual fidelity, functional correctness, and task validity. The resulting suite comprises 3,518 tasks spanning multi-step and post-authentication workflows, where existing works often fail to cover. Beyond reliable evaluation, WebHarbor provides high-fidelity synthetic web environments for cost-efficient reinforcement learning (RL). We demonstrate that a Qwen 4B-level GUI agent trained with RL in WebHarbor generalizes to unseen tasks and performs competitively with leading open-source GUI web agents across four benchmarks. The code and data are publicly available at https://github.com/aiming-lab/WebHarbor.

cs.AI · cs.CL · cs.LG

新论文 · v1arXiv:2611.02463

Think Globally, Generate Personally: Multi-View Thinking with Adaptive Generation for Generative Recommendation

Yuxuan Hu, Yingyi Zhang, Wenlin Zhang, Chao Zhang, Haotian Nan, Ziwei Liu, Jiancheng Dong, Tongzhou Wu 等 14 位作者

原文摘要

Semantic-ID-based (SID) generative recommendation (GR) represents each item as a sequence of discrete tokens and predicts the next item through autoregressive SID generation. However, existing methods face two challenges. First, insufficient shared context modeling for user sequences: full-history and recent behaviors provide overlapping yet complementary evidence, but modeling them within a single sequence may dilute current cues, whereas processing them through separate streams may fail to coordinate them. Second, insufficient personalized adaptation in progressive SID decisions: although decoder states evolve with generated prefixes, existing models typically use a shared output-side transformation across recommendation instances, without explicitly selecting a transformation suited to the current user need. To address these challenges, we propose Multi-View Thinking with Adaptive Generation (MV-Thinker), a framework that Thinks Globally and Generates Personally. First, Multi-View Temporal Thinking uses view-specific thinking queries and readers over overlapping full-history and recent-history views, coordinating both sources into complementary user-conditioned contexts before SID generation. Second, Hierarchical Residual Adaptation organizes lightweight adapters into nested residual paths before a shared vocabulary projection, adaptively transforming context-bearing decoder states for SID decisions. Extensive experiments on four public datasets demonstrate that MV-Thinker consistently outperforms strong discriminative and generative recommendation baselines across multiple ranking metrics. The implementation code and datasets are available on: https://anonymous.4open.science/r/MV-Thinker

cs.AI

版本更新 · v2arXiv:2610.32106

PersonaScienceBench: Evaluating Scientific Agents with Diverse Simulated Researchers

Siyang Wu, Weizhi Zhang, Chen Yang, Esther Xu Fei, Jorin Overwiening, Xu Pan, Jing Tang, Yixuan He 等 37 位作者

原文摘要

Scientific agents collaborate with researchers whose expertise and preferences differ, but benchmarks usually hold the collaborator fixed. We introduce PersonaScienceBench: 200 tasks from five benchmarks across four scientific domains. Simulated researchers provide context and feedback according to persona profiles, while task objectives and grading remain fixed. Agents encounter researcher preferences only through conversation. Across eighteen modelconfigurations, task performance, fact recovery, and self-repetition reveal different strengths. Detailed GPT 6 Astra analyses show distinct agent responses across researcher profiles; interaction traces illustrate targeted clar ification and workflow revision. These behaviors can differ even when final scores match. PersonaScienceBench therefore evaluates how agents collaborate with diverse researchers alongside whether they complete the task.

cs.AI

新论文 · v1arXiv:2611.02079

ParetoSaddler: Pareto-Guided Optimization of Agent Harnesses for Quality and Cost

Xingzhi Qian, Sungho Park, Rongyuan Tan, Jianbo Yu, Jue Zhang, Lorenzo Cavallaro, Menglin Xia, Yanzhi Chen 等 16 位作者

原文摘要

Harness optimization can substantially improve LLM agents without modifying model weights, but existing methods primarily optimize response quality. Extending them to joint quality--cost optimization introduces a challenge: applying the deployment preference during intermediate updates can prematurely reject candidates that are valuable for later improvements. We introduce ParetoSaddler, which addresses this mismatch by separating intermediate candidate promotion from final deployment selection. At each iteration, an optimizer updates a parent harness to produce a candidate, and then compares the two over repeated executions and uses Bayesian bootstrap Pareto support to promote candidates showing credible progress in either quality or cost. Promoted candidates receive broader development evaluation and remain available as parents for later optimization steps. We evaluate ParetoSaddler on ClawMark and GAIA2 using domain-disjoint splits. On ClawMark, ParetoSaddler improves quality from 70.86\% to 81.35\% while reducing cost from \$1.17 to \$1.01 per task; on GAIA2, it improves quality from 56.22\% to 62.89\% while reducing cost from \$0.78 to \$0.45 per task. The Pareto-selected harnesses also achieve higher quality at lower cost than quality-only harness optimization. Analysis shows that Pareto-aware optimization retains intermediate candidates that would be discarded by deployment preference but can support later improvements, while Bayesian bootstrap screening filters out candidates whose gains are weakly supported across runs.

cs.AI · cs.CL · cs.LG · cs.MA

新论文 · v1arXiv:2610.40437

面向异构动力系统贝叶斯滤波的预训练模型

A Pretrained Model for Bayesian Filtering in Heterogeneous Dynamical Systems

Ke Fan, Wen Wu, Haitao Su, Yilin Wang, Yuan Zhou, Chao Zhang

AI 速读 基于摘要

提出首个面向贝叶斯滤波的预训练模型 FilterFM,用单一检查点跨异构动力系统估计隐状态,并报告零样本滤波与缩放行为。

cs.LG

查看原文摘要

Filtering has not yet had its foundation-model moment: state estimation is still dominated either by online Bayesian filtering algorithms that require known dy- namics as inputs, or by learning-based neural filters trained from scratch for a single system or parametric family. The core challenge is structural heterogene- ity: dynamical systems differ in their governing dynamics, physical scales, and noise levels, precluding a shared representation space for a reusable filter. To bridge this gap, we introduce FilterFM, the first pretrained model for Bayesian filtering that estimates latent states across heterogeneous dynamical systems with a single checkpoint. FilterFM employs a hierarchical two-level observation se- quence encoder and a prior-to-posterior state-reconstruction module that together handle varying observation and state dimensions across heterogeneous systems, while modeling state uncertainty via quantile prediction. Trained on a mixture of heterogeneous filtering tasks, FilterFM exhibits superior in-domain performance, delivering significant gains in estimation accuracy, runtime efficiency, and noise robustness compared to existing baselines. Beyond in-domain performance, it marks the first model to successfully enable zero-shot filtering on unseen dynamics, bridging the generalization gap in state estimation. Furthermore, we uncover clear scaling behaviors in foundation-model-based Bayesian filtering, which combined with comprehensive component ablation studies, validate the structural optimality of our design and broaden the generalization scope for this research field.