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

+479新增论文
+361其中 AI 相关
+63已有论文修订
+93新增 AI 导读

arXiv 最近完成扫描:2026-11-16 01:34 · 全站最近入库:2026-11-16 13:44各信源进度 →

统计口径与数据新鲜度

统计 2026-11-15 14:20 — 2026-11-16 14:20(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:2026-11-16 01:34最近发现新增版本:2026-11-16 13:44库内论文最新更新时间:2026-11-14 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。

23,827 已收录论文19,941 AI 相关6,921 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 23,827 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-16 01:33(北京时间)
新论文 · v1arXiv:2610.38642

Measuring the Inaccessible: Can AI Evaluate Accessibility in Heritage Tourism?

Sabrina Armenio, Manuele Leonelli

原文摘要

Accessibility assessment underpins the right to participate in heritage tourism, yet evaluation of archaeological sites remains artisanal: fieldwork does not scale, is often carried out without accessibility training, and is reported in forms that reach neither the sector nor disabled visitors. AI appears to offer a shortcut. We argue that assessment is measurement and inference under sparse, expert-mediated evidence: AI transforms how that evidence is captured and communicated, whereas evaluation, which turns evidence into defensible judgements, demands properties current generative systems lack. In a five-park field study in Spain and Italy, an AI desk audit scored only 66% of dimension-site combinations, could not observe embodied and organisational dimensions, and mirrored sites' online self-presentation. Simple Bayesian models instead quantify the confidence rankings deserve and calibrate desk evidence against fieldwork. We propose a separation of roles between AI and interpretable statistical evaluation as the basis for a reliable accessibility atlas.

cs.CY

新论文 · v1arXiv:2610.38639

Enhanced image forensics through partial C2PA-based provenance information

Riccardo Ziglio, Eleonora Marchesini, Andrea Montibeller, Giulia Boato, Silvio Ranise, Cecilia Pasquini

原文摘要

Cryptographically verifiable C2PA-based Content Credentials (CCs) can be attached to freshly acquired or generated digital images but also to already existing ones with no previous provenance information, for instance after processing through trusted C2PA-enabled software tools. The latter case leads to images with so-called partial CCs, which capture only the last operations applied, while prior provenance remains unknown and can be investigated through signal forensics. This paper addresses the forensic analysis of such images, highlighting the opportunity to leverage the partial CCs as additional trusted knowledge to adapt forensic detectors towards the statistical characteristics of the image under analysis and mitigate potential distribution shifts. To this end, a two-step strategy is envisioned: (i) reconstructing the operations applied by the last signer through a structural analysis of the partial CCs; (ii) exploiting the obtained reconstruction to enhance the forensic detector of the analyst through an adaptation process. An empirical analysis on partial CCs produced by commercial C2PA-enabled software tools through different editing operations is carried out, providing evidence on the feasibility of the reconstruction in practical cases. An experimental case study on the forensic task of synthetic image detection is then presented, showing that the proposed strategy can significantly enhance the performance of state-of-the-art detectors on test images that are postprocessed via C2PA-enabled software tools after being generated/acquired.

cs.CR · cs.AI · cs.MM · eess.IV

新论文 · v1arXiv:2610.38637

On-Policy Self-Distillation with Teacher Evolution

Shufan Shen, Zhongni Hou, Chao Bi, Yufei Zhang, Guojun Yin, Shuhui Wang

原文摘要

On-Policy Self-Distillation (OPSD), which aligns a student model's token-level distribution with that of its self-teacher prompted by privileged context, has emerged as a promising direction to mitigate reward sparsity in sequence-level post-training paradigms. However, OPSD often fails to achieve continuous performance gains during training. In this paper, we find that the model's limited self-teaching capability underlies this phenomenon by generating unreliable guidance on certain samples. To address this problem, we propose Teacher-Evolution Self-Distillation (TESD), which enables the self-teacher to generate rollouts and receive environmental feedback based on task correctness and context independence. First, using these rewards as training objectives, we perform teacher-oriented optimization to continuously enhance the model's self-teaching capability during distillation. Second, by estimating teacher guidance reliability from these rewards, we apply adaptive student-oriented optimization to down-weight samples with unreliable guidance. Extensive experiments across multiple datasets and model scales show that TESD consistently outperforms representative token-level and sequence-level methods, highlighting the necessity of improving supervision quality in OPSD.

cs.LG · cs.AI

新论文 · v1arXiv:2610.38636

Curriculum-Based Deep Reinforcement Learning for Robust Autonomous Rocket Landing under Atmospheric Uncertainty

Atin Chowdhury, Piyush Joshi

原文摘要

Autonomous far-range rocket landing is a challenging control problem because navigation, descent-rate regulation, attitude management, and fuel use must be coordinated in the presence of uncertain atmospheric and vehicle dynamics. This paper presents a curriculum-driven proximal policy optimization (PPO) framework for three-dimensional rocket landing in a stochastic environment incorporating altitude-dependent aerodynamic drag, wind shear, temporally correlated turbulence, discrete gusts, uncertain propulsion and aerodynamic parameters, thrust-vector misalignment, engine lag, actuator-gain variation, noisy observations, and command latency. Learning is organised into far-range approach, soft descent, and integrated landing stages. Policy transfer, critic warm-up after reward changes, rehearsal of earlier tasks, and progressive expansion of weather severity are used to support learning across these coupled phases. Across 100,000 evaluation episodes, the policy achieves 96,656 successful landings, corresponding to a success rate of 96.656\% and a 95\% Wilson confidence interval of 96.543--96.766\%. Success decreases from 98.84\% under zero-disturbance conditions to 88.07\% in the highest weather-severity band. Successful touchdowns exhibit small miss distances and low residual horizontal and vertical velocities. An exploratory logistic-regression analysis identifies mean wind speed as the strongest measured correlate of success, with initial distance, initial altitude, initial vertical velocity, and wind-shear exponent also associated with outcomes. The results quantify both the effectiveness of the learned policy over the evaluated disturbance distribution and the degradation that occurs under severe compound atmospheric conditions.

cs.AI

版本更新 · v3arXiv:2610.00391

Interpretable Synthetic Medical Tabular Data Generation for Clinical Decision Support Using Fuzzy Cognitive Maps

Michael Vasilakakis, Dimitris K. Iakovidis

原文摘要

Synthetic medical tabular data generation has become essential for developing and validating computer-based medical systems (CBMSs) when real clinical data is restricted due to privacy, ethical, or data availability limitations. Existing probabilistic and deep generative models often lack interpretability and fail to preserve clinically meaningful dependencies, limiting their suitability for safety-critical applications. This paper proposes a novel application of Fuzzy Cognitive Maps (FCMs) in a framework for synthetic medical tabular data generation with explicit causality and privacy preservation. Clinical features are described using linguistically interpretable fuzzy sets, and inter-feature dependencies are encoded as FCM edge weights computed from fuzzy set intersections. Synthetic patient records are generated by propagating randomly initialized linguistic activation vectors through the FCM until convergence, followed by defuzzification to produce clinically coherent numerical values. The approach natively handles mixed data types, and domain constraints common in health records. Experimental evaluation on UCI medical benchmark datasets demonstrates competitive performance under a Train-on-Synthetic-Test-on-Real (TSTR) protocol. The proposed method achieves accuracy of up to 0.81 and AUROC of up to 0.90 on the Heart Disease dataset, matching or exceeding TVAE and Gaussian Copula baselines while running exclusively on CPU. Fidelity metrics including KS Complement (up to 0.91) and Correlation Similarity (up to 0.95) confirm strong statistical coherence, and DCR Baseline Protection scores consistently exceed those of TVAE, confirming adequate privacy guarantees. These results demonstrate that causally grounded, interpretable fuzzy modeling offers a computationally efficient and transparent alternative to deep generative models for trustworthy synthetic data generation in CBMSs.

cs.LG · cs.AI

新论文 · v1arXiv:2610.38634

"Close enough?" An investigation into multiplication errors in LLMs

William Bolton, Bezawit Tilaye, Huw Day

原文摘要

Large language models (LLMs) frequently fail at multi-digit arithmetic, but the underlying mechanisms governing these failures remain poorly understood. While recent work demonstrates that addition errors follow a "noisy quantisation" model localised around carry boundaries, whether this framework generalises to multiplication remains an open question. In this work, we evaluate multiplication capabilities across several small base LLMs on a dataset of 16,991 problems spanning varied operand lengths. We show that multiplication errors do not conform to the addition-style noisy quantisation model. Instead, we uncover a novel error regime in small Qwen models: errors in lower-order columns predominantly preserve parity. Conversely, higher-order digit errors shift toward off-by-one carry failures. Our findings suggest that arithmetic computation in LLMs relies on distinct, multi-periodic internal representations where parity is tracked more robustly than exact digit identity, providing new mechanistic insights into numerical reasoning in transformers.

cs.AI

新论文 · v1arXiv:2610.38632

The use of post-quantum cryptography in the automotive context

Mariana do Carmo Barata Gonçalves, Valderi Reis Quietinho Leithardt

原文摘要

This study comparatively evaluates post-quantum cryptography (PQC) in automotive communication scenarios, considering the threat posed by quantum algorithms such as Shor's and Grover's algorithms. The simulations use OMNeT++, Veins, INET, and SUMO on two hardware platforms and examine ML-KEM/CRYSTALS-Kyber, ML-DSA/CRYSTALS-Dilithium, and FALCON. ML-KEM and ML-DSA are finalized NIST standards, whereas FALCON is a NIST-selected candidate pending final standardization. The evaluation considers a rural V2V scenario and an urban V2X scenario supported by a roadside unit. Kyber exhibits low {key encapsulation mechanism (KEM)}\color{black} operation latency, Dilithium provides balanced signature performance, and FALCON has high key-generation and signing costs but efficient verification. The results are interpreted as a comparative assessment among the evaluated PQC schemes under the reported simulation conditions; {a conventional ECDSA/ECDH baseline measured in the same simulation setup is also reported for reference.}\color{black} The resulting dataset can support future studies of cryptographic selection in automotive systems.

cs.CR · cs.DC

新论文 · v1arXiv:2610.38631

Right Numbers, Wrong Questions: Evaluating LLMs on Underspecified Financial Queries

Radha Yadav, Prasanna Devadiga, Peeyush Mishra, Apoorv Singh

原文摘要

Financial assistants answer questions that sound factual but depend on what the user leaves unsaid: what a data figure measures, which product variant is meant, and the investor's situation and the rules that apply. An assistant that ignores these can still answer with a real number from its data, one that answers a different question. We call this frame collapse. We study it in Indian mutual funds, where product variants and tax rules are formally defined, so the correct answer can be computed for every reading. One study tests each challenge. Given an ambiguously labelled figure, models used it, often under the user's label. Given every alternative labelled, they listed them all, but the layout decided which came first. Missing a fact about the investor, weaker agents assumed a default or an outdated tax rule; requiring the fact did not guarantee its use. Because such answers match their data, checks against the data pass them. An AI judge caught mislabelled figures only when told what each field means, and still passed answers that silently chose another reading. We show how these failures arise, not how often, and propose controls for financial assistants.

cs.AI · cs.CL · q-fin.GN

新论文 · v1arXiv:2610.38629

ItemCompass: Real-Time Edge-AI Wearable Vision for Tag-Free Domestic Object Retrieval

Tsz Lok Cheung, Jeff Kai-Tai Tang, Anthony Kong, Zackary P. T. Sin

原文摘要

Misplacing household objects disrupts daily routines, especially for elderly users. ItemCompass addresses this with a real-time, tag-free wearable AR system that builds a persistent digital twin of the home for natural language object retrieval. A custom eyewear node streams visual and inertial data to an edge server, where YOLOv11n detection, Siamese re-identification, and a Pedestrian Dead Reckoning engine log object locations as Spatial Anchors in InfluxDB. Voice queries are resolved by a local Faster-Whisper and Qwen2 LLM pipeline, delivering concise spoken and AR guidance on a heads-up display. Evaluation shows 0.40 m localization drift, 97.5% step precision, and mAP@0.5 of 0.874, with users rating Accuracy and Trust at 4.6/5.0. The system highlights always-on sensing, conversational spatial memory, and privacy-by-design for wearable computing.

cs.HC

新论文 · v1arXiv:2610.38628

The Reality Gap in Automated Driving Systems Testing: Landscape, Challenges, and Research Directions

Stefano Carlo Lambertenghi, Oliver Weissl, Johannes Betz, Andrea Stocco

原文摘要

Simulation is essential for testing automated driving systems (ADS), but discrepancies between simulation and reality can undermine testing conclusions. It remains unclear which discrepancies the literature addresses and what evidence supports correspondence claims. We present a systematic mapping of 235 primary studies that measure or mitigate the reality gap in ADS testing, selected from 4,195 publications. We characterise objectives, targets, approaches, experimental setups, and evaluation evidence. Our classification distinguishes simulated and real-world execution across six ADS test components, separately for each approach and its evaluation reference. This distinguishes real-world information used to construct an approach from evidence used to evaluate its claims. Of the included studies, 76% address mitigation, primarily targeting scenario and actor realism and perception, while 94% report validation or measurement procedures. Only 61 studies report metrics from multiple families covering sensor/perception correspondence, ADS behaviour, vehicle dynamics, or safety outcomes; this coverage does not establish causal links between discrepancies and test verdicts. The synthesis highlights that real-world content and physical execution must be interpreted against the claim evaluated. The findings motivate claim-specific evaluation and component-level reporting to establish which discrepancies affect testing conclusions and when simulation evidence supports conclusions about real-world ADS behaviour.

cs.SE · cs.RO

新论文 · v1arXiv:2610.38624

SelectSep: Target-Selective Video Queries for Audio Source Separation

Suyeon Lee, Doyeop Kwak, Joon Son Chung

原文摘要

Video-queried sound separation (VQSS) aims to isolate a target sound from an audio mixture using its corresponding video as a query. However, scene-level video queries can become ambiguous when multiple sounding objects are visible, particularly when the target and interferer are semantically similar. We propose SelectSep, a target-selective VQSS framework that jointly uses text and a single click coordinate to specify the target source and instance without requiring segmentation at inference time. We adapt the visual encoder through target-feature distillation with text and click conditioning, and then fine-tune the separator using the adapted visual features. We also introduce an on-screen interference setting, where both the target and interferer are visible, to evaluate target selectivity. Experiments on standard benchmarks and the on-screen interference setting demonstrate consistent improvements in separation quality and target selectivity, particularly for mixtures containing semantically similar sources.

eess.AS · cs.MM · cs.SD

新论文 · v1arXiv:2610.38623

Cross-Primitive Consistency in Jev

Xu Liu, Guikun Chen, Kanzhi Wu, Wenguan Wang

原文摘要

Jev enables efficient decision-making with large language models (LLMs) through typed querying primitives, allowing the same semantic state to be expressed in different formats, such as binary and multiple-choice queries. However, the consistency of decisions across primitives has not been systematically evaluated. This work introduces PrimaCons, a four-axis benchmark for assessing cross-primitive consistency while preserving the semantics of the query. Evaluations across three Jev sizes reveal consistency violations across all four axes. Our analysis shows that these violations follow systematic patterns and that cross-primitive discrepancies predict decision failure with a ROC-AUC of 0.91. To mitigate these inconsistencies, we propose the Cross-Primitive Residual Calibrator (CPRC), which attaches a lightweight residual network to a frozen backbone and jointly optimizes predictive accuracy and cross-primitive consistency. Under a leave-one-domain-out protocol, CPRC reduces cross-primitive inconsistency by 58.57% and improves accuracy by +2.97%., demonstrating its effectiveness in both in-domain and out-of-domain settings. Our findings establish cross-primitive consistency as a key dimension for evaluating Jev and provide a practical approach to improving the reliability of its decisions. Code and benchmark is available at https://github.com/67L1/PrimaCons-CRPR.

cs.CV · cs.CL

新论文 · v1arXiv:2610.38621

When LLM Architectures Meet Smart Contract Vulnerability Detection: a Replication Study

Gerardo Iuliano, Gabriele De Vito, Dario Di Nucci

原文摘要

Smart contracts are immutable programs deployed on blockchain platforms, where vulnerabilities can translate directly into financial loss. Among the techniques proposed for their detection, recent work has relied increasingly on Large Language Models (LLMs) guided by carefully crafted prompts. However, the evidence accumulated so far rests almost entirely on the dense Transformer architecture behind the GPT line and on model snapshots already scheduled for deprecation, leaving open the question of whether the reported behaviors reflect a general property of LLMs or an artifact of that specific design. This paper presents an extended replication of the empirical study by Chen et al. on LLM-based smart contract vulnerability detection. We replicate the original protocol on GPT-4 as a baseline, followed by a differentiated replication, executing the protocol on representative models based on Mixture-of-Experts and RNN-like designs, together with an attempted preliminary evaluation of State Space Models. The exact replication confirms the findings of Chen et al., including the high-recall, low-precision detection pattern they report on GPT-4. Nevertheless, the differentiated replication shows that this pattern does not transfer uniformly across the evaluated models. Those from the same architectural family may also exhibit different behaviors, indicating that architectural family alone is insufficient to predict the resulting detection profile. We observe the same qualitative dense-Transformer profile in both GPT-4 and Gemma-3, despite a gap of roughly two orders of magnitude in parameter counts, whereas two Mixture-of-Experts models from different lineages exhibit qualitatively divergent behaviors, indicating that architectural family alone is insufficient to predict the detection profile.

cs.SE

新论文 · v1arXiv:2610.38620

Think Before You Act: Decision Gate for LLM Agents

Iftach Shoham, Yuval David, Offer Akrabi, Erez Bilgory, Ido Levy, Sami Marreed, Sergey Zeltyn, Segev Shlomov

原文摘要

LLM agents increasingly perform consequential actions through external tools, yet their proposed actions are often executed without independent verification of policy compliance or task completion. We introduce JevAct, a runtime verification framework that intercepts selected agent actions before execution and enables feedback-driven correction. JevAct compiles domain policies into executable state checks and structured questions evaluated by a prefill-only decision model, which produces probability-based judgments without relying on LLM generation. By combining deterministic verification of tool-state facts with probabilistic assessment of conversational context, the framework identifies potentially invalid actions and premature task termination, providing targeted feedback for bounded revision. JevAct operates independently of the underlying agent model and requires no modifications to its parameters or tools. We evaluate JevAct across eleven LLM agents on $τ^2$-bench Airline and Telecom tasks and BFCL. Results show improvements in agent reliability across multiple models and benchmarks, with particularly consistent gains on Telecom and BFCL, while performance on Airline is more mixed. Overall, these findings suggest that combining structured decision models with executable verification can improve the reliability of tool-using LLM agents.

cs.AI

新论文 · v1arXiv:2610.38617

How Deterministic SAST and AI Security Agents Divide the Work: Coverage, Harness Policy and Cost in Snyk VulnBench 2.0

Liran Tal, Chris Liu, Charlotte Fereday, Sebastian Roth, Brian Clark

原文摘要

We ask what AI coding agents and AI security harnesses find that deterministic static application security testing (SAST) does not, and what they miss that SAST catches. VulnBench 2.0 is a benchmark of 108 hand-curated, attacker-reachable vulnerabilities in 20 open-source web applications in Go, JavaScript/TypeScript, Python and Java; 62 flow across more than one file. A finding is credited only if it locates the vulnerability's attacker-controlled source and its dangerous sink, each within two lines. We evaluate nine productized configurations under one blind protocol: the Snyk Code static analyzer, Claude Code's /security-review with three model and effort settings (one with the Snyk MCP server), Codex Security with GPT-5.6 Luna, Terra and Sol, and the DeepSec scanner with two model backends. Snyk Code reached 82.4% macro recall (89 of 108) and Claude Code with Opus 5 at xhigh effort 79.3% (85 of 108); they disagree on 28 vulnerabilities, split 16 to 12, too few to tell them apart. Neither engine was sufficient alone: together they reached 101 of 108, the ceiling of all seven comparable configurations combined, and the AI configurations also reported at least seven real vulnerabilities that the reference set did not contain and Snyk Code did not report. What an AI engine misses depends on its harness as much as on its model: without Claude Code's built-in review policy, the same model matched 16 instead of 9 of the 20 vulnerabilities in the classes that policy excludes or restricts (supplementary run on 19 of 20 applications); Codex Security with GPT-5.6 Sol located 80 vulnerabilities at file level but 34 at line level; DeepSec's model-free file selection kept a file from only 56 of the 108 flows. Coverage and cost were only loosely related. The harness, fixtures, reference sets and all run data are public.

cs.CR · cs.AI · cs.SE

新论文 · v1arXiv:2610.38616

Order Maintenance in Worst-Case Constant Time, Verified

Denis Firsov

原文摘要

Order maintenance asks for a data structure that keeps a sequence of elements under insertions and deletions and tells which of two elements comes first. We give an algorithm, assembled from published components, that performs each operation in worst-case constant time, and verify it in Lean 4. The algorithm is a program for a random-access machine deeply embedded in Lean, whose interpreter counts every instruction. We prove that the program answers every query as a simple reference specification does, that each operation takes at most a fixed number of steps, independent of the number of elements and of the history, and that after $t$ operations no value it has computed has more than $O(\log t)$ bits, so it runs unchanged on a machine with words of that size. A verified translation that preserves step counts exactly connects the high-level proofs to the machine program, so the interpreter is the only cost model to trust. An unverified native implementation shows the algorithm's practical cost.

cs.LO · cs.DS

版本更新 · v3arXiv:2512.21320

Adaptive Allele-Haplotype Incidence Indexing for Pangenome Queries: Representation, Reconstruction, and Benchmarking

Roberto Garrone

原文摘要

Population-scale analysis of phased genetic variants requires both allele-carrier retrieval and ordered haplotype context. We examine H1, an adaptive allele-haplotype incidence-row index, and H2, a canonical edge-path representation derived from a fixed, nonoverlapping variant catalog. We prove conditional reconstruction of abstract H2 walks and distinguish this property from unrestricted equivalence to genomic variation graphs. A completed local notebook experiment used a chromosome 1 interval (20-22 Mb), 200 diploid individuals, 24,921 SNV/indel records, and 45 SVTYPE-annotated records. For 24,966 extracted nonreference rows across 400 haplotypes, the serialized H1 incidence-row files occupied 0.872 MiB with a simple adaptive layout and 1.126 MiB with a custom Roaring-like layout, versus 1.190 MiB for a bitmap-payload baseline; a whole-file Zstandard archive of the adaptive layout occupied 0.207 MiB. For a separately constructed nonoverlapping SNV projection containing 22,727 sites, indexed H2 edge sequences occupied 75,130,882 bytes in a raw format and 5,156,418 bytes with context-Huffman encoding (14.57-fold reduction). Carrier-equivalence and graph-adjacency assertions passed in the notebook, but full crosscallset phasing, nucleotide-level SV reconstruction, and comparison with production indexes remain unresolved. The measurements establish a restricted implementation feasibility result, not superior end-to-end pangenome compression.

q-bio.GN · cs.DB · cs.DS

版本更新 · v2arXiv:2608.28665

Understanding Temporal Semantic Stability in Open-Vocabulary UAV Perception through Metric 3D Fusion

Saurbh Singh Jamwal

原文摘要

Recent open-vocabulary segmentation models have significantly advanced semantic perception for UAVs, for aerial and remote-sensing imagery, yet predictions from moving platforms can remain temporally inconsistent across repeated observations of the same physical scene. While semantic segmentation is typically evaluated on single images, temporal reliability remains less explored despite its importance for long-horizon robotic perception. In this work, we investigate temporal semantic stability by associating frame-wise predictions with persistent world-space locations through metric 3D fusion. We introduce a voxel-level evaluation framework that jointly characterises final semantic agreement, Semantic Belief Drift (SBD), Observation Persistence (OP), and semantic uncertainty from accumulated evidence. Experiments on UAVid-3D-Scenes reveal substantial frame-wise semantic variation and show that high aggregate world-space agreement can overstate temporal stability when many locations have limited repeated-observation support. Persistence-stratified analysis shows that recurrent voxels expose substantially greater semantic disagreement, while higher-persistence voxels exhibit lower direct consecutive semantic-evidence divergence. This behaviour is observed across two segmentation backbones and remains consistent under variations in voxel resolution, geometric association, and temporal sampling density. Overall, conditions that reduce world-space recurrence can increase apparent aggregate stability, demonstrating that semantic consistency must be interpreted together with observation support. Our findings establish observation persistence as an essential conditioning variable for evaluating long-horizon semantic reliability and provide a framework for analysing temporal semantic behaviour beyond image-level prediction.

cs.CV · cs.RO

版本更新 · v2arXiv:2504.05515

How Do Solidity Versions Affect Vulnerability Detection Tools? An Empirical Study

Gerardo Iuliano, Davide Corradini, Michele Pasqua, Matteo Cicalese, Mariano Ceccato, Dario Di Nucci

原文摘要

Smart contract vulnerabilities pose significant security risks to the Ethereum ecosystem, driving the development of automated tools for detection and mitigation. Smart contracts are written in Solidity, a rapidly evolving programming language that continues to add features and improvements to enhance smart contract security. New versions of Solidity change the compilation process, potentially affecting how tools interpret and analyze smart contract code. We use Solidity as a case study to investigate a broader problem in software analysis: whether tool effectiveness remains stable as the underlying programming language and execution environment evolve. In this continuously evolving landscape, we investigated the compatibility of detection tools with different Solidity versions. More specifically, we analyzed detection tools by empirically assessing (i) their crash resilience, (ii) their detection effectiveness, and (iii) their execution time across different versions of Solidity. We collected 2,500 real-world smart contracts to construct a balanced wild dataset and created a separate injected-vulnerability dataset comprising 270 contracts. We extended SmartBugs, a framework that enables the execution of vulnerability detection tools for Solidity, adding 11 new tools. Results indicate that most tools are crash-resilient to version 0.4. However, 20% of the evaluated tools have been updated to remain compatible. Tool performance varies across Solidity versions and is affected by Solidity changes; execution time is higher in version 0.4.x, which was used for evaluation. We present a list of Solidity changes that affect tool performance and offer actionable takeaways for both researchers and practitioners.

cs.SE

版本更新 · v2arXiv:2606.09255

Who Is the Agent Talking To? Participant-Aware Role Switching for Embodied Student-Support Dialogue

Iro Samuel, Filip Janik, Ewa Olton, Robert Smales, Harris Spratt, Shea Tait, Md Zia Ullah, Yanchao Yu

原文摘要

We present RPO-PDT, an embodied conversational agent that adapts its conversational role to the current participant. It acts as a Per- sonal Development Tutor (PDT) when supporting students and as a simulated student when faculty rehearse tutoring strategies. Voluntary closed-set participant verification informs a confidence- controlled role manager: stable enrolled-faculty matches activate the Student role, while enrolled students and unmatched partici- pants use the default PDT role and uncertain observations cause no transition. The system combines Furhat interaction, Rasa or- chestration, institutional retrieval, safeguarding, and LLM-based generation. User control is preserved through manual role override, consent-based facial enrolment, temporary interaction identifiers, and explicit retention or deletion of enrolled profiles. The demon- stration exposes both role-switching behaviour and these privacy controls in interaction.

cs.RO

新论文 · v1arXiv:2610.38613

TRIM: Temporal Run-Time Monitoring of 3D Object Detection via Activation Statistics

Hakan Yekta Yatbaz, Konstantinos Koufos, Mehrdad Dianati

原文摘要

Reliable perception is essential to intelligent transportation systems, yet deep neural networks can silently miss safety-critical objects while continuing to produce apparently plausible outputs. Existing run-time monitors for 3D object detection generally assess each frame independently and therefore cannot exploit the temporal evolution of occlusion, point sparsity, and scene complexity. We present TRIM, a lightweight temporal monitor that detects missed-object failures without modifying or retraining the underlying detector. TRIM summarises intermediate activations using compact channel-wise statistics and processes short sequences of these summaries with a temporal convolutional network. Experiments on NuScenes show that temporal monitoring improves AUROC from 0.686 to 0.704 and reduces the false alarm rate at 95% recall from 0.818 to 0.759 compared with single-frame monitoring. Early and intermediate backbone features provide the strongest monitoring signal, while the temporal inference head requires only 0.159 ms on a CPU.

cs.CV · cs.RO

版本更新 · v3arXiv:2609.18866

Hamming Ideals and Grobner Bases for ISD-like Syndrome Decoding

Roberto La Scala, Marco Marchesin, Sharwan K. Tiwari

原文摘要

We investigate an algebraic approach to the Syndrome Decoding Problem, based on a reformulation of the Hamming weight constraint and its integration with the Information Set Decoding paradigm. We begin with a systematic analysis of the Hamming variety, deriving its defining equations in terms of elementary symmetric functions. Since these equations may have high degree, we exploit convolution identities for elementary symmetric functions, together with factorizations based on Lucas' identity, to derive an equivalent formulation with auxiliary variables and equations of bounded degree. Building on this modeling, we generalize the ISD paradigm through an ISD-like decoding strategy, implemented by the GBDecode algorithm, in which only a subset of an information set is fixed. This approach reduces the size of the combinatorial search space at the cost of solving the associated multivariate nonlinear systems. To handle this algebraic component, we employ the MultiSolve algorithm, which replaces a single Grobner basis computation with a collection of computations on simpler systems, obtained by exhaustively assigning a varying number of indeterminates over the finite field. This provides a tunable balance between combinatorial search and algebraic solving. We evaluate the resulting approach experimentally on instances of the Syndrome Decoding Problem for random binary linear codes, using parameters corresponding to the NIST Security Category 1 parameter set of the Classic McEliece cryptosystem. The experiments assess the feasibility of this combinatorial-algebraic approach and provide insights into the practical behavior of Grobner basis techniques within an ISD-like decoding framework.

cs.CR · cs.SC · math.AC

新论文 · v1arXiv:2610.38611

V-CAPE: Visual Consistency Assessment for Product Image Editing

Iaroslav Melekhov, Roberto Alcover Couso, Francesco Taioli, Daniel Coelho, Artur Bekasov, Virginia Fernandez Arguedas, Jose Miguel Grande Saiz

原文摘要

Recent advances in generative image editing enable complex transformations such as background replacement, object manipulation, and pose adjustment from natural language instructions. However, verifying that these transformations preserve visual consistency, defined as the preservation of an object's intrinsic visual attributes, including geometry, texture, color, and fine-grained details, remains a largely unsolved problem. This challenge is particularly pronounced at scale, where manual inspection is infeasible and automated quality assessment (AutoQA) could become essential. In this work, we introduce Visual Consistency Assessment for Product Image Editing (V-CAPE), a large-scale dataset for evaluating visual consistency in generative image editing. The dataset consists of 40K unique source-target product image pairs, each annotated with binary accept/reject labels and structured failure modes capturing fine-grained inconsistencies such as geometric distortions, pose errors, and identity mismatches. V-CAPE combines real-world edited images with a synthetic subset constructed from 3D assets, enabling both realistic evaluation and controlled analysis. Vision-language models (VLMs) across all evaluated size categories on AutoQA achieve accuracy below 65%, indicating that the dataset poses a substantial challenge regardless of model scale. Our results highlight fundamental limitations of current models in verifying visual consistency under transformation, positioning V-CAPE as a benchmark for advancing fine-grained image editing evaluation.

cs.CV

新论文 · v1arXiv:2610.38608

The Artificial Personality Model: Theory, Implementation, Measurement and Experimental Validation in Conversational Agents

Alexander Dregger, Barbarella Petz, Erik Kuhn, Pia Volk, Andreas Oberweis, Stefan Hillmann, Jannik Strötgen

原文摘要

Artificial personality shapes user experience (UX) in human-machine interaction, yet coherent theoretical frameworks and validated measurement instruments remain limited. This paper refines and empirically evaluates the Artificial Personality Model (APM), a hybrid framework integrating human-centred and machine-specific personality dimensions. Across three experiments (N = 395), the model was operationalised and evaluated using the Artificial Personality Questionnaire (APQ). Factor analyses revealed that some human personality dimensions (e.g., agreeableness, conscientiousness) are partially transferable, whereas others (e.g., extraversion) did not emerge as distinct dimensions. Additional machine-specific dimensions were identified. The APQ provided encouraging initial psychometric evidence, while the human-centred BFI-2 showed poor reliability and an uninterpretable factor structure in Experiment 3. Experimental manipulations demonstrated significant effects of artificial personality on user satisfaction, continuous use intention, and social presence. The findings contribute an empirically refined framework and a novel instrument for measuring perceived artificial personality, offering practical guidance for designing conversational agents.

cs.HC · cs.AI

新论文 · v1arXiv:2610.38605

Efficient Group-Penalty k-means for Text Clustering with Noisy LLM-Generated Constraints

Feiteng Nie, Yuan Sun, Shengkun Zhu, Sheng Wang, Zhiyong Peng

原文摘要

k-means provides a simple and efficient foundation for text clustering, but embedding alone can miss task-specific semantic boundaries. Must-link (ML) and cannot-link (CL) constraints can correct such errors, yet conventional constrained clustering assumes that these relations are already supplied. LLMs can generate them without task-specific labels, but exhaustive querying is costly and their judgments can be incorrect. We present GPKmeans, an efficient Group-Penalty k-means method for text clustering with noisy LLM-generated constraints. GPKmeans uses LLM as an offline local pairwise annotator, querying selected anchor-candidate pairs for sparse ML links and constructing set-valued CL evidence without all-pairs queries. It converts connected components of the ML-link graph and the generated CL sets into groups with normalized, bounded soft penalties, limiting each group's influence independently of its size. Cached coordinate descent is proposed to efficiently solve the constraints clustering problem. We prove finite-step convergence and derive deterministic and probabilistic oracle-referenced bounds that relate objective distortion to the penalty coefficients and to the group-level error probabilities of the generated constraints. Across nine datasets, GPKmeans uses fewer LLM calls and yields more accurate constraints. It achieves the best average ACC, NMI, and ARI while running approximately 30 times faster than state-of-the-art constrained clustering methods.

cs.DB

新论文 · v1arXiv:2610.38602

STAR: Scalable TEE-based Anonymous Rate-limiter

Kosei Akama, Yoshimichi Nakatsuka, Koichi Moriyama, Keisuke Uehara

原文摘要

Protecting Internet services from attacks such as TLS/HTTP floods requires rate limiting, yet identifying users to enforce these limits can compromise their privacy. Anonymous rate limiting promises to reconcile these goals, but existing schemes either struggle to scale or assume that services and authorities do not collude. We present STAR, which uses server-side trusted execution environments (TEEs) to overcome these limitations. By enabling lightweight cryptographic operations, TEEs make authentication efficient, but introduce a privacy challenge: malicious services can observe memory-access patterns to infer user secrets. We address this threat through countermeasures against secret-dependent memory accesses and assess our implementation using dynamic analysis. To extend these efficiency gains across servers, we also design a secure sharding mechanism that distributes client requests. We demonstrate that strong privacy guarantees can coexist with efficient authentication at scale; STAR processes authentication requests in tens of microseconds and handles approximately 13.9K requests per second per CPU core.

cs.CR

新论文 · v1arXiv:2610.38600

Data Scaling Laws in Stereo Matching: From In-domain Fitting to Cross-domain Generalization

Tong Zhao, Di Liang, Yiming Zeng, Bo Xu, Yingzhi Tang, Chen Bai

原文摘要

In the era of large models, stereo matching is developing towards generalizable foundation models trained on million-scale synthetic images. However, how model performance scales up with synthetic data is still underexplored. In this work, we preliminarily investigate the in-domain and cross-domain data scaling laws in stereo matching. A realistic synthetic dataset, named XStereo, containing 200 thousand samples is first built to serve as a high-quality benchmark for data scaling research. In-domain training on five large-scale datasets demonstrate a two-regime scaling behavior with data, transitioning from the standard power law to saturation, where the critical transition point is approximately invariant under a fixed model. Cross-domain performance exhibits a substantially weaker and less predictable dependence on the source-domain data scale. The distribution and coverage diversity are more effective for diminishing domain gaps. More instructive suggestions are provided for high-efficiency data construction and training. The insightful findings are significant verification and extension of the existing scaling laws in both language and vision, paving the way to efficient and stronger stereo matching. The XStereo dataset is public at https://huggingface.co/datasets/Tong-Zhao/XStereo.

cs.CV

新论文 · v1arXiv:2610.38598

Two-Stage Clipping: Linear-Time Approximate and Exact Mixed-Norm Projections for Transformers

Michel Barlaud, Jean-Paul Marmorat

原文摘要

Large Language Models (LLMs) based on Transformer architectures have achieved remarkable performance across artificial intelligence tasks, but their computational cost remains a major bottleneck. Structured sparsification provides a promising approach to reducing this cost. In particular, $\ell_{1,\infty}$ projections can induce column-wise sparsity in model matrices, but existing proximal methods (Prox) typically require $\mathcal{O}(nm\log(nm))$ operations for matrices in $\mathbb{R}^{n\times m}$, limiting their computational and energy efficiency. In this paper, we introduce Two-Stage Clipping (TSC), an efficient structured sparsification operator inspired by bilevel optimization. Rather than solving a bilevel optimization problem in the strict sense, TSC decomposes the computation into two successive stages. First, group-level quantities are projected to allocate the global sparsity budget and identify active groups. Second, the resulting values are used as group-wise clipping thresholds for the matrix coefficients. For square attention matrices ($n \times n$), the complexity of our TSC method is $O(n^2)$, which is linear in the number of matrix coefficients. We establish a theoretical bound on the discrepancy between TSC and the exact proximal projection and show on synthetic data that the additional Euclidean approximation cost remains small in practice. Extensive benchmarks demonstrate substantial runtime improvements over proximal baselines and validate the theoretical norm identities underlying the proposed construction.

cs.LG

新论文 · v1arXiv:2610.38595

Rethinking LLM Jailbreak Evaluation: Continuous Risk Landscapes Beyond Binary Outcomes

Yukai Zhou, Wenjie Wang

原文摘要

A binary success indicator is a natural representation for discriminative tasks such as image classification under adversarial perturbations, where each input is mapped to a single prediction. However, generative tasks are fundamentally different: an LLM jailbreak prompt induces a distribution over open-ended trajectories, while a sampled response reveals only one path. Yet LLM jailbreak evaluation typically retains the binary response indicator underlying attack success rate, obscuring the surrounding structure of possible generations. We introduce a continuous, context-conditioned risk landscape over first-token branches, estimated by fixing candidate openings and repeatedly sampling their continuations. This continuous risk-landscape perspective reveals two complementary properties: current decoder exposure and safe rerouting capacity, which have been obscured by binary-indicator-based ASR. The resulting representation also provides a common basis for comparing clean prompts, attacked variants, and attack strength against a known adaptive defense. Across multiple target models and jailbreak attacks, we uncover risky branches beneath apparently safe outputs, identify qualitatively different ways attacks reshape the model's opening distribution, and show that attacks strongest before a defense do not necessarily remain the strongest after the adaptive defense reacts. These findings recast jailbreaks as deformations of the surrounding continuation-risk landscape, establishing a more informative foundation for understanding jailbreak behavior and developing safer language models.

cs.LG · cs.CL

版本更新 · v2arXiv:2509.00728

A Survey on Open Dataset Search in the LLM Era: Retrospectives and Perspectives

Pengyue Li, Sheng Wang, Hua Dai, Zhiyu Chen, Zhifeng Bao, Brian D. Davison

原文摘要

High-quality datasets are typically required for accomplishing data-driven tasks, such as training medical diagnosis models, predicting real-time traffic conditions, or conducting experiments to validate research hypotheses. Consequently, open dataset search, which aims to ensure the efficient and accurate fulfillment of users' dataset requirements, has emerged as a critical research challenge and has attracted widespread interest. Recent studies have made notable progress in enhancing the flexibility and intelligence of open dataset search, and large language models (LLMs) have demonstrated strong potential in addressing long-standing challenges in this area. Therefore, a systematic and comprehensive review of the open dataset search problem is essential, detailing the current state of research and exploring future directions. In this survey, we focus on recent advances in open dataset search beyond traditional approaches that rely on metadata and keywords. From the perspective of dataset modalities, we place particular emphasis on example-based dataset search, advanced similarity measurement techniques based on dataset content, and efficient search acceleration techniques. In addition, we emphasize the mutually beneficial relationship between LLMs and open dataset search. On the one hand, LLMs help address complex challenges in query understanding, semantic modeling, and interactive guidance within open dataset search. In turn, advances in dataset search can support LLMs by enabling more effective integration into retrieval-augmented generation (RAG) frameworks and data selection processes, thereby enhancing downstream task performance. Finally, we summarize open research problems and outline promising directions for future work. This work aims to offer a structured reference for researchers and practitioners in the field of open dataset search.

cs.IR · cs.DB