跳到正文
研踪PaperTrail

版本更新

查看已发布论文的最新修订,在详情页对照实际观测到的版本。

部分采集异常

全站更新概况

+1112新增论文
+875其中 AI 相关
+133已有论文修订
+94新增 AI 导读

arXiv 最近完成扫描:2026-11-19 23:27 · 全站最近入库:2026-11-19 19:09各信源进度 →

统计口径与数据新鲜度

统计 2026-11-18 23:30 — 2026-11-19 23:30(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-19 23:27最近发现新增版本:2026-11-19 19:09库内论文最新更新时间:2026-11-19 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。

27,982 已收录论文23,249 AI 相关8,559 有修订112 HF 社区发现

论文修订列表

时间范围跟随排序:版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常,查看状态 →

找到 8,559 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-19 23:25(北京时间)
版本更新 · v2arXiv:2610.32255

Anti-coherence Regularized Absolute Scaling for Out-of-Distribution Detection

Donghwan Kim, Youngwoong Jin, Hyunsoo Yoon

原文摘要

Out-of-distribution (OOD) detection is recognized as a critical problem in AI safety. SCALE is an effective post-hoc OOD detection method in the activation-shaping family that requires no training data and rescales penultimate activations using a percentile-based magnitude ratio. However, this ratio is ill-defined when negative activations are present, since positive and negative contributions cancel within the underlying sum, causing SCALE to degenerate on backbones such as ViT. We address this with an Absolute Fix that computes the ratio over absolute-valued activations rather than discarding negative activations through ReLU. Building on this corrected scale, we propose Anti-coherence regularization, which penalizes the scaling factor by the fraction of a sample's max-logit contributions to the max logit that are sign-mismatched and thereby suppresses unreliable evidence for the predicted class. Despite requiring no access to training data or training labels, our method ties or outperforms activation-shaping methods that rely on training data in terms of AUROC and FPR@95 on CIFAR-10 and ImageNet under the OpenOOD v1.5 protocol.

cs.LG · cs.AI

版本更新 · v5arXiv:2503.07338

Aligned Delta-Triplane Transformers as Occupancy World Models

Haoran Xu, Peixi Peng, Shijun Guo, Guang Tan, Yiqian Chang, Yisen Zhao, Shuaixian Wang, Yonghong Tian

原文摘要

Occupancy World Models (OWMs) aim to predict future 3D occupancy scenes from historical observations and future ego motions, providing a useful world simulation tool for autonomous driving. Existing methods usually rely on large networks to implicitly align multi-frame historical states and predict future occupancy in a full-state manner, which is costly and redundant because most scene regions remain unchanged over short time intervals. In this paper, we propose Aligned Delta-Triplane Transformer (ADTT), a compact 4D OWM that explicitly aligns historical triplanes with ego-motion compensation and predicts only future scene changes. Based on the aligned triplane prior, a query-conditioned Transformer predicts residual changes, where ego-motion queries guide controllable future motion and learnable external queries capture scene changes beyond ego motion. The predicted changes are added to the aligned prior and decoded into future occupancy scenes. Experiments on Occ3D-nus show that ADTT achieves state-of-the-art forecasting performance with fewer parameters and higher FPS. Our code is publicly available online: https://github.com/kyoran/ADTT.

cs.RO · cs.AI

版本更新 · v2arXiv:2609.05880

Grounded and Faithful P&ID Reasoning: Constraining Vision-Language Models with Recovered Evidence Graphs

Prathamesh Gadekar, Sagar Srinivas Sakhinana, Venkataramana Runkana

原文摘要

Piping and Instrumentation Diagrams (P&IDs) are the authoritative maps of process plants: isolation, maintenance, and HAZOP decisions depend on what connects to what. Vision-language models describe these sheets fluently, yet they often invent or miss process connections---and an invented or missed link can reverse an isolation or reachability call, so a plant decision cannot trust a fluent answer that was never checked against the linework. We instead recover an explicit graph of the drawing---its symbols, the process connections between them, and the tags that name them---and then require the model to answer only by querying that graph through seven read-only operators, so a topology claim is returned only when it cites the query results that support it. On TopoPID-VQA, a new suite of 3000 topology questions over these sheets, Graph-Grounded Harness (Ours) raises exact match accuracy from 36.7--41.3% under image-only prompting to 74.3--76.0% for Qwen3-VL-4B, Qwen3-VL-8B, and Gemma-4-E4B. It does so on an imperfect substrate: on Digitize-PID dataset the recovered graph scores F1 0.742 on exact process connections, and 0.801 once symbols and tags are pooled in. The residual errors track that gap---grounding pays off where the recovered graph is right, and perception error still breaks topology questions where it is not.

cs.LG · cs.AI

版本更新 · v2arXiv:2602.03423

Origin Lens: A Privacy-First Mobile Framework for Cryptographic Image Provenance and AI Detection

Alexander Loth, Dominique Conceicao Rosario, Peter Ebinger, Martin Kappes, Marc-Oliver Pahl

原文摘要

The proliferation of generative AI poses challenges for information integrity assurance, requiring systems that connect model governance with end-user verification. We present Origin Lens, a privacy-first mobile framework that targets visual disinformation through a layered verification architecture. Unlike server-side detection systems, Origin Lens performs cryptographic image provenance verification and metadata-based AI detection locally on the device via a Rust/Flutter hybrid architecture. Our system integrates multiple signals - including cryptographic provenance, generative-model metadata and watermarks, and optional retrieval-augmented verification - to provide users with graded confidence indicators at the point of consumption. We discuss the framework's alignment with regulatory requirements (EU AI Act, DSA) and its role in verification infrastructure that complements platform-level mechanisms.

cs.CR · cs.CV · cs.CY · cs.HC

版本更新 · v2arXiv:2609.03035

You Can't Escape Your Activations : Evaluation Awareness and Multi-Agent Monitoring

Jaee Ponde, Aritra Das, Mihir More, Debayan Gupta

原文摘要

LLM agents are increasingly deployed in multi-agent systems, where they can collude while keeping their actions benign. Output monitors designed to detect such collusions can be fooled by obfuscation and steganography, motivating the use of probes trained on internal activations. However, these probes are usually evaluated on agents that do not know they are being watched. We study how activation-based detection changes when agents are explicitly informed that their internal activations are being monitored, and when they additionally receive feedback from the monitor. We keep the models, probes, and thresholds fixed and change only what the agents are told: nothing (baseline), that an activation monitor is present (aware), or that a monitor is present together with the previous round's score (feedback). We test two games, a four-agent blackjack game and a two-agent Simmons prisoners game, using Qwen3-32B-AWQ and GPT-OSS-20B in homogeneous and mixed pairings. Telling agents about the monitor does not hide them. The best probes stay accurate in all three conditions, and the agents keep colluding.

cs.MA · cs.LG

版本更新 · v3arXiv:2602.09593

Why Does Counterintuitive Likelihood Behavior Rarely Emerge in Tabular Anomaly Detection?

Donghwan Kim, Junghun Phee, Hyunsoo Yoon

原文摘要

Deep generative models with tractable likelihoods, exemplified by normalizing flows, offer an effective basis for anomaly detection through likelihood-based scoring. We demonstrate that, unlike in the image domain where deep generative models frequently assign higher likelihoods to anomalous data, such counterintuitive behavior occurs rarely in tabular settings. We first introduce a domain-agnostic formulation that enables consistent detection and evaluation of the counterintuitive phenomenon, addressing the lack of a precise definition in prior work. Through extensive experiments on 47 tabular datasets benchmarked against 13 baseline models and on 10 CV/NLP embedding datasets from ADBench, we show that the phenomenon is consistently rare in general tabular data and that normalizing flow likelihood achieves competitive anomaly detection performance. We further provide theoretical and empirical analyses attributing this disparity to differences in dimensionality and feature correlation between tabular and image data. Therefore, our results indicate that likelihood-based detection with normalizing flows is a practical approach for tabular anomaly detection.

cs.LG · cs.AI

版本更新 · v3arXiv:2605.19342

Semantic-Enriched Latent Visual Reasoning

Tianrun Xu, Yue Sun, Qixun Wang, Jingyi Lu, Yuan Wang, Tianren Zhang, Longteng Guo, Fengyun Rao 等 11 位作者

原文摘要

Multimodal latent-space reasoning aims to replace explicit thinking with images by performing visual reasoning directly in a compact latent space. However, existing approaches largely rely on visual supervision and produce latent representations that lack sufficient semantic richness, limiting their ability to support diverse region-level reasoning tasks. In this work, we introduce Semantic-Enriched Latent Visual Reasoning (SLVR), a two-stage learning framework that enriches latent representations with attribute-level visual semantics and aligns them with diverse reasoning objectives. In the first stage, SLVR learns semantically enriched region-centric latents under fine-grained attribute supervision. In the second stage, we design Multi-query Group Relative Policy Optimization (M-GRPO) to align latent representations across multiple queries grounded in the same region. To support this framework, we construct SLV-Set, comprising approximately 400K region-level attribute annotations and 800K multi-query question answering samples, and introduce SV-QA, a benchmark that evaluates latent reasoning under semantic variation. Experiments demonstrate that SLVR improves the robustness and semantic consistency of latent visual reasoning compared to existing baselines.

cs.CV

版本更新 · v2arXiv:2605.14413

MahaVar: OOD Detection via Class-wise Mahalanobis Distance Variance under Neural Collapse

Donghwan Kim, Hyunsoo Yoon

原文摘要

Out-of-distribution (OOD) detection is a critical component for ensuring the reliability of deep neural networks in safety-critical applications. In this work, we present a key empirical observation: for in-distribution (ID) samples, class-wise Mahalanobis distances exhibit a pronounced sharp minimum structure, where the distance to the nearest class is small while distances to all other classes remain large, resulting in high variance across classes. In contrast, OOD samples tend to exhibit a less pronounced sharp minimum structure, producing comparatively lower variance across classes. We further provide a theoretical analysis grounding this observation in Neural Collapse geometry: under relaxed Neural Collapse assumptions on within-class compactness and inter-class separation, ID samples are shown to structurally exhibit high class-wise distance variance, offering a theoretical basis for its use as an OOD score. Motivated by this observation and its theoretical backing, we propose MahaVar, a simple and effective post-hoc OOD detector that augments the Mahalanobis distance with a class-wise distance variance term. Following the OpenOOD v1.5 benchmark protocol, MahaVar achieves state-of-the-art performance on CIFAR-100 and ImageNet, with consistent improvements in both AUROC and FPR@95 over existing Mahalanobis-based methods across all benchmarks.

cs.LG · cs.AI

版本更新 · v2arXiv:2605.14431

FuzzAgent: Multi-Agent System for End-to-End Evolutionary Library Fuzzing

Yunlong Lyu, Peng Chen, Fengyi Wu, Junzhe Yu, Hao Chen

原文摘要

Library fuzzing synthesizes harnesses that expose new API interactions, but deploying it end to end still requires extensive project-specific integration. Existing LLM-based systems automate individual steps, yet they treat execution outcomes as coarse signals: a stalled campaign does not reveal which state blocks progress, and a crash trace does not reveal whether the library or the harness is at fault. We present FuzzAgent, a multi-agent system that builds and evolves a complete fuzzing campaign from a source tree alone. Specialized agents acquire project knowledge and repair campaign artifacts automatically. Hierarchical coverage diagnosis localizes blockers from modules down to branches, and dependency-aware generation converts them into harnesses with the required API lifecycle. Crash validation recovers runtime object states to distinguish harness misuse from library bugs. We evaluate FuzzAgent on 20 real-world C/C++ libraries against five state-of-the-art baselines (OSS-Fuzz, OSS-Fuzz-Gen, PromptFuzz, PromeFuzz, and ProteusFuzz). FuzzAgent completes the full fuzzing lifecycle for all 20 libraries without human intervention at $3.17 per library. On the 20 libraries, it reaches 179619 branches, exceeding OSS-Fuzz, PromptFuzz, ProteusFuzz, PromeFuzz, and OSS-Fuzz-Gen by 45.1%, 73.2%, 87.7%, 92.1%, and 191.2%, respectively. FuzzAgent also identifies 102 new library bugs, 90 of which have already been acknowledged or fixed by upstream maintainers.

cs.SE · cs.CR

版本更新 · v2arXiv:2605.07313

When Stored Evidence Stops Being Usable: Scale-Conditioned Evaluation of Agent Memory

Jiaqi Shao, Yiyi Lu, Yunzhen Zhang, Bing Luo

原文摘要

Memory-agent evaluations report fixed-snapshot accuracy or retrieval quality, but these scores do not show whether evidence remains usable as irrelevant sessions (sessions not annotated as task-relevant evidence for the query) accumulate. We present a scale-conditioned evaluation protocol for agent memory under evidence-preserving growth: for each query, task evidence is held fixed while irrelevant sessions are added. The protocol logs agent-memory trajectories and reports four diagnostics: budget-compliant reliability, tail memory-call burden, failure-regime decomposition, and the usable-scale boundary where reliability falls below the target. Applied to LongMemEval and LoCoMo across flat, planar, and hierarchical memory interfaces, the protocol shows reliability loss is not a single phenomenon. On LongMemEval, HippoRAG stays within the two-call budget but loses 16-20 percentage points in budget-compliant reliability as irrelevant sessions are added; LiCoMemory's observed failures depend strongly on the agent, with Qwen3-8B exceeding the budget while Qwen3-32B and Qwen3-235B remain reliable in the tested range. The result supports a framework for making scalable-memory claims conditional on agent, interface, scale range, and interaction budget. Code and evaluation artifacts: https://github.com/AndyLu666/memory-at-scale

cs.AI

版本更新 · v2arXiv:2606.24403

RE4: Transformation-aware Imitation of Object Interactions Using Manipulation Modes

Arsh Chawla, Rahul Shome

原文摘要

Object interaction tasks have been a focus of advances in imitation learning. End-to-end methods, dominated by generative variants have shown leaps in performance but tend to be black boxes. Recent indications hint at demonstration lookup as the operating process underneath generative policy performance. In this paper, we revisit a few modern imitation learning benchmarks for object interactions, with the aim of composing a simple framework from first principles. We repurpose theories of manipulation modes and apply them to retrieve and transform demonstration datasets, creating a minimal strategy that preserves performance and robustness while remaining interpretable. We identify pose estimation as a key module that governs information about the object. This informs a manipulation mode-aware retrieval of a demonstration, a mode-aware transformation, a replan step that connects to the retrieval point while preserving mode constraints, returning a transformed demonstration for rollout. These compose four key steps of the proposed RE4 framework, evaluated over state-based and image-based benchmarks in simulated Push-T, Robomimic, and MimicGen as well as a real robot experiment. Robustness is measured in an adversarial study that evaluates sparse data regimes, a study with visual distractors, and the addition of an obstructing collision geometry. RE4 outperforms baselines, while notably preserving interpretability. The results overwhelmingly motivate the benefits of identifying simple interpretable building blocks to learn manipulation skills for object interactions.

cs.RO · cs.LG

版本更新 · v2arXiv:2610.14807

ASIWorld: Benchmarking Autonomous Agents in a Persistent Survival Sandbox

Jianfeng Lin, Runze Wang, Haorong Hong, Yuxuan Xie, Zeno Zeng, Zhongyuan Liu

原文摘要

Evaluating autonomous agents requires examining whether they can translate goals into coherent action across extended interactions. In persistent environments, this requires coordinating interdependent actions under incomplete observations, accounting for delayed effects, and adapting as earlier decisions shape subsequent opportunities. We introduce ASIWorld, a survival sandbox that combines persistent world and character state with character-scoped observations and a programmable asynchronous interface to study sustained goal execution. Agents pursue interdependent production and exploration tasks through direct actions or agent-authored programs that continue running between model calls. The evaluation assesses task success, the attainment of development achievements, and survival costs, complemented by an analysis of execution behavior. In an exploratory study of nine agent configurations using a common harness, eight complete the production task and six complete both tasks. Analyses of execution trajectories and performance across difficulty levels reveal different preparation, combat, and recovery behaviors among configurations with similar task outcomes. Incomplete preparation is associated with stalled progression, while configurations that complete the tasks differ in survival costs and the fulfillment of additional achievement criteria. These findings illustrate the value of assessing sustained goal execution through both task outcomes and the behaviors and costs associated with achieving them.

cs.AI

版本更新 · v3arXiv:2610.30951

OpenAttention: One Percent Is Enough with Tail Proxies

Hyunwoo Yu, Jongbeom Lee, Hyunbin Kim, Sungjun Park, Jaemin Choi, Jincheol Yang, Seunghun Moon, Bongjoon Hyun 等 11 位作者

原文摘要

Sparse attention reads only a small subset of the key-value cache, and how to treat the unread tail remains a key challenge. Discarding the tail biases the output, and sampling it as previous approaches do fails at reads of 5% and below, where the tail likely holds heavy hitters the selector missed. Our key observation is that the simplest possible proxy, one token that folds the entire tail into its count-aware mean, already yields lower output error than a sample at every read behind a practical selector. We further show in closed form that at low reads sampling nearly doubles the weight error of discarding while a single proxy stays below it. Building on these findings, we explore approximating the dense attention distribution with a few proxies that target the tail. We propose OpenAttention, a pipeline of clustering, ErrorGate and top-k selection followed by a count-aware mean proxy. To implement clustering and selection both efficiently and effectively, we design training-free Query-Geometry Clustering (QGC) and a Query-Geometry Selector (QGS), which compress the keys while respecting the query directions. Additionally, unlike prior methods that rank clusters by centroid alone, ErrorGate allocates the exact read by the estimated weight error of each cluster. On RULER-32K HARD with Llama-3.1-8B, OpenAttention retains 99% of dense accuracy at a 1% read. It also achieves state-of-the-art accuracy across models, context lengths and datasets. Our customized attention kernel for OpenAttention runs the decode attention stage 10$\times$ faster than dense attention at a 1% read.

cs.LG · cs.AI

版本更新 · v2arXiv:2505.05488

From Events to Enhancement: A Survey on Event-Based Imaging Technologies

Yunfan Lu, Xiaogang Xu, Pengteng Li, Yusheng Wang, Yi Cui, Huizai Yao, Mingchao Xu, Hui Xiong

原文摘要

Event cameras offering high dynamic range and low latency have emerged as disruptive technologies in imaging. Despite growing research on leveraging these benefits for different imaging tasks, a comprehensive study of recently advances and challenges are still lacking. This limits the broader understanding of how to utilize events in universal imaging applications. In this survey, we first introduce a physical model and the characteristics of different event sensors as the foundation. Following this, we highlight the advancement and interaction of image/video enhancement tasks with events. Additionally, we explore advanced tasks, which capture richer light information with events, \eg~light field estimation, multi-view generation, and photometric. Finally, we discuss new challenges and open questions offering a perspective for this rapidly evolving field. More continuously updated resources are at this link: https://github.com/yunfanLu/Awesome-Event-Imaging

cs.CV

版本更新 · v2arXiv:2607.27982

ViP-Rig: Visual-Prompted Controllable Rigging

Zihan Qin, Mingze Sun, Yifan Mao, Jialei Xu, Jingfeng Guo, Changrong Hu, Wenbo Zhao, Junjun Jiang 等 9 位作者

原文摘要

Rigging is inherently task-dependent because the same mesh may require different skeletons and deformation behaviors across animation tasks. In practice, artists often inspect an initial rig and repeatedly edit its skeletal structure and deformation behavior to meet specific animation requirements. Existing automatic methods primarily generate a plausible rig from geometry, offering limited explicit control over the resulting skeleton and deformation behavior. In this work, we present ViP-Rig, a visual-prompted framework that supports both prompt-first rigging and result-guided editing by injecting features extracted from user-drawn or edited 2D skeletal and rigidity prompts into frozen pretrained backbones. Specifically, ViP-Rig consists of two stages, Skeleton Generation and Skinning Prediction. In the first stage, the skeletal sketch is processed by the Dense-to-Compact Visual Prompt Encoding to produce compact, fixed-length conditioning tokens. The resulting tokens are injected into a frozen pretrained autoregressive generator through gated adapters to control joint placement and branching structure while preserving the generator's geometric prior. In the second stage, the rigidity map is processed using the same visual encoding design, while the pretrained skinning backbone remains frozen. The resulting tokens are symmetrically injected into the point and joint streams to modulate point-joint compatibility and the resulting skinning weights. Experiments on Articulation-XL2.0 and zero-shot evaluation on ModelsResource show that ViP-Rig more accurately recovers target skeletons and skinning weights than geometry-conditioned baselines under prompt-guided evaluation. Qualitative results further demonstrate explicit and localized control in both prompt-first rigging and result-guided editing.

cs.CV

版本更新 · v2arXiv:2608.24069

Poisoning Agentic Alpha: Adversarial Vulnerabilities Across Roles and Architectures in Multi-Agent Trading Systems

CheolWon Na, Hao Ni, Lukasz Szpruch, Zhangyang Wang, Dhagash Mehta, Saurabh Nagrecha, Alejandro Lopez-Lira, Chanyeol Choi 等 10 位作者

原文摘要

LLM-based multi-agent trading systems are moving from research prototypes to live deployments that control real assets. They ingest news and social media from the open web and pass it between agents, so a single corrupted signal can reach the final decision and cause financial loss. We study two adversaries that can introduce such signals without access to model internals: a low-barrier data adversary that plants manipulated content in web sources, and a compromised-agent adversary that tampers with an agent's prompt. To our knowledge, this is the first systematic empirical study in finance of how an adversarial signal enters a multi-agent trading system and whether it survives to alter the final trading decision. Along the role axis, we pair each of four roles---Analyst, Researcher, Trader, and Risk Manager---with an attack matched to its interface. Along the structural axis, we compare four communication topologies, interpreted with a simple parameter-free heuristic, the Adversarial Signal Preservation Score. Experiments on post-cutoff data span five assets and two target directions. We find that no architecture is inherently robust: majority voting offers conditional protection depending on benign-agent agreement, while compromising a terminal decision node can bypass upstream safeguards. These findings provide empirical insights for developing more effective defense strategies for multi-agent systems.

cs.AI · cs.CE · cs.CR · cs.MA

版本更新 · v3arXiv:2507.00535

Rethinking Group Recommender Systems in the Era of Generative AI: From One-Shot Recommendations to Conversational Group Decision Support

Dietmar Jannach, Amra Delić, Francesco Ricci, Markus Zanker

原文摘要

More than twenty-five years ago, early ideas emerged on how to design systems that provide recommendations to groups of users rather than individuals. Since then, a wide range of algorithmic approaches has been proposed to elicit individual preferences, aggregate them, and generate group recommendations. However, despite this substantial body of work, relatively few examples of real-world group recommender systems are in use. This observation invites reflection on the assumptions of the academic research, particularly regarding how inter-group communication unfolds and how recommendation-supported decisions should be made. In this essay, we suggest that some of these assumptions and corresponding system designs may not fully align with users' needs or expectations. We therefore outline a forward-looking perspective that explores how insights from group-decision making research and recent advances in Generative AI, including systems such as ChatGPT, could better inform the design of group recommender systems. As one possible direction, we consider settings in which human group members interact and exchange information through a chat based interface, while an AI-based agent supports the decision-making process. Such an approach may contribute to design more natural group and system interactions, and could help facilitate a broader adoption of group recommender systems in practice.

cs.IR · cs.AI

版本更新 · v3arXiv:2508.07388

Invert4TVG: A Temporal Video Grounding Framework with Inversion Tasks Preserving Action Understanding Ability

Zhaoyu Chen, Hongnan Lin, Yongwei Nie, Fei Ma, Xuemiao Xu, Fei Yu, Chengjiang Long

原文摘要

Temporal Video Grounding (TVG) aims to localize video segments corresponding to a given textual query, which often describes human actions. However, we observe that current methods, usually optimizing for high temporal Intersection-over-Union (IoU), frequently struggle to accurately recognize or understand the underlying actions in both the video and query, thus reducing the effectiveness of these methods. To address this, we propose a novel TVG framework that integrates inversion-based TVG as auxiliary objectives to maintain the model's action understanding ability. We introduce three kinds of inversion TVG tasks derived from the original TVG annotations: (1) Verb Completion, predicting masked verbs (actions) in queries given video segments; (2) Action Recognition, identifying query-described actions; and (3) Video Description, generating descriptions containing query-relevant actions given video segments. These inversion tasks are entirely derived from the original TVG tasks and are probabilistically integrated with them within a reinforcement learning framework. By leveraging carefully designed reward functions, the model preserves its ability to understand actions, thereby improving the accuracy of temporal grounding. Experiments show our method outperforms state-of-the-art approaches, achieving a 7.1\% improvement in R1@0.7 on Charades-STA for a 3B model.

cs.AI

版本更新 · v4arXiv:2601.20251

Efficient Evaluation of LLM Performance with Statistical Guarantees

Skyler Wu, Yash Nair, Emmanuel J. Candès

原文摘要

Exhaustively evaluating many large language models (LLMs) on a large suite of benchmarks is expensive. We cast benchmarking as finite-population inference and, under a fixed query budget, seek tight confidence intervals (CIs) for model accuracy with asymptotic frequentist coverage. We propose Factorized Active Querying (FAQ), which (a) leverages historical information through a Bayesian factor model; (b) adaptively selects questions using a hybrid variance-reduction/active-learning sampling policy; and (c) maintains validity through Pro-Active Inference---a finite-population extension of active inference (Zrnic & Candès, 2024) that enables direct question selection while preserving asymptotic frequentist coverage. In our experiments, FAQ delivers up to $5\times$ effective sample size gains over strong baselines on two benchmark suites, across varying historical-data missingness levels, with negligible computational overhead: this means that it matches the CI width of uniform sampling while using up to $5\times$ fewer queries. We release our source code and our curated datasets to support reproducibility and future research.

stat.ML · cs.LG

版本更新 · v3arXiv:2609.18526

The Illusion of Local Privacy: Confidentiality Boundary Failures in Consumer LLM Serving Systems

Youssef Hamdi Zafan Ibrahim, Muhammad Ikram, Mohammed Khalaf Salama

原文摘要

Running large language models (LLMs) locally is often considered more private than cloud-hosted inference because user prompts remain on the device. We ask whether keeping inference local is, by itself, sufficient to keep those prompts confidential. Our results show that it is not: prompt confidentiality also depends on how the surrounding serving software handles prompt data before, during, and after inference. We examine four boundaries at which prompt confidentiality can fail in consumer local-LLM serving systems: model loading, runtime memory, wrapper-level persistence, and the serving interface. To study these boundaries, we develop LLAnalyzer, a measurement framework that tests each boundary separately and traces observed failures to the responsible software component. Applying LLAnalyzer to four open-weight model families and two consumer deployment platforms, we find markedly different behaviour across boundaries. In a 24-hour AFL++ campaign with more than 12 million executions, we observe no parser crashes or successful malformed GGUF loads within the explored state space. Runtime memory tells a different story: we recover prompts after inference because multiple plaintext representations survive in allocator-managed memory, and sanitisation reduces this residue without eliminating it. We also find that consumer wrappers can extend prompt lifetime through plaintext persistence. At the serving boundary, we uncover a previously undocumented authorization flaw in llama.cpp that allows one authenticated client to restore another tenant's saved conversation state; the attack succeeds in 200/200 controlled trials. Separately, shared prompt-prefix caching exposes a remote timing oracle that remains distinguishable under WAN conditions. We argue that local LLM systems need explicit guarantees for prompt lifetime, persistent storage, and tenant isolation.

cs.CR

版本更新 · v4arXiv:2512.11908

Safe Learning for Contact-Rich Robot Tasks: A Survey from Classical Learning-Based Methods to Safe Foundation Models

Heng Zhang, Rui Dai, Gokhan Solak, Pokuang Zhou, Nikos Tsagarakis, Yu She, Arash Ajoudani

原文摘要

Contact-rich tasks pose significant challenges for robotic systems due to inherent uncertainty, complex dynamics, and the high risk of damage during interaction. Recent advances in learning-based control have shown great potential in enabling robots to acquire and generalize complex manipulation skills in such environments, but ensuring safety, both during exploration and execution, remains a critical bottleneck for reliable real-world deployment. This survey provides a comprehensive overview of safe learning-based methods for robot contact-rich tasks. We categorize existing approaches into two main domains: safe exploration and safe execution. We review key techniques, including constrained reinforcement learning, risk-sensitive optimization, uncertainty-aware modeling, control barrier functions, and model predictive safety shields, and highlight how these methods incorporate prior knowledge, task structure, and online adaptation to balance safety and efficiency. A particular emphasis of this survey is on how these safe learning principles extend to and interact with emerging robotic foundation models, especially vision-language models (VLMs) and vision-language-action models (VLAs), which unify perception, language, and control for contact-rich manipulation. We discuss both the new safety opportunities enabled by VLM/VLA-based methods, such as language-level specification of constraints and multimodal grounding of safety signals, and the amplified risks and evaluation challenges they introduce. Finally, we outline current limitations and promising future directions toward deploying reliable, safety-aligned, and foundation-model-enabled robots in complex contact-rich environments. More details and materials are available at our \href{ https://github.com/jack-sherman01/Awesome-Learning4Safe-Contact-rich-tasks}{Project GitHub Repository}.

cs.RO

版本更新 · v3arXiv:2608.07267

WNM-3D: A World Navigation Model with 3D Scene Conditioning for Closed-Loop VLN

Yuehao Huang, Yunzi Wu, Xiaotao Zhang, Xinhai Li, Jiankun Dong, Sunyao Zhou, Jiajun Lv, Chi Zhang 等 11 位作者

原文摘要

Recent vision-language navigation (VLN) systems increasingly adapt pretrained vision-language models (VLMs) into vision-language-action (VLA) policies that map egocentric observations and language instructions directly to navigation actions. Although semantically capable, such action-centric training does not explicitly model how the agent's visual observations evolve under its predicted motion. Generative world-action models (WAMs) jointly predict future observations and actions, yet existing WAMs for continuous VLN do not condition joint future-view and action generation on geometry-aware representations inferred from the observation history. We present WNM-3D, a generative World Navigation Model with 3D scene conditioning for continuous VLN. A frozen feed-forward geometry encoder extracts cross-view representations from monocular RGB history, and a trainable 3D Scene-to-Token Adapter converts them into a fixed-length scene prefix for the world-action Diffusion Transformer. Through block-causal attention, this prefix remains visible to every future video-action block throughout joint denoising, providing persistent geometric context. We train WNM-3D with supervised world-action learning, DAgger-style adaptation on policy-visited states, and Counterfactual DanceGRPO refinement. Across GN-Bench and VLN-CE, WNM-3D consistently outperforms the backbone-matched WNM-2D counterpart, demonstrating gains from 3D scene conditioning across distinct visual domains. WNM-3D further outperforms strong VLN baselines on GN-Bench and demonstrates closed-loop deployment on a physical robot. Component and stage-wise ablations support the Adapter design and the complementary roles of DAgger-SFT and subsequent reward-guided refinement.

cs.AI · cs.CV · cs.RO

版本更新 · v2arXiv:2610.36527

ETC-Bench: A Multilingual Benchmark for Evaluation-Side Transcript Canonicalization

Zhiheng Qian, Junhao Du, Jing Peng, Hanqi Li, Kunyang Peng, Feng Xue, Shuai Wang, Kai Yu

原文摘要

Written transcripts of the same speech can differ in ways that are not uniquely determined by the speech signal. We formulate evaluation-side transcript canonicalization (ETC), which maps multiple surface forms to a single canonical form when their differences are not determined by speech. To our knowledge, ETC-Bench is the first and most comprehensive multilingual benchmark for evaluation-side transcript canonicalization, covering 181 phenomenon types across 12 languages. Each instance is a minimal pair that shares a sentence context and differs only in a target span exhibiting one phenomenon. To evaluate both canonicalization success and semantic preservation, we propose Semantic-preserving Exact-match Normalization Accuracy (SENA), which combines exact agreement between independently canonicalized pair members with a pair-relative BERTScore constraint against information loss. We further introduce the Taxonomy-guided Agent Canonicalization Skill (TACS), which provides LLM agents with phenomenon descriptions and explicit canonicalization contracts. Experiments with five baseline configurations and three TACS-based agents show that the agents outperform the baseline systems on shared languages. ETC-Bench provides a systematic testbed for evaluation-side transcript canonicalization across languages.

cs.CL

版本更新 · v2arXiv:2510.18131

BlueCodeAgent: A Blue Teaming Agent Powered by Automated Red Teaming for CodeGen AI

Chengquan Guo, Yuzhou Nie, Chulin Xie, Zinan Lin, Wenbo Guo, Bo Li

原文摘要

Existing research on CodeGen AI security mainly focuses on red teaming, which aims to uncover vulnerabilities and risks in AI-generated code. However, progress on the blue teaming side remains limited, as effective defenses require a deep security analysis of given tasks and edge cases. To fill in this gap, we propose BlueCodeAgent, an end-to-end blue teaming agent powered by automated red teaming. Our red teaming component generates diverse risky instances, providing effective edge cases and guidance for the subsequent blue teaming process. Our blue teaming agent then conducts multi-level defense, leveraging these red teaming examples to detect previously seen and unseen risk scenarios through constitution summarization and dynamic code analysis. Our evaluation across four representative code-related tasks (bias instruction detection, malicious instruction detection, vulnerable code detection, and prompt injection detection) shows that BlueCodeAgent achieves significant gains over diverse baselines. In particular, for vulnerability detection tasks, BlueCodeAgent integrates dynamic analysis to effectively reduce false positives, a challenging problem as base models tend to be over-conservative. Overall, with GPT-4o as the base model, BlueCodeAgent achieves an average F1 score improvement of 14.7% across four tasks compared to directly prompting the model, attributed to its ability to summarize actionable constitutions and perform dynamic analysis. Our code and data are available at https://github.com/1mocat/BlueCodeAgent.

cs.SE

版本更新 · v3arXiv:2404.07661

Robust performance metrics for imbalanced classification problems

Hajo Holzmann, Bernhard Klar

原文摘要

We show that established performance metrics in binary classification, such as Matthews' correlation coefficient (MCC), Cohen's $κ$, the F-score or the Jaccard similarity coefficient are not robust to class imbalance in the sense that if the proportion of the minority class tends to $0$, the true positive rate (TPR) of the Bayes classifier under these metrics {becomes very small or even tends to $0$}. Thus, in imbalanced classification problems, these metrics favour classifiers which ignore the minority class. To alleviate this issue we introduce robustified modifications of the MCC, of Cohen's $κ$ and of the F-score with an additional tuning parameter which allows to adapt the amount of robustness against class imbalance. As theoretical guarantee we show that the Bayes-optimal classifier for these robustified performance metrics, when expressed in terms of the density ratio $f_1/f_0$ of the class-conditional densities $f_i$, has a threshold parameter which is upper-bounded in terms of the tuning parameters. Therefore, even in strongly imbalanced settings, the TPR associated to this classifier will be bounded away from $0${, provided that $f_1/f_0$ exceeds this bound with positive probability under the positive class}. We numerically illustrate the behaviour of the various performance metrics and the effect of the tuning parameters in simulations as well as on a credit default data set. We also discuss connections to the receiver operating characteristic and precision-recall curves, which provide an alternative perspective on the proposed notion of robustness, and give recommendations on how to combine their usage with performance metrics.

stat.ML · cs.LG · stat.ME

版本更新 · v2arXiv:2605.06111

ASTOR: Multi-Task Code Reinforcement Learning via Utility-Driven Coordination

Yujia Chen, Yang Ye, Xiao Chu, Yuchi Ma, Cuiyun Gao

原文摘要

Reinforcement learning (RL) with verifiable rewards has proven effective at post-training LLMs for coding, yet deploying separate task-specific specialists incurs costs that scale with the number of tasks, motivating a unified multi-task RL (MTRL) approach. However, existing MTRL methods treat all coding tasks uniformly, relying on fixed data curricula under a shared optimization strategy, ultimately limiting the effectiveness of multi-task training. To address these limitations, we propose ASTOR, a multi-tASk code reinforcement learning framework via uTility-driven coORdination. Centered on task utility, a signal capturing each task learning potential and cross-task synergy, ASTOR comprises two coupled modules: 1) Hierarchical Utility-Routed Data Scheduling module hierarchically allocates training budget and prioritizes informative prompts, steering training toward the most valuable data and 2) Adaptive Utility-Calibrated Policy Optimization module dynamically scales per-task KL regularization, matching update constraints to each tasks current training state. Experiments on two widely-used LLMs across four representative coding tasks demonstrate that ASTOR consistently improves a single model across all tasks, outperforming the best task-specific specialist by 9.0%-9.5% and surpassing the strongest MTRL baseline by 7.5%-12.8%.

cs.SE · cs.AI

版本更新 · v2arXiv:2609.27611

A generalizable structural brain MRI foundation model via dual-priority federated pretraining

Zhen Yu, Yang Liu, Jianfeng Feng, Xiahai Zhuang, Qingchao Chen

原文摘要

Foundation models hold promise for generalizable analysis of structural brain magnetic resonance imaging (MRI) scans across diverse populations and imaging conditions. However, existing models typically rely on centralized pretraining using data pooled across cohorts, which is constrained by privacy and data-governance requirements. Moreover, larger cohorts can dominate optimization, underutilizing anatomical information from smaller cohorts and limiting generalization. Here we present BrainFedFM, a structural brain MRI foundation model federatively pretrained on 164,707 three-dimensional scans drawn from diverse real-world data distributions and organized across 42 federated sites. BrainFedFM uses dual-priority federated pretraining, in which spatial-priority masking emphasizes informative anatomical regions during local training, while site-priority aggregation adaptively weights contributions during global aggregation. Across 20 downstream datasets spanning 17 classification, regression and segmentation tasks, BrainFedFM achieved the state-of-the-art performance across seven foundation models, including four centralized models, while showing consistent advantages in classification and regression tasks and strong robustness under underrepresented populations and challenging imaging conditions. These findings demonstrate the generalizability of BrainFedFM and highlight federated pretraining as a practical strategy for developing neuroimaging foundation models from distributed data without pooling raw images.

cs.CV

版本更新 · v3arXiv:2510.02609

RedCodeAgent: Automatic Red-teaming Agent against Diverse Code Agents

Chengquan Guo, Chulin Xie, Yu Yang, Zhaorun Chen, Zinan Lin, Xander Davies, Yarin Gal, Dawn Song 等 9 位作者

原文摘要

Code agents have gained widespread adoption due to their strong code generation capabilities and integration with code interpreters, enabling dynamic execution, debugging, and interactive programming capabilities. While these advancements have streamlined complex workflows, they have also introduced critical safety and security risks. Current static safety benchmarks and red-teaming tools are inadequate for identifying emerging real-world risky scenarios, as they fail to cover certain boundary conditions, such as the combined effects of different jailbreak tools. In this work, we propose RedCodeAgent, the first automated red-teaming agent designed to systematically uncover vulnerabilities in diverse code agents. With an adaptive memory module, RedCodeAgent can leverage existing jailbreak knowledge, dynamically select the most effective red-teaming tools and tool combinations in a tailored toolbox for a given input query, thus identifying vulnerabilities that might otherwise be overlooked. For reliable evaluation, we develop simulated sandbox environments to additionally evaluate the execution results of code agents, mitigating potential biases of LLM-based judges that only rely on static code. Through extensive evaluations across multiple state-of-the-art code agents, diverse risky scenarios, and various programming languages, RedCodeAgent consistently outperforms existing red-teaming methods, achieving higher attack success rates and lower rejection rates with high efficiency. We further validate RedCodeAgent on real-world code assistants, e.g., Cursor and Codeium, exposing previously unidentified security risks. By automating and optimizing red-teaming processes, RedCodeAgent enables scalable, adaptive, and effective safety assessments of code agents. Our code and data are available at https://github.com/1mocat/RedCodeAgent.

cs.SE

版本更新 · v4arXiv:2605.16679

CHI-Bench: Can AI Agents Automate End-to-End, Long-Horizon, Policy-Rich Healthcare Workflows?

Haolin Chen, Deon Metelski, Leon Qi, Tao Xia, Joonyul Lee, Steve Brown, Kevin Riley, Frank Wang 等 33 位作者

原文摘要

End-to-end automation of realistic healthcare operations stresses three capabilities underrepresented in current benchmarks: policy density, decisions must be grounded in a large library of medical, insurance, and operational rules; Multi-role composition: a single task requires the agent to play multiple roles with handoffs; and multilateral interaction: intermediate workflow steps are multi-turn dialogs, such as peer-to-peer review and patient outreach. We introduce $χ$-Bench, a benchmark of long-horizon healthcare workflows across three domains: provider prior authorization, payer utilization management, and care management. Each task hands the agent a clinical case in a high-fidelity simulator of 20 healthcare apps exposed via 87 MCP tools, which it must drive to a terminal status through tool calls and writing the role's artifacts, guided by a 1,290+ document managed-care operations handbook skill. Across 30 agent harness/models configurations, the best agent resolves only 28.0% of tasks, no agent clears 20% on strict pass^3, and executing all tasks in a single session slumps the performance to 3.8%. These results raise the hypothesis that similar gaps are likely to surface in other policy-dense, role-composed, irreversible enterprise domains.

cs.CL · cs.AI

版本更新 · v2arXiv:2607.28070

CCFormer: Efficient Cross-Field Interaction and Hierarchical Sequence Compression for Industrial Recommendation at Tencent

Yunlong Wang, Huizhe Zhang, Haonan Hu, Yudong Li, Bing Wen, Jianchao Tu, Chengxiang Zhuo, Zang Li

原文摘要

Industrial candidate-ranking systems must combine long user behavior histories with heterogeneous user and item features under strict computational budgets. We propose CCFormer, a structured interaction architecture that separates cross-field retrieval from intra-history modeling. Feature-field-separated cross-attention allows user and target queries to read an evolving history hierarchy, while local subspace token mixing contextualizes history tokens independently of candidate targets. Hierarchical sequence compression reduces the number of history tokens and provides multi-scale historical context for subsequent interactions. Experiments on two public benchmarks show higher mean AUC than the evaluated baselines, while experiments on a large-scale industrial dataset show a favorable accuracy-compute trade-off and higher training throughput than HSTU. Online A/B tests across four recommendation and advertising scenarios report system-level improvements of up to 3.57% in click-through rate, 3.86% in page views, and 1.71% in advertising revenue relative to the corresponding production baselines. CCFormer has been fully deployed in all four scenarios, demonstrating its practical scalability and effectiveness in large-scale recommendation systems.

cs.IR