大模型对齐与安全 - arXivDaily 专题

2509.13731 2025-09-18 cs.RO 50%

Reinforcement Learning for Robotic Insertion of Flexible Cables in Industrial Settings

Jeongwoo Park, Seabin Lee, Changmin Park, Wonjong Lee, Changjoo Nam

机构 * Dept. of Electronic Engineering, Sogang University（电子工程系，成均馆大学）； Dept. of Artificial Intelligence, Sogang University（人工智能系，成均馆大学）

专题命中安全评测：safety(abstract)

2509.13629 2025-09-18 cs.CV 50%

SAMIR, an efficient registration framework via robust feature learning from SAM

Yue He, Min Liu, Qinghao Liu, Jiazheng Wang, Yaonan Wang, Hang Zhang, Xiang Chen

专题命中安全评测：alignment(abstract)

2509.10426 2025-09-18 cs.RO cs.MA 50%

DECAMP: Towards Scene-Consistent Multi-Agent Motion Prediction with Disentangled Context-Aware Pre-Training

Jianxin Shi, Zengqi Peng, Xiaolong Chen, Tianyu Wo, Jun Ma

机构 * School of Computer Science and Engineering, Beihang University（北京航空航天大学计算机科学与工程学院）； Robotics and Autonomous Systems Thrust, The Hong Kong University of Science and Technology (GZ)（香港科技大学（广州）机器人与自主系统方向）； Division of Emerging Interdisciplinary Areas, The Hong Kong University of Science and Technology（香港科技大学新兴交叉领域研究所）

专题命中安全评测：safety(abstract)

2509.12912 2025-09-17 cs.RO 50%

Spotting the Unfriendly Robot -- Towards better Metrics for Interactions

Raphael Wenzel, Malte Probst

机构 * Honda Research Institute Europe GmbH（本田欧洲研究院）

专题命中安全评测：safety(abstract)

Comments Presented at 2025 IEEE Conference on Robotics and Automation (ICRA) Workshop: Advances in Social Navigation: Planning, HRI and Beyond

2509.12492 2025-09-17 cs.CV 50%

Evaluating Robustness of Vision-Language Models Under Noisy Conditions

Purushoth, Alireza

机构 * University of Nevada Reno（内华达大学拉斯维加斯分校）

专题命中安全评测：alignment(abstract)

2509.11292 2025-09-17 cs.CV 50%

Leveraging Geometric Priors for Unaligned Scene Change Detection

Ziling Liu, Ziwei Chen, Mingqi Gao, Jinyu Yang, Feng Zheng

机构 * Southern University of Science and Technology（南方科技大学）； University of Sheffield（谢菲尔德大学）； Spatialtemporal AI（时空AI）

专题命中安全评测：alignment(abstract)

2509.12076 2025-09-16 cs.IR 50%

AEFS: Adaptive Early Feature Selection for Deep Recommender Systems

Fan Hu, Gaofeng Lu, Jun Chen, Chaonan Guo, Yuekui Yang, Xirong Li

专题命中安全评测：alignment(abstract)

Comments Accepted by TKDE

2509.11885 2025-09-16 cs.CV 50%

BREA-Depth: Bronchoscopy Realistic Airway-geometric Depth Estimation

Francis Xiatian Zhang, Emile Mackute, Mohammadreza Kasaei, Kevin Dhaliwal, Robert Thomson, Mohsen Khadem

机构 * Baillie Gifford Pandemic Science Hub（巴利尔·吉福德疫情科学中心）； Institute of Regeneration and Repair（再生与修复研究所）； Heriot-Watt University（赫罗特-瓦特大学）； Institute of Photonics and Quantum Science（光子与量子科学研究所）

专题命中安全评测：safety(abstract)

Comments The paper has been accepted to MICCAI 2025

2505.19260 2025-09-16 cs.CR 50%

ALRPHFS: Adversarially Learned Risk Patterns with Hierarchical Fast \& Slow Reasoning for Robust Agent Defense

Shiyu Xiang, Tong Zhang, Ronghao Chen

专题命中安全评测：safety(abstract)

Comments EMNLP 2025 findings, 20 pages, 2 figures

2503.20065 2025-09-16 physics.app-ph physics.optics 50%

Fast approximate solvers for metamaterials design in electromagnetism

Raphael Pestourie

专题命中安全评测：trustworthy(abstract)

2509.10284 2025-09-15 cs.MA cs.RO 50%

A Holistic Architecture for Monitoring and Optimization of Robust Multi-Agent Path Finding Plan Execution

David Zahrádka, Denisa Mužíková, David Woller, Miroslav Kulich, Jiří Švancara, Roman Barták

机构 * Faculty of Electrical Engineering, Czech Technical University in Prague, Prague, Czech Republic（布拉格捷克技术大学电气工程学院）； Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University in Prague, Prague, Czech Republic（捷克信息学、机器人学与自动化研究所）； Faculty of Mathematics and Physics, Charles University, Prague, Czech Republic（布拉格查理大学数学与物理学院）

专题命中安全评测：safety(abstract)

Comments 23 pages, 10 figures

2509.09922 2025-09-15 econ.GN q-fin.EC 50%

Robo-Advisors Beyond Automation: Principles and Roadmap for AI-Driven Financial Planning

Runhuan Feng, Hong Li, Ming Liu

专题命中安全评测：trustworthy(abstract)

Comments 37 pages, 2 figures

2411.02992 2025-09-15 cs.IR cs.CV 50%

Efficient and Effective Adaptation of Multimodal Foundation Models in Sequential Recommendation

Junchen Fu, Xuri Ge, Xin Xin, Alexandros Karatzoglou, Ioannis Arapakis, Kaiwen Zheng, Yongxin Ni, Joemon M. Jose

机构 * School of Computing Science, University of Glasgow（格拉斯哥大学计算机科学学院）； Amazon（亚马逊）； Telefonica Scientific Research（Telefonica科学研究院）； University of Science and Technology of China（中国科学技术大学）

专题命中安全评测：alignment(abstract)

Comments Accepted by IEEE Transactions on Knowledge and Data Engineering (TKDE)

2509.09311 2025-09-12 cs.CV 50%

Image Recognition with Vision and Language Embeddings of VLMs

Illia Volkov, Nikita Kisel, Klara Janouskova, Jiri Matas

机构 * Visual Recognition Group, Faculty of Electrical Engineering, Czech Technical University in Prague（视觉识别组，电气工程学院，布拉格捷克技术大学）

专题命中安全评测：alignment(abstract)

2509.08274 2025-09-11 cs.NI 50%

Enhancing 6G Network Security and Incident Response through Integrated VNF and SDN Technologies

Abdul Razaque, Abitkhanova Zhadyra Abitkhanovna

专题命中安全评测：safety(abstract)

Comments 14 page, 10 Figures

2509.08221 2025-09-11 cs.RO 50%

A Comprehensive Review of Reinforcement Learning for Autonomous Driving in the CARLA Simulator

Elahe Delavari, Feeza Khan Khanzada, Jaerock Kwon

专题命中安全评测：safety(abstract)

2509.07323 2025-09-10 cs.SD cs.CR 50%

When Fine-Tuning is Not Enough: Lessons from HSAD on Hybrid and Adversarial Audio Spoof Detection

Bin Hu, Kunyang Huang, Daehan Kwak, Meng Xu, Kuan Huang

机构 * Department of Computer Science and Technology, Kean University, USA（计算机科学与技术系，凯恩大学，美国）； Department of Computer Science and Technology, Wenzhou-Kean University, China（计算机科学与技术系，温州-凯恩大学，中国）

专题命中安全评测：trustworthy(abstract)

Comments 13 pages, 11 figures.This work has been submitted to the IEEE for possible publication

2509.05946 2025-09-09 cs.NI 50%

Large Language Models for Next-Generation Wireless Network Management: A Survey and Tutorial

Bisheng Wei, Ruihong Jiang, Ruichen Zhang, Yinqiu Liu, Dusit Niyato, Yaohua Sun, Yang Lu, Yonghui Li, Shiwen Mao, Chau Yuen, Marco Di Renzo, Mugen Peng

专题命中安全评测：trustworthy(abstract)

2508.12543 2025-09-09 cs.CV 50%

REVEAL -- Reasoning and Evaluation of Visual Evidence through Aligned Language

Ipsita Praharaj, Yukta Butala, Badrikanath Praharaj, Yash Butala

机构 * Carnegie Mellon University（卡内基梅隆大学）； VIT Bhopal（维捷商学院）

专题命中安全评测：alignment(abstract)

Comments 4 pages, 6 figures, International Conference on Computer Vision, ICCV 2025

2509.04619 2025-09-08 eess.SY cs.SY math.DS 50%

$\mathcal{L}_1$-DRAC: Distributionally Robust Adaptive Control

Aditya Gahlawat, Sambhu H. Karumanchi, Naira Hovakimyan

专题命中安全评测：safety(abstract)

2509.02952 2025-09-04 cs.CV 50%

STAR: A Fast and Robust Rigid Registration Framework for Serial Histopathological Images

Zeyu Liu, Shengwei Ding

机构 * School of Biological Science and Medical Engineering, Beihang University, Beijing, China（生物科学与医学工程学院，北航，北京，中国）； School of Computer Science and Engineering, Beihang University, Beijing, China（计算机科学与工程学院，北航，北京，中国）

专题命中安全评测：alignment(abstract)

Comments The code is available at https://github.com/Rowerliu/STAR

2509.01275 2025-09-04 cs.CV 50%

Novel Category Discovery with X-Agent Attention for Open-Vocabulary Semantic Segmentation

Jiahao Li, Yang Lu, Yachao Zhang, Fangyong Wang, Yuan Xie, Yanyun Qu

专题命中安全评测：alignment(abstract)

Comments Accepted by ACMMM2025

2509.02540 2025-09-03 eess.SP 50%

LLM-Enhanced Space-Air-Ground-Sea Integrated Networks

Halvin Yang, Sangarapillai Lambotharan, Mahsa Derakhshani, Lajos Hanzo

专题命中安全评测：trustworthy(abstract)

Comments 6 figures, 7 pages, magazine

2509.02150 2025-09-03 cs.SE 50%

Txt2Sce: Scenario Generation for Autonomous Driving System Testing Based on Textual Reports

Pin Ji, Yang Feng, Zongtai Li, Xiangchi Zhou, Jia Liu, Jun Sun, Zhihong Zhao

专题命中安全评测：safety(abstract)

2509.01460 2025-09-03 cs.HC 50%

Dissecting Atomic Facts: Visual Analytics for Improving Fact Annotations in Language Model Evaluation

Manuel Schmidt, Daniel A. Keim, Frederik L. Dennig

专题命中安全评测：alignment(abstract)

Comments 2 pages text plus poster, 2 figures, LaTeX

2509.00751 2025-09-03 cs.CV 50%

EVENT-Retriever: Event-Aware Multimodal Image Retrieval for Realistic Captions

Dinh-Khoi Vo, Van-Loc Nguyen, Minh-Triet Tran, Trung-Nghia Le

机构 * University of Science, VNU-HCM（越南国家大学科学学院）

专题命中安全评测：alignment(abstract)

Comments ACM Multimedia 2025

2508.20851 2025-08-29 cs.CV 50%

PathMR: Multimodal Visual Reasoning for Interpretable Pathology Diagnosis

Ye Zhang, Yu Zhou, Jingwen Qi, Yongbing Zhang, Simon Puettmann, Finn Wichmann, Larissa Pereira Ferreira, Lara Sichward, Julius Keyl, Sylvia Hartmann, Shuo Zhao, Hongxiao Wang, Xiaowei Xu, Jianxu Chen

机构 * School of Computer Science and Technology, Harbin Institute of Technology（哈尔滨工业大学计算机科学与技术学院）； Leibniz-Institut für Analytische Wissenschaften – ISAS – e.V.（莱比锡分析科学研究所（ISAS））； Department of Pathology, The Sixth Affiliated Hospital, Sun Yat-sen University（中山大学第六附属医院病理科部）； Institute of Pathology, University Hospital Essen（埃森大学医院病理科研究所）； Academy for Multidisciplinary Studies, Capital Normal University（首都师范大学多学科研究学院）

专题命中安全评测：alignment(abstract)

2508.19773 2025-08-28 cs.CV 50%

The Return of Structural Handwritten Mathematical Expression Recognition

Jakob Seitz, Tobias Lengfeld, Radu Timofte

机构 * Computer Vision Lab, CAIDAS \& IFI, University of W\"urzburg, W\"urzburg, Germany

专题命中安全评测：alignment(abstract)

2508.19639 2025-08-28 cs.MM 50%

FakeSV-VLM: Taming VLM for Detecting Fake Short-Video News via Progressive Mixture-Of-Experts Adapter

Junxi Wang, Yaxiong Wang, Lechao Cheng, Zhun Zhong

专题命中安全评测：alignment(abstract)

Comments EMNLP2025 Findings

2507.21696 2025-08-28 eess.SP 50%

Edge Agentic AI Framework for Autonomous Network Optimisation in O-RAN

Abdelaziz Salama, Zeinab Nezami, Mohammed M. H. Qazzaz, Maryam Hafeez, Syed Ali Raza Zaidi

专题命中安全评测：safety(abstract)

Journal ref IEEE International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC), 2025

1. 安全评测 9451 篇

Reinforcement Learning for Robotic Insertion of Flexible Cables in Industrial Settings

SAMIR, an efficient registration framework via robust feature learning from SAM

DECAMP: Towards Scene-Consistent Multi-Agent Motion Prediction with Disentangled Context-Aware Pre-Training

Spotting the Unfriendly Robot -- Towards better Metrics for Interactions

Evaluating Robustness of Vision-Language Models Under Noisy Conditions

Leveraging Geometric Priors for Unaligned Scene Change Detection

AEFS: Adaptive Early Feature Selection for Deep Recommender Systems

BREA-Depth: Bronchoscopy Realistic Airway-geometric Depth Estimation

ALRPHFS: Adversarially Learned Risk Patterns with Hierarchical Fast \& Slow Reasoning for Robust Agent Defense

Fast approximate solvers for metamaterials design in electromagnetism

A Holistic Architecture for Monitoring and Optimization of Robust Multi-Agent Path Finding Plan Execution

Robo-Advisors Beyond Automation: Principles and Roadmap for AI-Driven Financial Planning

Efficient and Effective Adaptation of Multimodal Foundation Models in Sequential Recommendation

Image Recognition with Vision and Language Embeddings of VLMs

Enhancing 6G Network Security and Incident Response through Integrated VNF and SDN Technologies

A Comprehensive Review of Reinforcement Learning for Autonomous Driving in the CARLA Simulator

When Fine-Tuning is Not Enough: Lessons from HSAD on Hybrid and Adversarial Audio Spoof Detection

Large Language Models for Next-Generation Wireless Network Management: A Survey and Tutorial

REVEAL -- Reasoning and Evaluation of Visual Evidence through Aligned Language

$\mathcal{L}_1$-DRAC: Distributionally Robust Adaptive Control

STAR: A Fast and Robust Rigid Registration Framework for Serial Histopathological Images

Novel Category Discovery with X-Agent Attention for Open-Vocabulary Semantic Segmentation

LLM-Enhanced Space-Air-Ground-Sea Integrated Networks

Txt2Sce: Scenario Generation for Autonomous Driving System Testing Based on Textual Reports

Dissecting Atomic Facts: Visual Analytics for Improving Fact Annotations in Language Model Evaluation

EVENT-Retriever: Event-Aware Multimodal Image Retrieval for Realistic Captions

PathMR: Multimodal Visual Reasoning for Interpretable Pathology Diagnosis

The Return of Structural Handwritten Mathematical Expression Recognition

FakeSV-VLM: Taming VLM for Detecting Fake Short-Video News via Progressive Mixture-Of-Experts Adapter

Edge Agentic AI Framework for Autonomous Network Optimisation in O-RAN