大模型对齐与安全 - arXivDaily 专题

2512.05686 2025-12-08 eess.SY cs.SY 78%

LA-RL: Language Action-guided Reinforcement Learning with Safety Guarantees for Autonomous Highway Driving

LA-RL: 基于语言动作引导的安全强化学习用于自动驾驶高速公路驾驶

Yiming Shu, Jiahui Xu, Jiwei Tang, Ruiyang Gao, Chen Sun

专题命中安全训练：safety(title,abstract)

AI总结 LA-RL通过整合大语言模型的语义推理和改进的安全层，提升自动驾驶高速公路驾驶的效率与安全性。

2303.12610 2025-11-25 eess.SY cs.SY math.OC 78%

Distributed Safe Control Design and Probabilistic Safety Verification for Multi-Agent Systems

分布式安全控制设计与多智能体系统的概率安全验证

Han Wang, Antonis Papachristodoulou, Kostas Margellos

专题命中安全训练：safety(title,abstract)

AI总结本文提出了一种分布式算法，用于多智能体系统的安全控制设计和概率安全验证，通过合作机制解决不可行性问题，并通过场景方法量化安全性。

Comments manuscript accepted by Automatica

Journal ref Automatica, Vol. 179, 2025

2511.14433 2025-11-19 cs.LO cs.RO cs.SE 78%

Safe-ROS: An Architecture for Autonomous Robots in Safety-Critical Domains

Diana C. Benjumea, Marie Farrell, Louise A. Dennis

机构 * Department of Computer Science The University of Manchester Manchester, UK（计算机科学系曼彻斯特大学曼彻斯特英国）； University of Manchester Manchester, UK（曼彻斯特大学曼彻斯特英国）

专题命中安全训练：safety(title,abstract)

Comments In Proceedings FMAS 2025, arXiv:2511.13245

Journal ref EPTCS 436, 2025, pp. 48-68

2502.12520 2025-10-28 cs.CV 78%

SafeEraser: Enhancing Safety in Multimodal Large Language Models through Multimodal Machine Unlearning

Junkai Chen, Zhijie Deng, Kening Zheng, Yibo Yan, Shuliang Liu, PeiJun Wu, Peijie Jiang, Jia Liu, Xuming Hu

机构 * The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））； The Hong Kong University of Science and Technology（香港科技大学）； Southeast University（东南大学）； Ant Group, Alibaba（蚂蚁集团）

专题命中安全训练：safety(title,abstract)

2505.02293 2025-10-09 cs.RO cs.MA cs.SY eess.SY 78%

Resolving Conflicting Constraints in Multi-Agent Reinforcement Learning with Layered Safety

Jason J. Choi, Jasmine Jerry Aloor, Jingqi Li, Maria G. Mendoza, Hamsa Balakrishnan, Claire J. Tomlin

机构 * University of California, Berkeley（加州大学伯克利分校）； Massachusetts Institute of Technology（麻省理工学院）

专题命中安全训练：safety(title,abstract)

Comments Accepted for publication at the 2025 Robotics: Science and Systems Conference. 18 pages, 8 figures

2510.02363 2025-10-06 eess.SY cs.SY 78%

Precise HDV Positioning through Safety-Aware Integrated Sensing and Communication in a Value-of-Information-Driven 6G V2X System

Mohammad Reza Abedi, Zahra Rashidi, Nader Mokari, Hamid Saeedi, Nizar Zorba

专题命中安全训练：safety(title,abstract)

2509.24418 2025-09-30 cs.CR 78%

GSPR: Aligning LLM Safeguards as Generalizable Safety Policy Reasoners

Haoran Li, Yulin Chen, Jingru Zeng, Hao Peng, Huihao Jing, Wenbin Hu, Xi Yang, Ziqian Zeng, Sirui Han, Yangqiu Song

专题命中安全训练：safety(title,abstract)

2509.13164 2025-09-18 cs.RO cs.SY eess.SY 78%

TeraSim-World: Worldwide Safety-Critical Data Synthesis for End-to-End Autonomous Driving

Jiawei Wang, Haowei Sun, Xintao Yan, Shuo Feng, Jun Gao, Henry X. Liu

机构 * University of Michigan（密歇根大学）； SaferDrive AI ； The University of Hong Kong（香港大学）； Tsinghua University（清华大学）； NVIDIA（英伟达）

专题命中安全训练：safety(title,abstract)

Comments 8 pages, 6 figures

2405.03486 2025-09-12 cs.CR cs.CV cs.SI 78%

UnsafeBench: Benchmarking Image Safety Classifiers on Real-World and AI-Generated Images

Yiting Qu, Xinyue Shen, Yixin Wu, Michael Backes, Savvas Zannettou, Yang Zhang

机构 * CISPA Helmholtz Center for Information Security（CISPA赫尔姆霍茨信息安全中心）； TU Delft（代尔夫特理工大学）

专题命中安全训练：safety(title,abstract)

Comments To Appear in the ACM Conference on Computer and Communications Security (CCS), October 13, 2025

2503.09423 2025-09-09 cs.RO cs.CV 78%

Efficient Alignment of Unconditioned Action Prior for Language-conditioned Pick and Place in Clutter

Kechun Xu, Xunlong Xia, Kaixuan Wang, Yifei Yang, Yunxuan Mao, Bing Deng, Jieping Ye, Rong Xiong, Yue Wang

机构 * Zhejiang University and Alibaba Cloud（浙江大学和阿里云）； Alibaba Cloud（阿里云）； Zhejiang University（浙江大学）

专题命中安全训练：alignment(title,abstract)

Comments Accepted by T-ASE and CoRL25 GenPriors Workshop

2508.05527 2025-08-08 cs.CV 78%

AI vs. Human Moderators: A Comparative Evaluation of Multimodal LLMs in Content Moderation for Brand Safety

Adi Levi, Or Levi, Sardhendu Mishra, Jonathan Morra

机构 * Zefr Inc（Zefr公司）

专题命中安全训练：safety(title,abstract)

Comments Accepted to the Computer Vision in Advertising and Marketing (CVAM) workshop at ICCV 2025

2409.09845 2025-08-05 cs.RO 78%

Friction-Aware Safety Locomotion for Wheeled-legged Robots using Vision Language Models and Reinforcement Learning

Bo Peng, Donghoon Baek, Qijie Wang, Joao Ramos

机构 * University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）； Department of Electrical and Computer Engineering（电气与计算机工程系）； Department of Mechanical Science Engineering（机械科学与工程系）； School of Software（软件学院）

专题命中安全训练：safety(title,abstract)

Comments Accepted to Humanoids 2025

2507.23226 2025-08-01 cs.CV 78%

Toward Safe, Trustworthy and Realistic Augmented Reality User Experience

Yanming Xiu

机构 * Department of Electrical and Computer Engineering, Duke University（电子工程系，杜克大学）

专题命中安全训练：trustworthy(title)；safety(abstract)

Comments 2 pages, 4 figures

2507.20685 2025-07-29 eess.SY cs.SY 78%

What's Really Different with AI? -- A Behavior-based Perspective on System Safety for Automated Driving Systems

Marcus Nolte, Nayel Fabian Salem, Olaf Franke, Jan Heckmann, Christoph Höhmann, Georg Stettinger, Markus Maurer

专题命中安全训练：safety(title,abstract)

Comments 8 pages, 1 figure, 1 table, to be published in 2025 IEEE International Automated Vehicle Validation Conference (IAVVC)

2505.04980 2025-07-16 cs.RO cs.SY eess.SY 78%

LVLM-MPC Collaboration for Autonomous Driving: A Safety-Aware and Task-Scalable Control Architecture

Kazuki Atsuta, Kohei Honda, Hiroyuki Okuda, Tatsuya Suzuki

机构 * Department of Mechanical Systems Engineering（机械系统工程系）； Nagoya University（名古屋大学）

专题命中安全训练：safety(title,abstract)

Comments 8 pages, 8 figures

2506.22894 2025-07-01 cs.RO 78%

Safe Reinforcement Learning with a Predictive Safety Filter for Motion Planning and Control: A Drifting Vehicle Example

Bei Zhou, Baha Zarrouki, Mattia Piccinini, Cheng Hu, Lei Xie, Johannes Betz

机构 * State Key Laboratory of Industrial Control Technology, Zhejiang University（浙江大学工业控制技术国家重点实验室）； Professorship of Autonomous Vehicle Systems, Technical University of Munich（慕尼黑工业大学自主车辆系统教授职位）

专题命中安全训练：safety(title,abstract)

2501.02620 2025-06-04 eess.SY cs.RO cs.SY 78%

Back to Base: Towards Hands-Off Learning via Safe Resets with Reach-Avoid Safety Filters

Azra Begzadić, Nikhil Uday Shinde, Sander Tonkens, Dylan Hirsch, Kaleb Ugalde, Michael C. Yip, Jorge Cortés, Sylvia Herbert

专题命中安全训练：safety(title,abstract)

Comments The first three authors contributed equally to the work

2505.19860 2025-05-27 cs.RO 78%

Causal Bayesian Networks for Data-driven Safety Analysis of Complex Systems

Roman Gansch, Lina Putze, Tjark Koopmann, Jan Reich, Christian Neurohr

机构 * Robert Bosch GmbH, Corporate Research（罗伯特·博世有限公司，企业研究）； German Aerospace Center (DLR) e.V., Institute of Systems Engineering for Future Mobility（德国航空航天中心（DLR）协会，未来交通系统工程研究所）； Fraunhofer Institute for Experimental Software Engineering (IESE)（弗劳恩霍夫实验软件工程研究所）

专题命中安全训练：safety(title,abstract)

2501.00973 2025-05-06 eess.SY cs.SY 78%

Defense Strategies for Autonomous Multi-agent Systems: Ensuring Safety and Resilience Under Exponentially Unbounded FDI Attacks

Yichao Wang, Mohamadamin Rajabinezhad, Dimitra Panagou, Shan Zuo

专题命中安全训练：safety(title,abstract)

2412.04153 2025-04-21 cs.RO math.OC 78%

A Dynamic Safety Shield for Safe and Efficient Reinforcement Learning of Navigation Tasks

Murad Dawood, Ahmed Shokry, Maren Bennewitz

专题命中安全训练：safety(title,abstract)

Comments Accepted in L4DC2025

2504.06670 2025-04-10 cs.RO 78%

Dynamic Residual Safe Reinforcement Learning for Multi-Agent Safety-Critical Scenarios Decision-Making

Kaifeng Wang, Yinsong Chen, Qi Liu, Xueyuan Li, Xin Gao

专题命中安全训练：safety(title,abstract)

2503.14656 2025-03-20 cs.RO math.OC 78%

Safety-Critical and Distributed Nonlinear Predictive Controllers for Teams of Quadrupedal Robots

Basit Muhammad Imran, Jeeseop Kim, Taizoon Chunawala, Alexander Leonessa, Kaveh Akbari Hamed

专题命中安全训练：safety(title,abstract)

2503.06892 2025-03-11 cs.RO 78%

SafePlan: Leveraging Formal Logic and Chain-of-Thought Reasoning for Enhanced Safety in LLM-based Robotic Task Planning

Ike Obi, Vishnunandan L. N. Venkatesh, Weizheng Wang, Ruiqi Wang, Dayoon Suh, Temitope I. Amosa, Wonse Jo, Byung-Cheol Min

专题命中安全训练：safety(title,abstract)

2501.13697 2025-01-24 eess.SY cs.SY stat.ML 78%

Safety in safe Bayesian optimization and its ramifications for control

Christian Fiedler, Johanna Menn, Sebastian Trimpe

专题命中安全训练：safety(title,abstract)

2409.16809 2025-01-08 cs.CE 78%

Analytical assessment of workers' safety concerning direct and indirect ways of getting infected by dangerous pathogen

Krzysztof Domino, Arkadiusz Sochan, Jarosław Adam Miszczak

专题命中安全训练：safety(title,abstract)

Journal ref Journal of Computational Science Volume 85, February 2025, 102509

2412.15437 2024-12-23 eess.SY cs.SY 78%

Safety-Critical Control of Discontinuous Systems with Nonsmooth Safe Sets

Mohammed Alyaseen, Nikolay Atanasov, Jorge Cortes

专题命中安全训练：safety(title,abstract)

2411.10031 2024-11-18 eess.SY cs.SY 78%

Enforcing Cooperative Safety for Reinforcement Learning-based Mixed-Autonomy Platoon Control

Jingyuan Zhou, Longhao Yan, Jinhao Liang, Kaidi Yang

专题命中安全训练：safety(title,abstract)

2404.03570 2024-11-04 cs.RO 78%

Embodied AI with Two Arms: Zero-shot Learning, Safety and Modularity

Jake Varley, Sumeet Singh, Deepali Jain, Krzysztof Choromanski, Andy Zeng, Somnath Basu Roy Chowdhury, Avinava Dubey, Vikas Sindhwani

专题命中安全训练：safety(title,abstract)

2410.03885 2024-10-08 cs.RO cs.SY eess.SY math.OC 78%

Collaborative Safety-Critical Formation Control with Obstacle Avoidance

Brooks A. Butler, Chi Ho Leung, Philip E. Paré

专题命中安全训练：safety(title,abstract)

Comments This work is under review for publication in Automatica. arXiv admin note: text overlap with arXiv:2311.11156

2409.15343 2024-09-25 cs.IR 78%

Advertiser Content Understanding via LLMs for Google Ads Safety

Joseph Wallace, Tushar Dogra, Wei Qiao, Yuan Wang

专题命中安全训练：safety(title,abstract)

1. 安全训练 3302 篇

LA-RL: Language Action-guided Reinforcement Learning with Safety Guarantees for Autonomous Highway Driving

Distributed Safe Control Design and Probabilistic Safety Verification for Multi-Agent Systems

Safe-ROS: An Architecture for Autonomous Robots in Safety-Critical Domains

SafeEraser: Enhancing Safety in Multimodal Large Language Models through Multimodal Machine Unlearning

Resolving Conflicting Constraints in Multi-Agent Reinforcement Learning with Layered Safety

Precise HDV Positioning through Safety-Aware Integrated Sensing and Communication in a Value-of-Information-Driven 6G V2X System

GSPR: Aligning LLM Safeguards as Generalizable Safety Policy Reasoners

TeraSim-World: Worldwide Safety-Critical Data Synthesis for End-to-End Autonomous Driving

UnsafeBench: Benchmarking Image Safety Classifiers on Real-World and AI-Generated Images

Efficient Alignment of Unconditioned Action Prior for Language-conditioned Pick and Place in Clutter

AI vs. Human Moderators: A Comparative Evaluation of Multimodal LLMs in Content Moderation for Brand Safety

Friction-Aware Safety Locomotion for Wheeled-legged Robots using Vision Language Models and Reinforcement Learning

Toward Safe, Trustworthy and Realistic Augmented Reality User Experience

What's Really Different with AI? -- A Behavior-based Perspective on System Safety for Automated Driving Systems

LVLM-MPC Collaboration for Autonomous Driving: A Safety-Aware and Task-Scalable Control Architecture

Safe Reinforcement Learning with a Predictive Safety Filter for Motion Planning and Control: A Drifting Vehicle Example

Back to Base: Towards Hands-Off Learning via Safe Resets with Reach-Avoid Safety Filters

Causal Bayesian Networks for Data-driven Safety Analysis of Complex Systems

Defense Strategies for Autonomous Multi-agent Systems: Ensuring Safety and Resilience Under Exponentially Unbounded FDI Attacks

A Dynamic Safety Shield for Safe and Efficient Reinforcement Learning of Navigation Tasks

Dynamic Residual Safe Reinforcement Learning for Multi-Agent Safety-Critical Scenarios Decision-Making

Safety-Critical and Distributed Nonlinear Predictive Controllers for Teams of Quadrupedal Robots

SafePlan: Leveraging Formal Logic and Chain-of-Thought Reasoning for Enhanced Safety in LLM-based Robotic Task Planning

Safety in safe Bayesian optimization and its ramifications for control

Analytical assessment of workers' safety concerning direct and indirect ways of getting infected by dangerous pathogen

Safety-Critical Control of Discontinuous Systems with Nonsmooth Safe Sets

Enforcing Cooperative Safety for Reinforcement Learning-based Mixed-Autonomy Platoon Control

Embodied AI with Two Arms: Zero-shot Learning, Safety and Modularity

Collaborative Safety-Critical Formation Control with Obstacle Avoidance

Advertiser Content Understanding via LLMs for Google Ads Safety