大模型对齐与安全 - arXivDaily 专题

2501.17588 2025-04-01 nlin.CD 50%

Controlling Transient Chaos in the Lorenz System with Machine Learning

David Valle, Rubén Capeans, Alexandre Wagemakers, Miguel A. F. Sanjuán

专题命中安全训练：safety(abstract)

Comments Machine learning, Partial control, Transient chaos, Lorenz system, Transformer models. Eur. Phys. J. Spec. Top. (2025)

2503.23791 2025-04-01 cs.PL cs.SE 50%

LLMigrate: Transforming "Lazy" Large Language Models into Efficient Source Code Migrators

Yuchen Liu, Junhao Hu, Yingdi Shan, Ge Li, Yanzhen Zou, Yihong Dong, Tao Xie

专题命中安全训练：safety(abstract)

2503.21844 2025-03-31 cs.HC 50%

"Ignorance is Not Bliss": Designing Personalized Moderation to Address Ableist Hate on Social Media

Sharon Heung, Lucy Jiang, Shiri Azenkot, Aditya Vashistha

专题命中安全训练：safety(abstract)

2410.15660 2025-03-28 eess.SY cs.SY 50%

SPARC: Prediction-Based Safe Control for Coupled Controllable and Uncontrollable Agents with Conformal Predictions

Shuqi Wang, Siqi Wang, Shaoyuan Li, Xiang Yin

专题命中安全训练：safety(abstract)

2401.01128 2025-03-27 cs.CV 50%

SSP: A Simple and Safe automatic Prompt engineering method towards realistic image synthesis on LVM

Weijin Cheng, Jianzhi Liu, Jiawen Deng, Fuji Ren

机构 * University of Electronic Science and Technology of China (UESTC)（电子科技大学（UESTC））

专题命中安全训练：safety(abstract)

Comments 10 pages, 8 figures

Journal ref 2024 IEEE International Conference on Systems, Man, and Cybernetics (SMC)

2503.17615 2025-03-25 cs.RO physics.ins-det 50%

Feature Selection Based on Reinforcement Learning and Hazard State Classification for Magnetic Adhesion Wall-Climbing Robots

Zhen Ma, He Xu, Jielong Dou, Yi Qin, Xueyu Zhang

专题命中安全训练：safety(abstract)

Comments 21 pages, 11 figures, manuscript for Journal of Autonomous Robots

2503.16462 2025-03-24 cs.HC 50%

What are Social Norms for Low-speed Autonomous Vehicle Navigation in Crowded Environments? An Online Survey

Mahsa Golchoubian, Moojan Ghafurian, Nasser Lashgarian Azad, Kerstin Dautenhahn

专题命中安全训练：safety(abstract)

Journal ref HAI 2021: Proceedings of the 9th International Conference on Human-Agent Interaction

2503.10793 2025-03-17 cs.CR cs.SE 50%

HALURust: Exploiting Hallucinations of Large Language Models to Detect Vulnerabilities in Rust

Yu Luo, Han Zhou, Mengtao Zhang, Dylan De La Rosa, Hafsa Ahmed, Weifeng Xu, Dianxiang Xu

专题命中安全训练：safety(abstract)

2503.10049 2025-03-14 cs.CV 50%

Enhancing Multi-Agent Systems via Reinforcement Learning with LLM-based Planner and Graph-based Policy

Ziqi Jia, Junjie Li, Xiaoyang Qu, Jianzong Wang

机构 * Ping An Technology (Shenzhen) Co., Ltd.（平安科技（深圳）有限公司）； Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）； Huazhong University of Science and Technology（华中科技大学）

专题命中安全训练：safety(abstract)

Comments Accepted by the 2025 IEEE International Conference on Robotics & Automation (ICRA 2025)

2503.08123 2025-03-12 cs.NI 50%

LLM4MAC: An LLM-Driven Reinforcement Learning Framework for MAC Protocol Emergence

Renxuan Tan, Rongpeng Li, Zhifeng Zhao

专题命中安全训练：alignment(abstract)

Comments 5 pages, 5 figures

2503.07404 2025-03-11 cs.RO 50%

Towards Safe Robot Foundation Models

Maximilian Tölle, Theo Gruner, Daniel Palenicek, Jonas Günster, Puze Liu, Joe Watson, Davide Tateo, Jan Peters

机构 * Technical University of Darmstadt（达姆施塔特工业大学）； German Research Center for Artificial Intelligence（德国人工智能研究中心）； University of Oxford（牛津大学）； Robotics Institute Germany（德国机器人研究所）； Centre for Cognitive Science（认知科学中心）

专题命中安全训练：safety(abstract)

2409.18862 2025-03-10 eess.SY cs.MA cs.RO cs.SY 50%

Safe Decentralized Multi-Agent Control using Black-Box Predictors, Conformal Decision Policies, and Control Barrier Functions

Sacha Huriot, Hussein Sibai

机构 * Washington University in St. Louis（圣路易斯华盛顿大学）

专题命中安全训练：safety(abstract)

Comments 6 pages, 1 figure, accepted for presentation at ICRA 2025

2503.02076 2025-03-05 cs.RO cs.SY eess.SY 50%

CorrA: Leveraging Large Language Models for Dynamic Obstacle Avoidance of Autonomous Vehicles

Shanting Wang, Panagiotis Typaldos, Andreas A. Malikopoulos

机构 * Cornell University（康奈尔大学）

专题命中安全训练：safety(abstract)

2403.05748 2025-02-28 cs.RO 50%

Autonomous Guidewire Navigation for Robot-assisted Endovascular Interventions: A Knowledge-Driven Visual Guidance Approach

Wentao Liu, Weijin Xu, Xiaochuan Li, Bowen Liang, Ziyang He, Mengke Zhu, Jingzhou Song, Huihua Yang, Qingsheng Lu

机构 * Wandong Medical Technology Co., Ltd（万东医疗科技有限公司）； Beijing Police College（北京警察学院）； School of Intelligent Engineering and Automation, Beijing University of Posts and Telecommunications（北京邮电大学智能工程与自动化学院）； Department of Vascular Surgery, Shanghai Changhai Hospital, Naval Medical University（海军军医大学上海长海医院血管外科）； Beijing Institute of Satellite Information Engineering（北京卫星信息工程研究所）

专题命中安全训练：safety(abstract)

2502.15649 2025-02-24 cs.RO 50%

A Simulation Pipeline to Facilitate Real-World Robotic Reinforcement Learning Applications

Jefferson Silveira, Joshua A. Marshall, Sidney N. Givigi

机构 * Ingenuity Labs Research Institute（Ingenuity Labs 研究所）； School of Computing（计算机学院）

专题命中安全训练：safety(abstract)

Comments Paper accepted to be presented at IEEE SysCon 2025

2502.13663 2025-02-20 cs.IT eess.SP math.IT 50%

User Association and Coordinated Beamforming in Cognitive Aerial-Terrestrial Networks: A Safe Reinforcement Learning Approach

Zizhen Zhou, Jungang Ge, Ying-Chang Liang

专题命中安全训练：safety(abstract)

Comments This work has been submitted to the IEEE for possible publication

2502.05072 2025-02-10 stat.AP 50%

Joint TITE-CRM for Dual Agent Dose Finding Studies

Helen Barnett, Oliver Boix, Dimitris Kontos, Thomas Jaki

专题命中安全训练：safety(abstract)

2401.14554 2025-02-10 cs.RO math.OC 50%

GCBF+: A Neural Graph Control Barrier Function Framework for Distributed Safe Multi-Agent Control

Songyuan Zhang, Oswin So, Kunal Garg, Chuchu Fan

专题命中安全训练：safety(abstract)

Comments 20 pages, 15 figures; Accepted by IEEE Transactions on Robotics (T-RO)

2501.14232 2025-01-31 eess.SY cs.SY 50%

Learning-Augmented Online Control for Decarbonizing Water Infrastructures

Jianyi Yang, Pengfei Li, Tongxin Li, Adam Wierman, Shaolei Ren

专题命中安全训练：safety(abstract)

Comments Accepted by e-Energy 2025

2212.00398 2025-01-28 cs.RO cs.SY eess.SY 50%

Distributed Model Predictive Covariance Steering

Augustinos D. Saravanos, Isin M. Balci, Efstathios Bakolas, Evangelos A. Theodorou

机构 * Georgia Institute of Technology（佐治亚理工学院）； University of Texas at Austin（德克萨斯大学奥斯汀分校）

专题命中安全训练：safety(abstract)

Journal ref IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2024

2501.08280 2025-01-15 physics.soc-ph 50%

Using Gamified Experiments to Tame Complexity: the case of the Schelling Model of Segregation

Aleix Nicolás Olivé, Luce Prignano, Dimitri Marinelli, Emanuele Cozzo

专题命中安全训练：alignment(abstract)

Comments working paper

2501.05239 2025-01-10 cs.CR cs.CV eess.SP 50%

Is Your Autonomous Vehicle Safe? Understanding the Threat of Electromagnetic Signal Injection Attacks on Traffic Scene Perception

Wenhao Liao, Sineng Yan, Youqian Zhang, Xinwei Zhai, Yuanyuan Wang, Eugene Yujun Fu

专题命中安全训练：safety(abstract)

Comments To appear in AAAI 2025

2501.01096 2025-01-03 eess.SY cs.SY math.OC 50%

Learning-Based Stable Optimal Guidance for Spacecraft Close-Proximity Operations

Kun Wang, Roberto Armellin, Adam Evans, Harry Holt, Zheng Chen

专题命中安全训练：safety(abstract)

2406.13223 2024-12-16 cs.RO 50%

Act Better by Timing: A timing-Aware Reinforcement Learning for Autonomous Driving

Guanzhou Li, Jianping Wu, Yujing He

机构 * Tsinghua University（清华大学）； Tsinghua University Research Institute at Shenzhen（清华大学深圳研究院）； Sichuan Tianfu Yongxing Laboratory（四川天府永兴实验室）

专题命中安全训练：safety(abstract)

2412.07564 2024-12-11 cs.SE 50%

Is ChatGPT 3 safe for students?

Julia Kotovich, Manuel Oriol

专题命中安全训练：safety(abstract)

Comments 8 pages

Journal ref Frontiers in Software Engineering Education (FISEE 2023)

2411.19582 2024-12-10 eess.SY cs.SY 50%

Early Versus Late Traffic Management For Autonomous Agents

Salman Ghori, Ania Adil, Eric Feron

专题命中安全训练：safety(abstract)

2412.04659 2024-12-09 cs.RO cs.MA cs.SY eess.SY 50%

LiveNet: Robust, Minimally Invasive Multi-Robot Control for Safe and Live Navigation in Constrained Environments

Srikar Gouru, Siddharth Lakkoju, Rohan Chandra

机构 * University of Virginia（弗吉尼亚大学）

专题命中安全训练：safety(abstract)

2411.10558 2024-11-19 cs.MA cs.GT cs.NE 50%

Multi-agent Path Finding for Timed Tasks using Evolutionary Games

Sheryl Paul, Anand Balakrishnan, Xin Qin, Jyotirmoy V. Deshmukh

专题命中安全训练：safety(abstract)

2406.05309 2024-11-14 cs.RO 50%

CoBL-Diffusion: Diffusion-Based Conditional Robot Planning in Dynamic Environments Using Control Barrier and Lyapunov Functions

Kazuki Mizuta, Karen Leung

机构 * University of Washington（华盛顿大学）； NVIDIA（英伟达）

专题命中安全训练：safety(abstract)

2410.14468 2024-11-05 cs.RO 50%

Knowledge Transfer from Simple to Complex: A Safe and Efficient Reinforcement Learning Framework for Autonomous Driving Decision-Making

Rongliang Zhou, Jiakun Huang, Mingjun Li, Hepeng Li, Haotian Cao, Xiaolin Song

专题命中安全训练：safety(abstract)

1. 安全训练 3317 篇

Controlling Transient Chaos in the Lorenz System with Machine Learning

LLMigrate: Transforming "Lazy" Large Language Models into Efficient Source Code Migrators

"Ignorance is Not Bliss": Designing Personalized Moderation to Address Ableist Hate on Social Media

SPARC: Prediction-Based Safe Control for Coupled Controllable and Uncontrollable Agents with Conformal Predictions

SSP: A Simple and Safe automatic Prompt engineering method towards realistic image synthesis on LVM

Feature Selection Based on Reinforcement Learning and Hazard State Classification for Magnetic Adhesion Wall-Climbing Robots

What are Social Norms for Low-speed Autonomous Vehicle Navigation in Crowded Environments? An Online Survey

HALURust: Exploiting Hallucinations of Large Language Models to Detect Vulnerabilities in Rust

Enhancing Multi-Agent Systems via Reinforcement Learning with LLM-based Planner and Graph-based Policy

LLM4MAC: An LLM-Driven Reinforcement Learning Framework for MAC Protocol Emergence

Towards Safe Robot Foundation Models

Safe Decentralized Multi-Agent Control using Black-Box Predictors, Conformal Decision Policies, and Control Barrier Functions

CorrA: Leveraging Large Language Models for Dynamic Obstacle Avoidance of Autonomous Vehicles

Autonomous Guidewire Navigation for Robot-assisted Endovascular Interventions: A Knowledge-Driven Visual Guidance Approach

A Simulation Pipeline to Facilitate Real-World Robotic Reinforcement Learning Applications

User Association and Coordinated Beamforming in Cognitive Aerial-Terrestrial Networks: A Safe Reinforcement Learning Approach

Joint TITE-CRM for Dual Agent Dose Finding Studies

GCBF+: A Neural Graph Control Barrier Function Framework for Distributed Safe Multi-Agent Control

Learning-Augmented Online Control for Decarbonizing Water Infrastructures

Distributed Model Predictive Covariance Steering

Using Gamified Experiments to Tame Complexity: the case of the Schelling Model of Segregation

Is Your Autonomous Vehicle Safe? Understanding the Threat of Electromagnetic Signal Injection Attacks on Traffic Scene Perception

Learning-Based Stable Optimal Guidance for Spacecraft Close-Proximity Operations

Act Better by Timing: A timing-Aware Reinforcement Learning for Autonomous Driving

Is ChatGPT 3 safe for students?

Early Versus Late Traffic Management For Autonomous Agents

LiveNet: Robust, Minimally Invasive Multi-Robot Control for Safe and Live Navigation in Constrained Environments

Multi-agent Path Finding for Timed Tasks using Evolutionary Games

CoBL-Diffusion: Diffusion-Based Conditional Robot Planning in Dynamic Environments Using Control Barrier and Lyapunov Functions

Knowledge Transfer from Simple to Complex: A Safe and Efficient Reinforcement Learning Framework for Autonomous Driving Decision-Making