大模型对齐与安全 - arXivDaily 专题

2309.11057 2024-09-25 cs.RO cs.MA 78%

Safety Guaranteed Robust Multi-Agent Reinforcement Learning with Hierarchical Control for Connected and Automated Vehicles

Zhili Zhang, H M Sabbir Ahmad, Ehsan Sabouni, Yanchao Sun, Furong Huang, Wenchao Li, Fei Miao

专题命中安全训练：safety(title,abstract)

Comments 6 pages, 6 figures

2409.14580 2024-09-24 cs.RO 78%

Updating Robot Safety Representations Online from Natural Language Feedback

Leonardo Santos, Zirui Li, Lasse Peters, Somil Bansal, Andrea Bajcsy

专题命中安全训练：safety(title,abstract)

Comments Submitted to ICRA 2025

2404.11882 2024-04-19 eess.SY cs.RO cs.SY 78%

Hybrid Navigation Acceptability and Safety

Benoit Clement, Marie Dubromel, Paulo E. Santos, Karl Sammut, Michelle Oppert, Feras Dayoub

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

2211.04665 2024-04-03 cs.RO 78%

Improving safety in mixed traffic: A learning-based model predictive control for autonomous and human-driven vehicle platooning

Jie Wang, Zhihao Jiang, Yash Vardhan Pant

专题命中安全训练：safety(title,abstract)

2404.01096 2024-04-02 cs.SE cs.PL 78%

Enabling Memory Safety of C Programs using LLMs

Nausheen Mohammed, Akash Lal, Aseem Rastogi, Subhajit Roy, Rahul Sharma

专题命中安全训练：safety(title,abstract)

2403.17830 2024-03-27 cs.CV 78%

Assessment of Multimodal Large Language Models in Alignment with Human Values

Zhelun Shi, Zhipin Wang, Hongxing Fan, Zaibin Zhang, Lijun Li, Yongting Zhang, Zhenfei Yin, Lu Sheng, Yu Qiao, Jing Shao

专题命中安全训练：alignment(title,abstract)

Comments arXiv admin note: text overlap with arXiv:2311.02692

2309.17078 2024-03-27 cs.IR 78%

Unsupervised Large Language Model Alignment for Information Retrieval via Contrastive Feedback

Qian Dong, Yiding Liu, Qingyao Ai, Zhijing Wu, Haitao Li, Yiqun Liu, Shuaiqiang Wang, Dawei Yin, Shaoping Ma

专题命中安全训练：alignment(title,abstract)

Comments Accepted by SIGIR24

2312.03429 2024-03-26 cs.CR 78%

Behavioral Authentication for Security and Safety

Cheng Wang, Hao Tang, Hangyu Zhu, Junhan Zheng, Changjun Jiang

专题命中安全训练：safety(title,abstract)

2402.01576 2024-02-05 cs.RO 78%

Training Adversarial yet Safe Agent to Characterize Safety Performance of Highly Automated Vehicles

Minghao Zhu, Anmol Sidhu, Keith A. Redmill

专题命中安全训练：safety(title,abstract)

2401.06245 2024-01-15 math.OC 78%

Distributed Optimal Output Consensus Control of Heterogeneous Multi-Agent Systems with Safety Constraints

Ji Ma, Shu Liang, Yiguang Hong

专题命中安全训练：safety(title,abstract)

Comments 15 pages, 4 figures

2312.08689 2023-12-15 cs.RO 78%

Safety-Critical Coordination of Legged Robots via Layered Controllers and Forward Reachable Set based Control Barrier Functions

Jeeseop Kim, Jaemin Lee, Aaron D. Ames

专题命中安全训练：safety(title,abstract)

Comments 7 pages, 7 figures. arXiv admin note: substantial text overlap with arXiv:2303.13630

2312.04158 2023-12-08 eess.SY cs.SY 78%

Safety-Enhanced Self-Learning for Optimal Power Converter Control

Yihao Wan, Qianwen Xu, Tomislav Dragičević

专题命中安全训练：safety(title,abstract)

2310.15478 2023-12-06 math.OC cs.RO 78%

How to Train Your Neural Control Barrier Function: Learning Safety Filters for Complex Input-Constrained Systems

Oswin So, Zachary Serlin, Makai Mann, Jake Gonzales, Kwesi Rutledge, Nicholas Roy, Chuchu Fan

专题命中安全训练：safety(title,abstract)

Comments Submitted to ICRA 2024. Project page can be found at https://mit-realm.github.io/pncbf

2212.07566 2023-11-30 cs.SE 78%

Identifying and Explaining Safety-critical Scenarios for Autonomous Vehicles via Key Features

Neelofar, Aldeida Aleti

专题命中安全训练：safety(title,abstract)

Comments 28 pages, 6 figures

2210.01041 2023-10-19 cs.RO 78%

Probabilistic Safeguard for Reinforcement Learning Using Safety Index Guided Gaussian Process Models

Weiye Zhao, Tairan He, Changliu Liu

专题命中安全训练：safety(title,abstract)

Comments L4DC 2023

2303.17584 2023-10-03 eess.SY cs.SY 78%

Consensus controller with safety guarantee: an application to the kinematic bicycle model

Kaicheng Niu, Chaouki Abdallah, Mohammad Hayajneh

专题命中安全训练：safety(title,abstract)

2304.09119 2023-04-27 cs.RO 78%

Safety Guaranteed Manipulation Based on Reinforcement Learning Planner and Model Predictive Control Actor

Zhenshan Bing, Aleksandr Mavrichev, Sicong Shen, Xiangtong Yao, Kejia Chen, Kai Huang, Alois Knoll

专题命中安全训练：safety(title,abstract)

2210.03855 2023-04-04 eess.SY cs.MA cs.SY math.OC 78%

Safety Embedded Stochastic Optimal Control of Networked Multi-Agent Systems via Barrier States

Lin Song, Pan Zhao, Neng Wan, Naira Hovakimyan

专题命中安全训练：safety(title,abstract)

2302.11436 2023-02-23 econ.GN q-fin.EC 78%

Industrial Policy for Advanced AI: Compute Pricing and the Safety Tax

Mckay Jensen, Nicholas Emery-Xu, Robert Trager

专题命中安全训练：safety(title,abstract)

Comments 32 pages, 7 figures

2301.10201 2023-01-25 cs.ET 78%

Safety of self-assembled neuromorphic hardware

Can Rager, Kyle Webster

专题命中安全训练：safety(title,abstract)

Comments 7 pages, 1 figure

2112.03012 2023-01-10 cs.RO cs.SY eess.SY 78%

Bounded Distance-control for Multi-UAV Formation Safety and Preservation in Target-tracking Applications

Aditya Hegde, Jasmine Jerry Aloor, Debasish Ghose

专题命中安全训练：safety(title,abstract)

Comments Published in the Proceedings of the Institution of Mechanical Engineers, Part G: Journal of Aerospace Engineering. 2022. Paper is 11 pages, 10 figures

Journal ref Proceedings of the Institution of Mechanical Engineers, Part G: Journal of Aerospace Engineering. 2022;0(0)

2210.08137 2022-10-18 cs.RO 78%

User-specific, Adaptable Safety Controllers Facilitate User Adoption in Human-Robot Collaboration

Ahalya Prabhakar, Aude Billard

专题命中安全训练：safety(title,abstract)

Comments Presented at the AI-HRI Symposium at AAAI Fall Symposium Series (FSS) 2022 (arXiv:2209.14292)

2204.03801 2022-04-11 cs.RO cs.SY eess.SY 78%

Barrier Bayesian Linear Regression: Online Learning of Control Barrier Conditions for Safety-Critical Control of Uncertain Systems

Lukas Brunke, Siqi Zhou, Angela P. Schoellig

专题命中安全训练：safety(title,abstract)

Comments Conference on Learning for Dynamics and Control (L4DC) 2022

2204.00691 2022-04-05 cs.HC 78%

Human-AI Interaction for User Safety in Social Matching Apps: Involving Marginalized Users in Design

Douglas Zytko, Nicholas Furlo, Hanan Aljasim

专题命中安全训练：safety(title,abstract)

Comments Accepted to the "Artificially Intelligent Technology for the Margins" workshop at the 2021 ACM CHI Conference on Human Factors in Computing Systems

2111.03781 2022-03-17 cs.LO cs.FL 78%

Monotonic Safety for Scalable and Data-Efficient Probabilistic Safety Analysis

Matthew Cleaveland, Ivan Ruchkin, Oleg Sokolsky, Insup Lee

专题命中安全训练：safety(title,abstract)

Comments 12 pages, 6 figures

2112.03347 2022-02-08 eess.SY cs.SY 78%

Structured learning of safety guarantees for the control of uncertain dynamical systems

Marc-Antoine Beaudoin, Benoit Boulet

专题命中安全训练：safety(title,abstract)

2006.03196 2021-12-07 cs.HC 78%

Towards Better Driver Safety: Empowering Personal Navigation Technologies with Road Safety Awareness

Runsheng Xu, Shibo Zhang, Yue Zhao, Peixi Xiong, Allen Yilun Lin, Brent Hecht, Jiaqi Ma

专题命中安全训练：safety(title,abstract)

Comments Submitted to Autonomous Intelligent System Journal

2110.07067 2021-11-03 cs.RO cs.SY eess.SY 78%

Offline Reinforcement Learning for Autonomous Driving with Safety and Exploration Enhancement

Tianyu Shi, Dong Chen, Kaian Chen, Zhaojian Li

专题命中安全训练：safety(title,abstract)

Comments Machine Learning for Autonomous Driving Workshop on NeurIPS 2021

2110.04633 2021-10-12 cs.RO 78%

Credit Assignment Safety Learning from Human Demonstrations

Ahalya Prabhakar, Aude Billard

专题命中安全训练：safety(title,abstract)

Comments Presented at AI-HRI symposium as part of AAAI-FSS 2021 (arXiv:2109.10836)

2107.00913 2021-07-05 cs.MA 78%

Reinforcement Learning Provides a Flexible Approach for Realistic Supply Chain Safety Stock Optimisation

Edward Elson Kosasih, Alexandra Brintrup

专题命中安全训练：safety(title,abstract)

Comments 12 pages; 6 figures

1. 安全训练 3302 篇

Safety Guaranteed Robust Multi-Agent Reinforcement Learning with Hierarchical Control for Connected and Automated Vehicles

Updating Robot Safety Representations Online from Natural Language Feedback

Hybrid Navigation Acceptability and Safety

Improving safety in mixed traffic: A learning-based model predictive control for autonomous and human-driven vehicle platooning

Enabling Memory Safety of C Programs using LLMs

Assessment of Multimodal Large Language Models in Alignment with Human Values

Unsupervised Large Language Model Alignment for Information Retrieval via Contrastive Feedback

Behavioral Authentication for Security and Safety

Training Adversarial yet Safe Agent to Characterize Safety Performance of Highly Automated Vehicles

Distributed Optimal Output Consensus Control of Heterogeneous Multi-Agent Systems with Safety Constraints

Safety-Critical Coordination of Legged Robots via Layered Controllers and Forward Reachable Set based Control Barrier Functions

Safety-Enhanced Self-Learning for Optimal Power Converter Control

How to Train Your Neural Control Barrier Function: Learning Safety Filters for Complex Input-Constrained Systems

Identifying and Explaining Safety-critical Scenarios for Autonomous Vehicles via Key Features

Probabilistic Safeguard for Reinforcement Learning Using Safety Index Guided Gaussian Process Models

Consensus controller with safety guarantee: an application to the kinematic bicycle model

Safety Guaranteed Manipulation Based on Reinforcement Learning Planner and Model Predictive Control Actor

Safety Embedded Stochastic Optimal Control of Networked Multi-Agent Systems via Barrier States

Industrial Policy for Advanced AI: Compute Pricing and the Safety Tax

Safety of self-assembled neuromorphic hardware

Bounded Distance-control for Multi-UAV Formation Safety and Preservation in Target-tracking Applications

User-specific, Adaptable Safety Controllers Facilitate User Adoption in Human-Robot Collaboration

Barrier Bayesian Linear Regression: Online Learning of Control Barrier Conditions for Safety-Critical Control of Uncertain Systems

Human-AI Interaction for User Safety in Social Matching Apps: Involving Marginalized Users in Design

Monotonic Safety for Scalable and Data-Efficient Probabilistic Safety Analysis

Structured learning of safety guarantees for the control of uncertain dynamical systems

Towards Better Driver Safety: Empowering Personal Navigation Technologies with Road Safety Awareness

Offline Reinforcement Learning for Autonomous Driving with Safety and Exploration Enhancement

Credit Assignment Safety Learning from Human Demonstrations

Reinforcement Learning Provides a Flexible Approach for Realistic Supply Chain Safety Stock Optimisation