大模型对齐与安全

On Labs and Fabs: Mapping How Alliances, Acquisitions, and Antitrust are Shaping the Frontier AI Industry

Tomás Aguirre

专题命中 安全训练 ：safety(abstract)

Comments This is a preliminary version of the paper. Comments are welcome. E-mail: t6aguirre@gmail.com

MARLander: A Local Path Planning for Drone Swarms using Multiagent Deep Reinforcement Learning

Demetros Aschu, Robinroy Peter, Sausar Karaf, Aleksey Fedoseev, Dzmitry Tsetserukou

专题命中 安全训练 ：safety(abstract)

Object Manipulation in Marine Environments using Reinforcement Learning

Ahmed Nader, Muhayy Ud Din, Mughni Irfan, Irfan Hussain

专题命中 安全训练 ：safety(abstract)

Comments 8 pages

Journal ref 15th IFAC Conference on Control Applications in Marine Systems, Robotics and Vehicles (CAMS 2024)

MatrixWorld: A pursuit-evasion platform for safe multi-agent coordination and autocurricula

Lijun Sun, Yu-Cheng Chang, Chao Lyu, Chin-Teng Lin, Yuhui Shi

专题命中 安全训练 ：safety(abstract)

SLANT: Spurious Logo ANalysis Toolkit

Maan Qraitem, Piotr Teterwak, Kate Saenko, Bryan A. Plummer

专题命中 安全训练 ：harmlessness(abstract)

Quantifying the Reliance of Black-Box Decision-Makers on Variables of Interest

Daniel Vebman

专题命中 安全训练 ：alignment(abstract)

VERT: Verified Equivalent Rust Transpilation with Large Language Models as Few-Shot Learners

Aidan Z. H. Yang, Yoshiki Takashima, Brandon Paulsen, Josiah Dodds, Daniel Kroening

专题命中 安全训练 ：safety(abstract)

Optimal control barrier functions for RL based safe powertrain control

Habtamu Hailemichael, Beshah Ayalew, Andrej Ivanco

专题命中 安全训练 ：safety(abstract)

Journal ref IFAC-PapersOnLine Volume 56, Issue 3, 2023, Pages 385-390

Delay-Aware Multi-Agent Reinforcement Learning for Cooperative Adaptive Cruise Control with Model-based Stability Enhancement

Jiaqi Liu, Ziran Wang, Peng Hang, Jian Sun

专题命中 安全训练 ：safety(abstract)

Distributed Safe Navigation of Multi-Agent Systems using Control Barrier Function-Based Optimal Controllers

Pol Mestres, Carlos Nieto-Granda, Jorge Cortés

专题命中 安全训练 ：safety(abstract)

Bridging Intelligence and Instinct: A New Control Paradigm for Autonomous Robots

Shimian Zhang, Qiuhong Lu

专题命中 安全训练 ：safety(abstract)

Designing Safe and Engaging AI Experiences for Children: Towards the Definition of Best Practices in UI/UX Design

Grazia Ragone, Paolo Buono, Rosa Lanzilotti

专题命中 安全训练 ：safety(abstract)

Comments 4 pages, The paper has been peer-reviewed and presented at the "CHI 2024 Workshop on Child-centred AI Design", May 11, 2024, Honolulu, HI, USA

Uncovering large inconsistencies between machine learning derived gridded settlement datasets

Vedran Sekara, Andrea Martini, Manuel Garcia-Herranz, Do-Hyung Kim

专题命中 安全训练 ：alignment(abstract)

Comments 14 pages, 4 figures

Error Detection and Correction Codes for Safe In-Memory Computations

Luca Parrini, Taha Soliman, Benjamin Hettwer, Jan Micha Borrmann, Simranjeet Singh, Ankit Bende, Vikas Rana, Farhad Merchant, Norbert Wehn

专题命中 安全训练 ：safety(abstract)

Comments This paper will be presented at 29th IEEE European Test Symposium 2024 (ETS) 2024

vPALs: Towards Verified Performance-aware Learning System For Resource Management

Guoliang He, Gingfung Yeung, Sheriffo Ceesay, Adam Barker

专题命中 安全训练 ：safety(abstract)

Comments presented at Deployable AI Workshop at AAAI-2024

DePAint: A Decentralized Safe Multi-Agent Reinforcement Learning Algorithm considering Peak and Average Constraints

Raheeb Hassan, K. M. Shadman Wadith, Md. Mamun or Rashid, Md. Mosaddek Khan

专题命中 安全训练 ：safety(abstract)

Comments accepted for publication in Springer Applied Intelligence Journal

Collaborative Safe Formation Control for Coupled Multi-Agent Systems

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

专题命中 安全训练 ：safety(abstract)

Comments This work has been accepted to be presented at the 2024 European Control Conference

Decentralized Multimedia Data Sharing in IoV: A Learning-based Equilibrium of Supply and Demand

Jiani Fan, Minrui Xu, Jiale Guo, Lwin Khin Shar, Jiawen Kang, Dusit Niyato, Kwok-Yan Lam

专题命中 安全训练 ：safety(abstract)

Journal ref IEEE Transactions on Vehicular Technology (Volume: 73, Issue: 3, March 2024)

Segmentation tool for images of cracks

Andrii Kompanets, Remco Duits, Davide Leonetti, Nicky van den Berg, H. H., Snijder

专题命中 安全训练 ：safety(abstract)

Envisioning MedCLIP: A Deep Dive into Explainability for Medical Vision-Language Models

Anees Ur Rehman Hashmi, Dwarikanath Mahapatra, Mohammad Yaqub

专题命中 安全训练 ：safety(abstract)

A Control Barrier Function Composition Approach for Multi-Agent Systems in Marine Applications

Yujia Yang, Chris Manzie, Ye Pu

专题命中 安全训练 ：safety(abstract)

Comments 11 pages, 8 figures

HeR-DRL:Heterogeneous Relational Deep Reinforcement Learning for Decentralized Multi-Robot Crowd Navigation

Xinyu Zhou, Songhao Piao, Wenzheng Chi, Liguo Chen, Wei Li

专题命中 安全训练 ：safety(abstract)

Communication-Efficient Decentralized Multi-Agent Reinforcement Learning for Cooperative Adaptive Cruise Control

Dong Chen, Kaixiang Zhang, Yongqiang Wang, Xunyuan Yin, Zhaojian Li, Dimitar Filev

专题命中 安全训练 ：safety(abstract)

Comments 14 pages, 11 figures

Image Safeguarding: Reasoning with Conditional Vision Language Model and Obfuscating Unsafe Content Counterfactually

Mazal Bethany, Brandon Wherry, Nishant Vishwamitra, Peyman Najafirad

专题命中 安全训练 ：safety(abstract)

Learning Crowd Behaviors in Navigation with Attention-based Spatial-Temporal Graphs

Yanying Zhou, Jochen Garcke

专题命中 安全训练 ：safety(abstract)

Close to Human-Level Agreement: Tracing Journeys of Violent Speech in Incel Posts with GPT-4-Enhanced Annotations

Daniel Matter, Miriam Schirmer, Nir Grinberg, Jürgen Pfeffer

专题命中 安全训练 ：alignment(abstract)

Comments 10 pages, 2 figures, 3 tables

Rate-Tunable Control Barrier Functions: Methods and Algorithms for Online Adaptation

Hardik Parwana, Dimitra Panagou

专题命中 安全训练 ：safety(abstract)

Swarm-GPT: Combining Large Language Models with Safe Motion Planning for Robot Choreography Design

Aoran Jiao, Tanmay P. Patel, Sanjmi Khurana, Anna-Mariya Korol, Lukas Brunke, Vivek K. Adajania, Utku Culha, Siqi Zhou, Angela P. Schoellig

专题命中 安全训练 ：safety(abstract)

Comments 10 pages, 9 figures

Learning Safe Control for Multi-Robot Systems: Methods, Verification, and Open Challenges

Kunal Garg, Songyuan Zhang, Oswin So, Charles Dawson, Chuchu Fan

专题命中 安全训练 ：safety(abstract)

Comments Submitted to Annual Reviews in Control

Interpretable Reinforcement Learning for Robotics and Continuous Control

Rohan Paleja, Letian Chen, Yaru Niu, Andrew Silva, Zhaoxin Li, Songan Zhang, Chace Ritchie, Sugju Choi, Kimberlee Chestnut Chang, Hongtei Eric Tseng, Yan Wang, Subramanya Nageshrao, Matthew Gombolay

专题命中 安全训练 ：safety(abstract)

Comments arXiv admin note: text overlap with arXiv:2202.02352