Agentic AI for Robot Control: Flexible but still Fragile
用于机器人控制的智能体AI:灵活但依然脆弱
Oscar Lima, Marc Vinci, Martin Günther, Marian Renz, Alexander Sung, Sebastian Stock, Johannes Brust, Lennart Niecksch, Zongyao Yi, Felix Igelbrink, Benjamin Kisliuk, Martin Atzmueller, Joachim Hertzberg
机构
*
ETH Zurich(苏黎世联邦理工学院)
;
University of Cambridge(剑桥大学)
;
Technical University of Munich(慕尼黑技术大学)
;
Max Planck Institute for Intelligent Systems(智能系统马克斯·普朗克研究所)
;
German Aerospace Center (DLR)(德国航空航天中心(DLR))
TamperBench: Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering
TamperBench:系统化压力测试微调和篡改下的LLM安全性
Saad Hossain, Tom Tseng, Punya Syon Pandey, Samanvay Vajpayee, Matthew Kowal, Nayeema Nonta, Samuel Simko, Stephen Casper, Zhijing Jin, Kellin Pelrine, Sirisha Rambhatla
机构
*
Critical ML Lab Waterloo Canada(Waterloo大学Critical ML实验室)
;
FAR.AI Berkeley USA(伯克利美国FAR.AI公司)
;
University of Toronto Toronto Canada(多伦多大学)
;
University of Waterloo Waterloo Canada(Waterloo大学)
;
ETH Zürich Zürich Switzerland(苏黎世联邦理工学院)
;
MIT CSAIL Cambridge USA(麻省理工学院CSAIL实验室)
;
University of Toronto, MPI, EuroSafeAI, Vector Institute Toronto Canada(多伦多大学、马克斯·普朗克研究所、EuroSafeAI、Vector Institute)
;
Critical ML Lab University of Waterloo Waterloo Canada(Waterloo大学Critical ML实验室)
You Only Train Once: Differentiable Subset Selection for Omics Data
你只训练一次:用于组学数据的可微分子集选择
Daphné Chopard, Jorge da Silva Gonçalves, Irene Cannistraci, Thomas M. Sutter, Julia E. Vogt
机构
*
Department of Computer Science, ETH Zurich(计算机科学系,苏黎世联邦理工学院)
;
Department of Intensive Care and Neonatology, University Children’s Hospital Zurich(重症医学与新生儿科,苏黎世大学儿童医院)
From Segments to Scenes: Temporal Understanding for Agentic Autonomous Driving via Vision-Language Models
从片段到场景:自动驾驶中基于视觉语言模型的时间理解
Kevin Cannons, Saeed Ranjbar Alvar, Mohammad Asiful Hossain, Ahmad Rezaei, Mohsen Gholami, Alireza Heidarikhazaei, Zhou Weimin, Yong Zhang, Mohammad Akbari
机构
*
University of California, Berkeley(加州大学伯克利分校)
;
University of Cambridge(剑桥大学)
;
University of Toronto(多伦多大学)
;
ETH Zurich(苏黎世联邦理工学院)
;
University of Washington(华盛顿大学)
;
University of Southern California(南加州大学)
Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
基于深度学习的高维抛物型偏微分方程和反向随机微分方程的数值方法
Weinan E, Jiequn Han, Arnulf Jentzen
机构
*
Beijing Institute of Big Data Research (China)(北京大数据研究院(中国))
;
Princeton University (USA)(普林斯顿大学(美国))
;
Peking University (China)(北京大学(中国))
;
ETH Zurich (Switzerland)(苏黎世联邦理工学院(瑞士))
Bayesian Optimization with Safety Constraints: Safe and Automatic Parameter Tuning in Robotics
具有安全约束的贝叶斯优化:机器人中的安全自动参数调节
Felix Berkenkamp, Andreas Krause, Angela P. Schoellig
机构
*
1 Learning \& Adaptive Systems Group, Department of Computer Science, ETH Zurich, Switzerland. 2 Dynamic Systems Lab, Institute for Aerospace Studies, University of Toronto, Canada.
Communication Compression for Decentralized Training
分布式训练中的通信压缩
Hanlin Tang, Shaoduo Gan, Ce Zhang, Tong Zhang, Ji Liu
机构
*
Department of Computer Science, University of Rochester(罗切斯特大学计算机科学系)
;
Department of Computer Science, ETH Zurich(苏黎世联邦理工学院计算机科学系)
;
Tencent AI Lab(腾讯AI实验室)
Xiaojing Zhang, Alexander Liniger, Francesco Borrelli
机构
*
Model Predictive Control Laboratory, Department of Mechanical Engineering, University of California, Berkeley, USA(加州大学伯克利分校机械工程系模型预测控制实验室)
;
Automatic Control Laboratory, Department of Information Technology and Electrical Engineering, ETH Zurich, Switzerland(苏黎世联邦理工学院信息科技与电气工程系自动控制实验室)
A General Safety Framework for Learning-Based Control in Uncertain Robotic Systems
一种用于不确定机器人系统中基于学习的控制的通用安全框架
Jaime F. Fisac, Anayo K. Akametalu, Melanie N. Zeilinger, Shahab Kaynama, Jeremy Gillula, Claire J. Tomlin
机构
*
Department of Mechanical and Process Engineering, ETH Zurich(瑞士苏黎世联邦理工学院机械与过程工程系)
;
Clearpath Robotics(Clearpath机器人公司)
;
Electronic Frontier Foundation(电子前沿基金会)
CommentsThis is a slightly updated version of the paper published in the ISIT proceedings. Specifically, we corrected errors in the arguments on the volume of tubes. Note that this correction does not affect the main statements of the paper
Journal refProc. of IEEE International Symposium on Information Theory (ISIT), Barcelona, Spain, pp. 1163-1167, July 2016