University of Michigan（密歇根大学安娜堡分校）

SafetyALFRED: Evaluating Safety-Conscious Planning of Multimodal Large Language Models

SafetyALFRED：评估多模态大语言模型的安全意识规划

Josue Torres-Fonseca, Naihao Deng, Yinpei Dai, Shane Storks, Yichi Zhang, Rada Mihalcea, Casey Kennington, Joyce Chai

机构 * University of Michigan（密歇根大学） ； Boise State University（博伊西州立大学） 纠错

AI总结 本文提出SafetyALFRED，基于ALFRED基准测试，引入六类厨房真实世界危险，评估多模态大语言模型在安全意识规划中的表现，发现静态QA评估不足，需转向强调具身环境中的纠正行动的基准。

Comments Work accepted at ACL 2026 Findings

Collaborative Contextual Bayesian Optimization

协同上下文贝叶斯优化

Chih-Yu Chang, Qiyuan Chen, Tianhan Gao, David Fenning, Chinedum Okwudire, Neil Dasgupta, Wei Lu, Raed Al Kontar

机构 * Department of Mathematics, Imperial College London, London, United Kingdom ； Department of Mechanical Engineering, University of Michigan, Ann Arbor, MI, USA. ； Department of Industrial \& Operations Engineering, University of Michigan, Ann Arbor, MI, USA. ； Department of Chemical ； Nano Engineering, University of California, San Diego, CA, USA 纠错

AI总结 本文提出CCBO框架，实现多客户端协同进行上下文贝叶斯优化，支持在线协作和离线初始化，并通过模拟和实际应用证明其在客户端异质性下的有效性。