University of Michigan

AI & ML interests

None defined yet.

Recent Activity

shxjames  authored a paper 2 days ago

When "Correct" Is Not Safe: Can We Trust Functionally Correct Patches Generated by Code Agents?

wonderwind271  authored a paper about 1 month ago

From Behavioral Performance to Internal Competence: Interpreting Vision-Language Models with VLM-Lens

Yinpei  authored a paper 3 months ago

Teaching Embodied Reinforcement Learning Agents: Informativeness and Diversity of Language Use

View all activity

Papers

Distributional Autoencoders Know the Score

View all Papers

Team members 1,616