pinned
Running
22
Online-Mind2Web Leaderboard
🌐
Visualize AI agent performance with tables and interactive plots
AI & ML interests
Natural language processing, language models, language agents
Recent Activity
View all activity
Papers
When Actions Go Off-Task: Detecting and Correcting Misaligned Actions in Computer-Use Agents
When Benign Inputs Lead to Severe Harms: Eliciting Unsafe Unintended Behaviors of Computer-Use Agents