arxiv:2602.07274
William Li
williamium
AI & ML interests
Learning AI efficiently and robustly in interactive, multi-modal and embodied environment.
Recent Activity
upvoted a paper 1 day ago
CocoaBench: Evaluating Unified Digital Agents in the Wild updated a model 3 days ago
williamium/deepeyes upvoted a paper 3 days ago
Can Vision Language Models Infer Human Gaze Direction? A Controlled
Study