arxiv:2608.28958
Patrick (Tsung-Han) Wu
tsunghanwu
AI & ML interests
Vision and Language
Recent Activity
upvoted a paper 29 days ago
OmniTaskonomy: When Does Visual Generation Improve Visual Understanding? authored a paper 2 months ago
SAM 3: Segment Anything with Concepts authored a paper 2 months ago
DigitalCoach: Communication and Grounding Gaps in Human and Agentic Computer Use Coaching