34
UI-TARS
🌖
Generate click coordinates from image and instruction
Siyuan Hu
h-siyuan
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
5 days ago
TPDiff: Temporal Pyramid Video Diffusion Model
upvoted
a
paper
22 days ago
PhotoDoodle: Learning Artistic Image Editing from Few-Shot Pairwise Data
upvoted
a
paper
about 1 month ago
WorldGUI: Dynamic Testing for Comprehensive Desktop GUI Automation
Organizations
h-siyuan's activity
liked
a
Space
about 2 months ago
liked
a
dataset
4 months ago
liked
2
Spaces
4 months ago