arxiv:2505.15436
Pengxiang Li
PengxiangLi
·
AI & ML interests
None yet
Recent Activity
authored
a paper
10 days ago
Chain-of-Focus: Adaptive Visual Search and Zooming for Multimodal
Reasoning via RL
liked
a Space
14 days ago
depth-anything/Depth-Anything-V2
upvoted
a
paper
15 days ago
Sekai: A Video Dataset towards World Exploration
Organizations
None yet
