arxiv:2510.23607
Wang Chengyao PRO
wcy1122
AI & ML interests
Multimodal Intelligence
Recent Activity
updated a Space 4 days ago
wcy1122/MGM-Omni upvoted a paper about 1 month ago
LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation upvoted a paper 3 months ago
VP-VLA: Visual Prompting as an Interface for Vision-Language-Action Models