arxiv:2603.03985
Yansong Shi
nanamma
AI & ML interests
multi modality, video understanding, robotics
Recent Activity
upvoted a paper about 10 hours ago
VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding upvoted a paper 4 months ago
Video-o3: Native Interleaved Clue Seeking for Long Video Multi-Hop Reasoning new activity 4 months ago
nanamma/RIVER:Add task categories and link to paperOrganizations
