arxiv:2503.03651
Rui Zhao
ruizhaocv
AI & ML interests
Multimodal and GenAI
Recent Activity
upvoted
a
paper
about 7 hours ago
See, Point, Fly: A Learning-Free VLM Framework for Universal Unmanned
Aerial Navigation
upvoted
a
paper
about 8 hours ago
LongLive: Real-time Interactive Long Video Generation
upvoted
a
paper
4 days ago
Video models are zero-shot learners and reasoners