arxiv:2605.21573
Fangyun Wei
fangyunwei
AI & ML interests
None yet
Recent Activity
upvoted a paper about 1 month ago
VideoVLA: Video Generators Can Be Generalizable Robot Manipulators upvoted a paper about 1 month ago
Spatia: Video Generation with Updatable Spatial Memory upvoted a paper about 1 month ago
InsightTok: Improving Text and Face Fidelity in Discrete Tokenization for Autoregressive Image Generation