arxiv:2412.02692
Fengyuan Shi
shifengyuan
AI & ML interests
None yet
Recent Activity
authored
a paper
about 1 month ago
BIVDiff: A Training-Free Framework for General-Purpose Video Synthesis
via Bridging Image and Video Diffusion Models
authored
a paper
about 1 month ago
Taming Scalable Visual Tokenizer for Autoregressive Image Generation
updated
a model
about 1 month ago
TencentARC/Open-MAGVIT2-AR-XL-256-resolution
Organizations
