arxiv:2412.09645
zhangfan
Fan-s
AI & ML interests
Video Generation, MultiModal Learning
Recent Activity
upvoted a paper 1 day ago
HiAR: Efficient Autoregressive Long Video Generation via Hierarchical Denoising upvoted a paper 3 months ago
LongVie 2: Multimodal Controllable Ultra-Long Video World Model upvoted a paper 3 months ago
Architecture Decoupling Is Not All You Need For Unified Multimodal Model Organizations
