Junliang Guo

leo-guo's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes

authored a paper 12 days ago

VidTwin: Video VAE with Decoupled Structure and Dynamics

Paper • 2412.17726 • Published 19 days ago • 8

authored a paper 23 days ago

VidTok: A Versatile and Open-Source Video Tokenizer

Paper • 2412.13061 • Published 25 days ago • 8

liked a model 26 days ago

microsoft/VidTok

Updated about 18 hours ago • 26

upvoted a paper 4 months ago

Compositional 3D-aware Video Generation with LLM Director

Paper • 2409.00558 • Published Aug 31, 2024 • 15