AnyTalker
🎬
75
Let your character interact naturally
Xianghao Kong
refkxh
AI & ML interests
Computer Vision
Recent Activity
authored a paper about 7 hours ago
UniVidX: A Unified Multimodal Framework for Versatile Video Generation via Diffusion Priors upvoted a paper about 9 hours ago
UniVidX: A Unified Multimodal Framework for Versatile Video Generation via Diffusion Priors authored a paper about 1 month ago
Astrolabe: Steering Forward-Process Reinforcement Learning for Distilled Autoregressive Video ModelsOrganizations
liked a
Space 5 months ago
liked a
dataset 11 months ago