Ming Chen's picture

59 3

Ming Chen

ChenMing-thu14

·

AI & ML interests

3D Human Pose Estimation

Recent Activity

upvoted a paper 3 days ago

Learning from Next-Frame Prediction: Autoregressive Video Modeling Encodes Effective Representations

upvoted a paper 3 days ago

TurboDiffusion: Accelerating Video Diffusion Models by 100-200 Times

upvoted a paper 4 days ago

SemanticGen: Video Generation in Semantic Space

View all activity

Organizations

None yet

authored a paper 2 months ago

Kling-Avatar: Grounding Multimodal Instructions for Cascaded Long-Duration Avatar Animation Synthesis

Paper • 2509.09595 • Published Sep 11 • 48

authored a paper 4 months ago

MIDAS: Multimodal Interactive Digital-human Synthesis via Real-time Autoregressive Video Generation

Paper • 2508.19320 • Published Aug 26 • 29