Junxian Mu

xxz9

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 1 day ago

VideoCoCo: Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System

upvoted a paper 2 months ago

Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models

upvoted a paper 2 months ago

InsightTok: Improving Text and Face Fidelity in Discrete Tokenization for Autoregressive Image Generation

View all activity

Organizations

models 0

None public yet

datasets 0

None public yet