Junxian Mu
xxz9
AI & ML interests
None yet
Recent Activity
upvoted a paper 5 days ago
TLive-Omni: An Omni-Modal Understanding Model for E-Commerce Live Streaming upvoted a paper about 1 month ago
VideoCoCo: Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System upvoted a paper 3 months ago
Lens: Rethinking Training Efficiency for Foundational Text-to-Image ModelsOrganizations
