Architecture Decoupling Is Not All You Need For Unified Multimodal Model
Paper • 2511.22663 • Published • 29 •
4
Dian Zheng PRO
zhengli1013
AI & ML interests
generative model
Recent Activity
upvoted a paper 15 days ago
OneSearch-VL: Unified Multimodal Deep Research Agent for Image and Video upvoted a paper 17 days ago
TACD: Distilling Efficient Text-to-Motion Models via Terminal Amplification Control upvoted a paper about 2 months ago
Puffin-World: Scaling a Unified Multimodal Model with Native 3D World StatesOrganizations
commented a
paper 11 months ago