Cheers: Decoupling Patch Details from Semantic Representations Enables Unified Multimodal Comprehension and Generation
Paper • 2603.12793 • Published • 38
Jingfan Ke
JingfanKe
AI & ML interests
None yet
Recent Activity
liked a model about 1 year ago
zhibinlan/LLaVE-2B upvoted a paper over 1 year ago
Migician: Revealing the Magic of Free-Form Multi-Image Grounding in
Multimodal Large Language ModelsOrganizations
None yet
upvoted a paper about 1 month ago