ReToken: One Token to Improve Vision-Language Models for Visual Retrieval
Paper • 2607.28627 • Published • 9
yuqun wu
yuqun
·
AI & ML interests
None yet
Recent Activity
upvoted a paper about 21 hours ago
ReToken: One Token to Improve Vision-Language Models for Visual Retrieval upvoted a paper 1 day ago
4Director: Controlling Video World Models with Rigid 3D Geometry liked a model 1 day ago
vveicao/4DirectorOrganizations
