TokLIP: Marry Visual Tokens to CLIP for Multimodal Comprehension and Generation Paper • 2505.05422 • Published May 8 • 8
FlexiAct: Towards Flexible Action Control in Heterogeneous Scenarios Paper • 2505.03730 • Published May 6 • 28
Cobra: Efficient Line Art COlorization with BRoAder References Paper • 2504.12240 • Published Apr 16 • 28