RefCaptioner: Multi-Reference Image-Grounded Video Captioning Paper • 2607.28509 • Published 2 days ago • 24
Beacon: Knowing When and How to Perform Agentic Visual Reasoning Paper • 2607.28595 • Published 2 days ago • 45
MultiRef-Compass: Towards Comprehensive Evaluation of Multi-Reference-to-Audio-Video Generation Paper • 2607.14189 • Published 17 days ago • 34
KeyFrame-Compass: Towards Comprehensive Evaluation of Keyframe-Conditioned Video Generation Paper • 2607.14202 • Published 17 days ago • 42