RefCaptioner: Multi-Reference Image-Grounded Video Captioning Paper • 2607.28509 • Published 1 day ago • 20
Beacon: Knowing When and How to Perform Agentic Visual Reasoning Paper • 2607.28595 • Published 1 day ago • 39
MultiRef-Compass: Towards Comprehensive Evaluation of Multi-Reference-to-Audio-Video Generation Paper • 2607.14189 • Published 16 days ago • 34
KeyFrame-Compass: Towards Comprehensive Evaluation of Keyframe-Conditioned Video Generation Paper • 2607.14202 • Published 16 days ago • 42
MultiRef-Compass: Towards Comprehensive Evaluation of Multi-Reference-to-Audio-Video Generation Paper • 2607.14189 • Published 16 days ago • 34
KeyFrame-Compass: Towards Comprehensive Evaluation of Keyframe-Conditioned Video Generation Paper • 2607.14202 • Published 16 days ago • 42
CapRiCorn-1K: A Comprehensive Benchmark for Video Captioning and Subject Referential Consistency Across Temporal Scales Paper • 2606.21949 • Published Jun 20