Wanshun Su

RowanSu

4

·

AI & ML interests

None yet

Recent Activity

upvoted a paper about 21 hours ago

RefCaptioner: Multi-Reference Image-Grounded Video Captioning

upvoted a paper about 22 hours ago

Beacon: Knowing When and How to Perform Agentic Visual Reasoning

updated a dataset 15 days ago

RowanSu/avutenchmark

View all activity

Organizations

upvoted a paper about 21 hours ago

RefCaptioner: Multi-Reference Image-Grounded Video Captioning

Paper • 2607.28509 • Published 2 days ago • 24

upvoted a paper about 22 hours ago

Beacon: Knowing When and How to Perform Agentic Visual Reasoning

Paper • 2607.28595 • Published 2 days ago • 44

upvoted 2 papers 15 days ago

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