VersaVid-R1: A Versatile Video Understanding and Reasoning Model from Question Answering to Captioning Tasks
By: Xinlong Chen , Yuanxing Zhang , Yushuo Guan and more
Potential Business Impact:
Helps computers understand and answer questions about videos.
Recent advancements in multimodal large language models have successfully extended the Reason-Then-Respond paradigm to image-based reasoning, yet video-based reasoning remains an underdeveloped frontier, primarily due to the scarcity of high-quality reasoning-oriented data and effective training methodologies. To bridge this gap, we introduce DarkEventInfer and MixVidQA, two novel datasets specifically designed to stimulate the model's advanced video understanding and reasoning abilities. DarkEventinfer presents videos with masked event segments, requiring models to infer the obscured content based on contextual video cues. MixVidQA, on the other hand, presents interleaved video sequences composed of two distinct clips, challenging models to isolate and reason about one while disregarding the other. Leveraging these carefully curated training samples together with reinforcement learning guided by diverse reward functions, we develop VersaVid-R1, the first versatile video understanding and reasoning model under the Reason-Then-Respond paradigm capable of handling multiple-choice and open-ended question answering, as well as video captioning tasks. Extensive experiments demonstrate that VersaVid-R1 significantly outperforms existing models across a broad spectrum of benchmarks, covering video general understanding, cognitive reasoning, and captioning tasks.
Similar Papers
Looking Beyond Visible Cues: Implicit Video Question Answering via Dual-Clue Reasoning
CV and Pattern Recognition
Helps computers understand video meaning, not just what's shown.
Video-R2: Reinforcing Consistent and Grounded Reasoning in Multimodal Language Models
CV and Pattern Recognition
Helps computers understand videos by watching carefully.
OneThinker: All-in-one Reasoning Model for Image and Video
CV and Pattern Recognition
One model understands images and videos for many tasks.