Video-MOPD improves video understanding with multi-teacher learning
Video-MOPD: Multi-Teacher On-Policy Distillation for Video Understanding
Computer Vision and Pattern Recognition
Summary
Understanding videos well requires a model to do several tricky tasks at once, like noticing details, understanding timing, and solving problems. The authors created Video-MOPD-8B, a model trained to get better at these by learning from multiple expert models each focused on a different skill. They use a special training method that combines feedback from these expert teachers while picking the best learning examples. This approach helps the model perform well across many types of video tasks.
What this means in practice
- •For video software developers: Build applications that require accurate video analysis including timing and reasoning using advanced multi-teacher trained models.
- •For machine learning engineers: Incorporate multi-teacher on-policy distillation methods to improve model performance on complex multi-domain video tasks.
Authors
Zhenxin Qin, Peng Shi, Cong Han, Yinlong Qian, Zequn Jie, Lin Ma
Abstract
Video understanding demands a convergence of complementary capabilities across perception, temporal understanding, and complex reasoning, which are difficult to jointly optimize within a single model. We introduce Video-MOPD-8B, an open-weight model dedicated to video understanding tasks. To fundamentally enhance its capabilities, we conduct targeted reinforcement learning (RL) optimization across three core domains: video temporal grounding (VTG), general video comprehension, and video STEM reasoning. We then unify their complementary capabilities via Multi-Teacher On-Policy Distillation (MOPD), which consolidates expert knowledge by supervising student-generated trajectories with routed teacher feedback. We further introduce Reliability-Aware Informative Sampling (RAIS), which selects examples with consistently reliable teacher supervision and large teacher-student performance gaps. Together, these components enable Video-MOPD-8B to achieve coordinated and comprehensive performance gains across diverse video understanding tasks. Extensive experiments on comprehensive benchmarks covering general video understanding, temporal grounding, video reasoning, and video STEM tasks demonstrate that Video-MOPD-8B achieves state-of-the-art performance among existing models at a comparable scale. The trained model weights are available at https://huggingface.co/LandH/Video-MOPD-8B.