Video-MOPD: Multi-Teacher On-Policy Distillation for Video Understanding

Researchers released Video-MOPD-8B, an open-weight video understanding model trained via Multi-Teacher On-Policy Distillation (MOPD), which the paper reports achieves state-of-the-art performance among models of comparable scale. The model was optimized with targeted reinforcement learning across three domains — video temporal grounding (VTG), general video comprehension, and video STEM reasoning — and uses Reliability-Aware Informative Sampling (RAIS) to select examples with reliable teacher supervision and large teacher-student gaps. The trained weights are available at https://huggingface.co/LandH/Video-MOPD-8B.

arXiv:2609.09300v1 Announce Type: new 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.