Preprint
Sep 2026
Video-MOPD: Multi-Teacher On-Policy Distillation for Video Understanding
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 c...
Zheng-Xing Qin, Peng Shi, Cong Han et al.
· 1 citation