Preprint
Aug 2026
Where to Look Matters: On-Policy Self-Distillation for Long-Video Understanding
Clue-OPSD, a clue-privileged on-policy self-distillation framework for long-video understanding that uses clue intervals as privileged supervision without relying on ground-truth answer labels, while requiring no clue annotations or additional modules at inference time is introduced.
Kaishen Wang, Dong-Di Zhao, Yijun Liang et al.
· 0 citations