Preprint
Aug 2026
Latent On-Policy Self-Distillation
This work introduces Latent On-Policy Self-Distillation (LOPD), which, rather than proposing another hand-crafted OPSD variant with a newly prescribed form of privileged context, makes the teacher's privileged context itself learnable end-to-end from experience.
Gui-Min Zhang, Jiayang Lyu, Ran Sun et al.
· 1 citation