@article{hdpohybriddistillationpolicyoptimization,
  title = {HDPO: Hybrid Distillation Policy Optimization via Privileged Self-Distillation},
  author = {Ken Ding},
  year = {2026},
  eprint = {2603.23871},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2603.23871},
}