#artificial intelligence
Apr 2026
Lightning OPD: Efficient Post-Training for Large Reasoning Models with Offline On-Policy Distillation
Lightning OPD is proposed, an offline on-policy distillation framework that enforces teacher consistency and eliminates the need for a live teacher server entirely and achieves comparable performance to standard OPD while delivering 4.0x higher training efficiency.
Ye-Cheng Wu, Song Han, H. Cai
· arXiv.org · 30 citations
· ⚡2