OPD 技术
1
衍生技术
0
相关产品
1
相关事件
OPD · 相关文章
相关文章
Stage-1 Controls the Entropy Regime, Not the Outcome
ArXiv CS.CV2026-06-09
Multi-Rollout On-Policy Distillation via Peer Successes and Failures
ArXiv CS.AI2026-06-02
Prune-OPD: Efficient and Reliable On-Policy Distillation for Long-Horizon Reasoning
ArXiv CS.AI2026-05-29
ADWIN: Adaptive Windows for Horizon-Aware On-Policy Distillation
ArXiv CS.AI2026-05-28