類似資料

• TIP: Token Importance in On-Policy Distillation
  著者:: Xu, Yuanda, 等
  出版事項: (2026)
• Beyond GRPO and On-Policy Distillation: An Empirical Sparse-to-Dense Reward Principle for Language-Model Post-Training
  著者:: Xu, Yuanda, 等
  出版事項: (2026)
• Overconfident Errors Need Stronger Correction: Asymmetric Confidence Penalties for Reinforcement Learning
  著者:: Xu, Yuanda, 等
  出版事項: (2026)
• Not all tokens are needed(NAT): token efficient reinforcement learning
  著者:: Sang, Hejian, 等
  出版事項: (2026)
• CRISP: Compressed Reasoning via Iterative Self-Policy Distillation
  著者:: Sang, Hejian, 等
  出版事項: (2026)