Entropy-Gated Selective Policy Optimization:Token-Level Gradient Allocation for Hybrid Training of Large Language Models

Documenti analoghi

• GAC: Noise-Aware Adaptive Mixing for Hybrid SFT-RL Post-Training
  di: Hu, Yuelin, et al.
  Pubblicazione: (2026)
• ERPO: Token-Level Entropy-Regulated Policy Optimization for Large Reasoning Models
  di: Yu, Song, et al.
  Pubblicazione: (2026)
• Hidden Failure Modes of Gradient Modification under Adam in Continual Learning, and Adaptive Decoupled Moment Routing as a Repair
  di: Hu, Yuelin, et al.
  Pubblicazione: (2026)
• Entropy-Regularized Token-Level Policy Optimization for Language Agent Reinforcement
  di: Wen, Muning, et al.
  Pubblicazione: (2024)
• TLPO: Token-Level Policy Optimization for Mitigating Language Confusion in Large Language Models
  di: Choo, Jinho, et al.
  Pubblicazione: (2026)