Policy Split: Incentivizing Dual-Mode Exploration in LLM Reinforcement with Dual-Mode Entropy Regularization

Documenti analoghi

• Utilizing and Calibrating Hindsight Process Rewards via Reinforcement with Mutual Information Self-Evaluation
  di: Yao, Jiashu, et al.
  Pubblicazione: (2026)
• Deterministic Reversible Data Augmentation for Neural Machine Translation
  di: Yao, Jiashu, et al.
  Pubblicazione: (2024)
• Incorporating Self-Rewriting into Large Language Model Reasoning Reinforcement
  di: Yao, Jiashu, et al.
  Pubblicazione: (2025)
• HomeSafeBench: A Benchmark for Embodied Vision-Language Models in Free-Exploration Home Safety Inspection
  di: Gao, Siyuan, et al.
  Pubblicazione: (2025)
• ReFF: Reinforcing Format Faithfulness in Language Models across Varied Tasks
  di: Yao, Jiashu, et al.
  Pubblicazione: (2024)