Trust Region Preference Approximation: A simple and stable reinforcement learning algorithm for LLM reasoning

Documenti analoghi

• DGRO: Enhancing LLM Reasoning via Exploration-Exploitation Control and Reward Variance Management
  di: Su, Xuerui, et al.
  Pubblicazione: (2025)
• HybriDNA: A Hybrid Transformer-Mamba2 Long-Range DNA Language Model
  di: Ma, Mingqian, et al.
  Pubblicazione: (2025)
• OThink-MR1: Stimulating multimodal generalized reasoning capabilities via dynamic reinforcement learning
  di: Liu, Zhiyuan, et al.
  Pubblicazione: (2025)
• MolChord: Structure-Sequence Alignment for Protein-Guided Drug Design
  di: Zhang, Wei, et al.
  Pubblicazione: (2025)
• Reveal the Mystery of DPO: The Connection between DPO and RL Algorithms
  di: Su, Xuerui, et al.
  Pubblicazione: (2025)