Utility-Diversity Aware Online Batch Selection for LLM Supervised Fine-tuning

Documenti analoghi

• RLVR without Ineffective Samples: Group Prioritized Off-Policy Optimization for LLM Reasoning
  di: Mao, Yixiu, et al.
  Pubblicazione: (2026)
• Dynamics-Predictive Sampling for Active RL Finetuning of Large Reasoning Models
  di: Mao, Yixiu, et al.
  Pubblicazione: (2026)
• Adaptive Neighborhood-Constrained Q Learning for Offline Reinforcement Learning
  di: Mao, Yixiu, et al.
  Pubblicazione: (2025)
• Fast and Robust: Task Sampling with Posterior and Diversity Synergies for Adaptive Decision-Makers in Randomized Environments
  di: Qu, Yun, et al.
  Pubblicazione: (2025)
• Offline Reinforcement Learning with OOD State Correction and OOD Action Suppression
  di: Mao, Yixiu, et al.
  Pubblicazione: (2024)