Efficient RLVR Training via Weighted Mutual Information Data Selection

Documenti analoghi

• CodeScaler: Scaling Code LLM Training and Test-Time Inference via Reward Models
  di: Zhu, Xiao, et al.
  Pubblicazione: (2026)
• Balancing the Reasoning Load: Difficulty-Differentiated Policy Optimization with Length Redistribution for Efficient and Robust Reinforcement Learning
  di: Xia, Yinan, et al.
  Pubblicazione: (2026)
• You Only Need Minimal RLVR Training: Extrapolating LLMs via Rank-1 Trajectories
  di: Wei, Zhepei, et al.
  Pubblicazione: (2026)
• How Far Can Unsupervised RLVR Scale LLM Training?
  di: He, Bingxiang, et al.
  Pubblicazione: (2026)
• Linear Dynamics in the RLVR Training of Large Language Models
  di: Wang, Tianle, et al.
  Pubblicazione: (2026)