3 citations · 9 across the 18 of their papers we have counts for
Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Selecting Diverse SFT Traces Improves Post-RL Generalization
Dylan Zhang, Mingyuan Wu, Jinning Li
Verified solutions are not equally useful for preparing reasoning models for reinforcement learning (RL). We present a comprehensive study of route diversity, the variation in the…
cs.LG2026
Good SFT Optimizes for SFT, Better SFT Prepares for Reinforcement Learning
Dylan Zhang, Yufeng Xu, Haojin Wang +2
Post-training of reasoning LLMs is a holistic process that typically consists of an offline SFT stage followed by an online reinforcement learning (RL) stage. However, SFT is often…
cs.LG2024★ 1 cited
Entropy-Regularized Process Reward Model
Hanning Zhang, Pengcheng Wang, Shizhe Diao +6
Large language models (LLMs) have shown promise in performing complex multi-step reasoning, yet they continue to struggle with mathematical reasoning, often making systematic error…