pith. sign in

Yongfu Zhu

Identifiers

  • name variant Yongfu Zhu 0.60 · backfill

Papers (4)

  1. Right Makes Might: Aligning Verified Hidden States Empowers RL Reasoning cs.LG · 2026 · author #3
  2. Leveraging Error Diversity in Group Rollouts for Reinforcement Learning cs.LG · 2026 · author #4
  3. Step-wise Rubric Rewards for LLM Reasoning cs.LG · 2026 · author #4
  4. TinyR1-32B-Preview: Boosting Accuracy with Branch-Merge Distillation cs.CL · 2025 · author #6

Mentions

  • 2606.03234 #3 · arxiv_oai · confidence 0.70 Yongfu Zhu
  • 2605.17333 #4 · arxiv_oai · confidence 0.70 Yongfu Zhu
  • 2605.17291 #4 · arxiv_oai · confidence 0.70 Yongfu Zhu

Frequent Coauthors