pith. sign in

Lifan Yuan

Identifiers

  • name variant Lifan Yuan 0.60 · backfill

Papers (6)

  1. Probing the Critical Point (CritPt) of AI Reasoning: a Frontier Physics Research Benchmark cs.AI · 2025 · author #5
  2. The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models cs.LG · 2025 · author #4
  3. The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning cs.LG · 2025 · author #3
  4. TTRL: Test-Time Reinforcement Learning cs.CL · 2025 · author #14
  5. Process Reinforcement through Implicit Rewards cs.LG · 2025 · author #2
  6. UltraFeedback: Boosting Language Models with Scaled AI Feedback cs.CL · 2023 · author #2

Mentions

  • 2505.15134 #3 · arxiv_oai · confidence 0.70 Lifan Yuan
  • 2310.01377 #2 · arxiv_oai · confidence 0.70 Lifan Yuan

Frequent Coauthors