Yuanda Xu

Identifiers

• name variant Yuanda Xu 0.60 · backfill

Papers (4)

1. Beyond GRPO and On-Policy Distillation: An Empirical Sparse-to-Dense Reward Principle for Language-Model Post-Training cs.LG · 2026 · author #1
2. TIP: Token Importance in On-Policy Distillation cs.LG · 2026 · author #1
3. PACED: Distillation and On-Policy Self-Distillation at the Frontier of Student Competence cs.AI · 2026 · author #1
4. CRISP: Compressed Reasoning via Iterative Self-Policy Distillation cs.LG · 2026 · author #2

Mentions

• 2604.14084 #1 · arxiv_oai · confidence 0.70 Yuanda Xu
• 2605.12483 #1 · arxiv_oai · confidence 0.70 Yuanda Xu

Frequent Coauthors

• Hejian Sang 4 shared papers
• Ran He 4 shared papers
• Zhengze Zhou 4 shared papers
• Zhipeng Wang 4 shared papers
• Alborz Geramifard 2 shared papers
• Jiachen Sun 1 shared papers