Xingwei Gan

Identifiers

• name variant Xingwei Gan 0.60 · backfill

Papers (1)

1. Complementing reinforcement learning with SFT through logit averaging in the post training of LLMs cs.LG · 2026 · author #1

Mentions

• 2605.20555 #1 · arxiv_oai · confidence 0.70 Xingwei Gan

Frequent Coauthors

• Ying Zhu 1 shared papers