pith. sign in

Hong Dingqian

Identifiers

  • name variant Hong Dingqian 0.60 · backfill

Papers (1)

  1. RSPO: Risk-Seeking Policy Optimization for Pass@k and Max@k Metrics in Large Language Models cs.LG · 2025 · author #8

Mentions

  • 2508.01174 #8 · arxiv_oai · confidence 0.70 Hong Dingqian

Frequent Coauthors