pith. sign in

Runqing Miao

Identifiers

  • name variant Runqing Miao 0.60 · backfill

Papers (1)

  1. Thinking-Based Non-Thinking: Solving the Reward Hacking Problem in Training Hybrid Reasoning Models via Reinforcement Learning cs.AI · 2026 · author #5

Mentions

  • 2601.04805 #5 · arxiv_oai · confidence 0.70 Runqing Miao

Frequent Coauthors