pith. sign in

Yifu Zheng

Identifiers

  • name variant Yifu Zheng 0.60 · backfill

Papers (1)

  1. RL2ML: Finite-Rollout Surrogate Objectives from Reinforcement Learning to Maximum Likelihood cs.LG · 2026 · author #1

Mentions

  • 2605.30154 #1 · arxiv_oai · confidence 0.70 Yifu Zheng