pith. sign in

Dingwei Zhu

Identifiers

  • name variant Dingwei Zhu 0.60 · backfill

Papers (6)

  1. Prefix-Adaptive Block Diffusion for Efficient Document Recognition cs.CV · 2026 · author #6
  2. Entropy Polarity in Reinforcement Fine-Tuning: Direction, Asymmetry, and Control cs.LG · 2026 · author #11
  3. EVPO: Explained Variance Policy Optimization for Adaptive Critic Utilization in LLM Post-Training cs.LG · 2026 · author #4
  4. AgentV-RL: Scaling Reward Modeling with Agentic Verifier cs.CL · 2026 · author #13
  5. DFPO: Scaling Value Modeling via Distributional Flow towards Robust and Generalizable LLM Post-Training cs.LG · 2026 · author #1
  6. DVPO: Distributional Value Modeling-based Policy Optimization for LLM Post-Training cs.LG · 2025 · author #1

Mentions

  • 2605.16861 #6 · arxiv_oai · confidence 0.70 Dingwei Zhu
  • 2605.11775 #11 · backfill · confidence 0.70 Dingwei Zhu

Frequent Coauthors