pith. sign in

Huanwei Di

Identifiers

  • name variant Huanwei Di 0.60 · backfill

Papers (1)

  1. PR2: Predictive Routing Replay for MoE-Based LLM Reinforcement Learning cs.LG · 2026 · author #5

Mentions

  • 2606.00395 #5 · arxiv_oai · confidence 0.70 Huanwei Di

Frequent Coauthors