pith. sign in

Ju Huang

Identifiers

  • name variant Ju Huang 0.60 · backfill

Papers (5)

  1. The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning cs.LG · 2026 · author #7
  2. Spotlight: Synergizing Seed Exploration and Spot GPUs for DiT RL Post-Training cs.DC · 2026 · author #4
  3. ROSE: Rollout On Serving GPUs via Cooperative Elasticity for Agentic RL cs.DC · 2026 · author #10
  4. Complementary RL: Towards Efficient Experience-Driven Agent Learning cs.LG · 2026 · author #6
  5. Recollements, sinks elimination and Leavitt path algebras math.RA · 2016 · author #2

Mentions

  • 2606.29526 #7 · arxiv_oai · confidence 0.70 Ju Huang
  • 2603.17621 #6 · arxiv_oai · confidence 0.70 Ju Huang
  • 2606.19004 #4 · arxiv_oai · confidence 0.70 Ju Huang
  • 2605.06534 #10 · arxiv_oai · confidence 0.70 Ju Huang

Frequent Coauthors