pith. sign in

Junwu Xiong

Identifiers

  • name variant Junwu Xiong 0.60 · backfill

Papers (10)

  1. Pre-VLA: Preemptive Runtime Verification for Reliable Vision-Language-Action and World-Model Rollouts cs.CV · 2026 · author #8
  2. AdaptiveLoad: Towards Efficient Video Diffusion Transformer Training cs.DC · 2026 · author #9
  3. D-VLA: A High-Concurrency Distributed Asynchronous Reinforcement Learning Framework for Vision-Language-Action Models cs.AI · 2026 · author #11
  4. NoiseGate: Learning Per-Latent Timestep Schedules as Information Gating in World Action Models cs.RO · 2026 · author #11
  5. Sword: Style-Robust World Models as Simulators via Dynamic Latent Bootstrapping for VLA Policy Post-Training cs.CV · 2026 · author #7
  6. JoyAI-RA 0.1: A Foundation Model for Robotic Autonomy cs.RO · 2026 · author #52
  7. JoyAI-LLM Flash: Advancing Mid-Scale LLMs with Token Efficiency cs.CL · 2026 · author #24
  8. RL-VLA$^3$: A Flexible and Asynchronous Reinforcement Learning Framework for VLA Training cs.AI · 2026 · author #16
  9. Reinforcement Learning for Uplift Modeling cs.LG · 2018 · author #9
  10. Latent Dirichlet Allocation for Internet Price War cs.AI · 2018 · author #9

Mentions

  • 2605.22446 #8 · arxiv_oai · confidence 0.70 Junwu Xiong
  • 2605.17923 #9 · arxiv_oai · confidence 0.70 Junwu Xiong

Frequent Coauthors