3 papers
cs.LG2026
Stable Asynchrony: Variance-Controlled Off-Policy RL for LLMs
Luke J. Huang, Zhuoyang Zhang, Qinghao Hu +2
Asynchronous reinforcement learning has become increasingly central to scaling LLM post-training, delivering major throughput gains by decoupling rollout generation from policy upd…
cs.RO2026
ForeAct: Steering Your VLA with Efficient Visual Foresight Planning
Zhuoyang Zhang, Shang Yang, Qinghao Hu +5
Vision-Language-Action (VLA) models convert high-level language instructions into concrete, executable actions, a task that is especially challenging in open-world environments. We…
cs.CV2025
Locality-aware Parallel Decoding for Efficient Autoregressive Image Generation
Zhuoyang Zhang, Luke J. Huang, Chengyue Wu +4
We present Locality-aware Parallel Decoding (LPD) to accelerate autoregressive image generation. Traditional autoregressive image generation relies on next-patch prediction, a memo…