collaborators

9 papers

cs.DC2026

RollArt: Disaggregated Multi-Task Agentic RL Training at Scale

Wei Gao, Yuheng Zhao, Tianyuan Wu +15

Agentic Reinforcement Learning (RL) trains LLMs through multi-turn interactions with environments, producing workloads that mix compute-bound prefill, bandwidth-bound decoding, CPU…

cs.RO2026

OMP: One-step Meanflow Policy with Directional Alignment

Han Fang, Yize Huang, Yuheng Zhao +3

Robot manipulation has increasingly adopted data-driven generative policy frameworks, yet the field faces a persistent trade-off: diffusion models suffer from high inference latenc…

cs.DC2026

ROSE: Rollout On Serving GPUs via Cooperative Elasticity for Agentic RL

Wei Gao, Yuheng Zhao, Dilxat Muhtar +13

Agentic reinforcement learning (RL) is reshaping LLM post-training, but end-to-end training time is dominated by compute-intensive, multi-turn rollouts whose resource demand varies…

cs.LG2026

Towards Fully Parameter-Free Stochastic Optimization: Grid Search with Self-Bounding Analysis

Yuheng Zhao, Yu-Hu Yan, Amit Attia +3

Parameter-free stochastic optimization aims to design algorithms that are agnostic to the underlying problem parameters while still achieving convergence rates competitive with opt…

cs.LG2026

Gradient-Variation Regret Bounds for Unconstrained Online Learning

Yuheng Zhao, Andrew Jacobsen, Nicolò Cesa-Bianchi +1

We develop parameter-free algorithms for unconstrained online learning with regret guarantees that scale with the gradient variation $V_T(u) = \sum_{t=2}^T \|\nabla f_t(u)-\nabla f…

cs.DC2025

RollMux: Phase-Level Multiplexing for Disaggregated RL Post-Training

Tianyuan Wu, Lunxi Cao, Yining Wei +11

Rollout-training disaggregation is emerging as the standard architecture for Reinforcement Learning (RL) post-training, where memory-bound rollout and compute-bound training are ph…