1 citations · 1 across the 10 of their papers we have counts for
11 papers
Rollplex: Cross-Phase GPU Spatial Sharing for Vision Language Model Post-Training
Hanfeng Lu, Tianyu Feng, Suyi Li +8
Vision-language models (VLMs) enable embodied agents to reason and act from visual observations and language instructions. Reinforcement learning (RL) post-training enhances these…
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…
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…
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…
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…
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…
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…
Gradient-Variation Online Adaptivity for Accelerated Optimization with Hölder Smoothness
Yuheng Zhao, Yu-Hu Yan, Kfir Yehuda Levy +1
Smoothness is known to be crucial for acceleration in offline optimization, and for gradient-variation regret minimization in online learning. Interestingly, these two problems are…
RollPacker: Mitigating Long-Tail Rollouts for Fast, Synchronous RL Post-Training
Wei Gao, Yuheng Zhao, Dakai An +11
Reinforcement Learning (RL) is a pivotal post-training technique for enhancing the reasoning capabilities of Large Language Models (LLMs). However, synchronous RL post-training oft…
Reinforcement Learning Optimization for Large-Scale Learning: An Efficient and User-Friendly Scaling Library
Weixun Wang, Shaopan Xiong, Gengru Chen +38
We introduce ROLL, an efficient, scalable, and user-friendly library designed for Reinforcement Learning Optimization for Large-scale Learning. ROLL caters to three primary user gr…
Different intermediate water cluster with distinct nucleation dynamics among mono layer ice nucleation
Yuheng Zhao, Yi Qin Gao
Recent first-principle calculations unveiled a distinctive dynamic behavior in water molecule rotation during the melting process of highly confined water, indicating a notable tim…