tracked author

Weixun Wang

RollArt equal-contribution author from Alibaba Group. Stable evidence comes from the RollArt, RollPacker and ROLL Flash author lines; no high-confidence personal homepage or X account was found in this pass.

1 archived notes X: not-found

Related Notes

按论文归档时间排序,展示该作者在本站已经出现的材料。

Jun 30, 2026

RollArt: Disaggregated Multi Task Agentic RL Training at Scale

RollArt 用静态 task domain affinity 声明把训练、prefill heavy rollout、decode heavy rollout、环境与 reward 映射到 H800、H20、CPU/Kubernetes 和 serverless 资源池,再用轨迹级状态机、起始版本年龄上限 $\alpha$ 与 Mooncake weight movement 协调跨池异步;OSDI camera ready 支持...

2512.22560-rollart-disaggregated-agentic-rl-training RL InfrastructureRollout OptimizationDistributed Training