Shaohuai Shi
2 indexed papers
Recent (6 mo)
2With code
0Influential cites
0Benchmarked
0Publications per year
226
Top categories
Distributed×2AI×1Networking×1Performance×1
Frequent co-authors
Research Timeline
2026
Accelerating Disaggregated RL for Visual Generative LLMs with Diffusion-Based Parallelism and Trainer-Assisted Generation
DigenRL is a disaggregated RL framework for diffusion-based generative LLMs that achieves 1.56-2.10x throughput improvements over state-of-the-art diffusion RL systems.
KernelFlume: Elastic Core-Attention Scaling for Agentic Long-Context Decoding
KernelFlume is a decode-centric architecture that disaggregates the stable projection/FFN path from core-attention computation to improve efficiency and reduce cost in serving long-context demand.
Highlighted terms show continued research focus across papers
Papers
cs.DCEmpiricalRecentJun 28, 2026
KernelFlume: Elastic Core-Attention Scaling for Agentic Long-Context Decoding
Guangyu Xiang, Xueze Kang, Lin Zhang, Wenxiang Lin +3 more
KernelFlume is a decode-centric architecture that disaggregates the stable projection/FFN path from core-attention computation to improve efficiency and reduce cost in serving long-context demand.
View →
cs.AIcs.DCcs.NIEmpirical