Yinmin Zhong

6 papers · 2023–2026 · 2 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (12) 👥 Mega-Team · Squad 🏆 Keyword Champion

Venues

NSDI (4) OSDI (2)

Top co-authors

Xin Jin (6) Xuanzhe Liu (3) Shengyu Liu (3) Yibo Zhu (2) Hao Zhang (2) Zili Zhang (2) Bingyang Wu (2) Sida Zhao (1) Zhuohan Li (1) Ion Stoica (1)

Research topics

Machine Learning (4) Optimization & Theory (4) Natural Language Processing (3) Application Areas (3) Resources & Methods (3) Artificial Intelligence (2) Computer Science (2) Deep Learning (2) Core AI (2) Systems (2) Reinforcement Learning (1) Methods (1) Models (1) Techniques (1)

Keywords

large language model (3) model parallelism (2) reinforcement learning from human feedback (1) training optimization (1) fault tolerance (1) throughput optimization (1) training throughput (1) gpu resource allocation (1) resource scheduling (1) latency optimization (1) stage fusion (1) gpu utilization (1) inference serving (1) distributed system (1) preemptive scheduling (1) statistical multiplexing (1) serving latency (1) bursty workload (1) distributed cluster (1) large language model training (1)

Papers

DistRS: Disaggregated Reward Service for RLVR with Batch-Level Constraint NSDI 2026 FastServe: Iteration-Level Preemptive Scheduling for Large Language Model Inference NSDI 2026 Optimizing RLHF Training for Large Language Models with Stage Fusion NSDI 2025 DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving OSDI 2024 MegaScale: Scaling Large Language Model Training to More Than 10,000 GPUs NSDI 2024 AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving OSDI 2023