Future Open Source Research

面向未来的开源研究

Future Machine Learning
& Systems Lab实验室

We study how to make machine learning more capable, efficient, and practical at scale through four connected directions: algorithm and architecture innovation, systems optimization, quantization, and post-training-driven modeling.

我们研究如何让机器学习在大规模场景下更强大、更高效、更实用,聚焦四个相互关联的方向:算法与架构创新、系统优化、量化,以及后训练驱动的建模。

About 关于

Who we are

我们是谁

Welcome to the Future Machine Learning & Systems (FutureMLS) Lab. We work at the intersection of machine learning and computer systems. Today's foundation models are remarkably capable but costly to train and serve. Our mission is to close the gap between rapidly growing model capability and the real-world cost of deploying these models.

欢迎来到 Future Machine Learning & Systems (FutureMLS) 实验室。我们的研究处在机器学习与计算机系统的交叉地带。今天的基础模型能力惊人,但训练与部署的成本同样高昂。我们的使命,是弥合模型能力的快速增长与真实部署成本之间的鸿沟。

We pursue algorithm-system co-design across four connected themes: Efficient ML Algorithm for algorithm and architecture innovation, Efficient ML System for systems optimization, Quantization as a core research focus, and Modeling for improving models through training. Our work spans the AI stack, from methods and model design to kernels, runtimes, and serving systems, and is open-source, reproducible, and built to be used.

我们围绕四个相互关联的主题推进算法—系统协同设计:Efficient ML Algorithm 负责算法与架构创新,Efficient ML System 负责系统层面的优化,Quantization 是我们的核心研究方向,Modeling 则通过训练让模型变得更强。我们的工作贯穿整个 AI 技术栈——从方法与模型设计,到算子、运行时与服务系统——并且坚持开源、可复现、可直接使用。

Founder & PI: Zhongzhu Zhou 创始人 & 负责人:周中柱

Founder 创始人

About Zhongzhu Zhou

关于周中柱

Zhongzhu Zhou (Charlie Zhou) is the founder and principal investigator of the Future Machine Learning & Systems Lab. He is a Senior Research Scientist on the Turbo Team at Together AI, and earned his Ph.D. at the School of Computer Science, University of Sydney.

周中柱(Charlie Zhou)是 Future Machine Learning & Systems 实验室的创始人与首席研究员。他现任 Together AI Turbo 团队高级研究科学家,并于悉尼大学计算机科学学院取得博士学位。

His research spans efficient machine learning and systems — from pretraining quality to efficient algorithms and algorithm–system co-design that bridges emerging ML/LLM methods and real-world applications, improving both productivity (usable, robust stacks) and performance (throughput, memory, and cost-efficiency). He received his B.Eng. (Hons) from Sun Yat-sen University, and has interned at Dolby, the DeepSpeed team at Microsoft, and Tencent.

他的研究覆盖高效机器学习与系统——从预训练质量,到高效算法,再到连接前沿 ML/LLM 方法与真实应用的算法—系统协同设计,同时提升研发效率(好用且稳健的技术栈)与运行性能(吞吐、显存与成本)。他本科毕业于中山大学并获荣誉学位,曾在 Dolby、微软 DeepSpeed 团队与腾讯实习。

He leads projects across the lab's four themes, including OSCAR (2-bit KV-cache quantization) and CARE (covariance-aware Multi-Head Latent Attention).

他主导实验室四个方向上的多个项目,包括 OSCAR(2-bit KV-cache 量化)与 CARE(协方差感知的 Multi-Head Latent Attention)。

Research 研究

What we work on

我们的研究方向

Four directions, one goal: efficient and capable AI at scale.

四个方向,一个目标:让大规模 AI 既高效又强大。

01

Efficient ML Algorithm

Algorithm and architecture innovations that improve capability while reducing compute, memory, and deployment cost.

通过算法与架构创新提升模型能力,同时降低计算、显存与部署成本。

02

Efficient ML System

System-level optimizations that make efficient methods practical end-to-end, from kernels and runtimes to high-throughput serving.

从算子、运行时到高吞吐服务,用系统层面的优化让高效方法端到端地落地。

03

Quantization

A core research focus on low-bit weight, activation, and KV-cache quantization that preserves accuracy while cutting memory and compute.

我们的核心方向:低比特的权重、激活与 KV-cache 量化,在压缩显存与计算的同时保持精度。

04

Modeling

Model improvement through training optimization, architecture design, and adaptation methods that make models stronger and easier to use.

通过训练优化、架构设计与适配方法改进模型,让模型更强、也更易用。

News 新闻

Recent updates

最新动态

Team 团队

People

团队成员

A small group of researchers and advisors building in the open.

一支小而专注的研究者与顾问团队,坚持开放地做研究。

Advisors

顾问

Xiaoxia Wu

Xiaoxia Wu

Advisor

顾问

Principal Research scientist in efficient ML and low-bit quantization, with extensive work across the DeepSpeed and Together AI.

高效机器学习与低比特量化方向的首席研究科学家,在 DeepSpeed 与 Together AI 有大量相关工作。

  • Efficient ML Algorithm
  • Efficient ML System
  • Quantization
Shuaiwen Leon Song

Shuaiwen Leon Song

Advisor

顾问

Professor at the University of Sydney; high-performance computing and ML systems.

悉尼大学教授,研究方向为高性能计算与机器学习系统。

  • Efficient ML System

Members

成员

PhD Students

博士生

Mentored PhDs

指导的博士生

Yiyang Guo

Yiyang Guo

Ph.D. Student, UC Santa Cruz

博士生,加州大学圣克鲁兹分校

Post-training-driven modeling with a focus on Mixture-of-Experts (MoE) training.

后训练驱动的建模,聚焦 Mixture-of-Experts (MoE) 训练。

  • Modeling
  • Mixture-of-Experts
Zhizhou Sha

Zhizhou Sha

Ph.D. Student, UT Austin

博士生,德克萨斯大学奥斯汀分校

Quantization-aware training for efficient and accurate large language models.

面向高效且高精度大语言模型的量化感知训练。

  • Quantization
  • Quantization-Aware Training

Mentored Students

指导的学生

Fengxiang “Bobbie” Bie

Fengxiang “Bobbie” Bie

Student Researcher

学生研究员

Efficient ML algorithms and speculative decoding; contributor to CARE.

高效机器学习算法与投机解码;CARE 项目贡献者。

  • Efficient ML Algorithm
  • Speculator
Ziyan Chen

Ziyan Chen

Student Researcher

学生研究员

Efficient ML algorithms and KV-cache compression; contributor to OSCAR and CARE.

高效机器学习算法与 KV-cache 压缩;OSCAR 与 CARE 项目贡献者。

  • Efficient ML Algorithm
Ryan Wang

Ryan Wang

Student Researcher

学生研究员

Efficient ML algorithms and speculative decoding for large-scale machine learning.

面向大规模机器学习的高效算法与投机解码。

  • Efficient ML Algorithm
  • Speculator
Yuqing Jian

Yuqing Jian

Student Researcher

学生研究员

Quantization-aware training for efficient, low-bit large language models.

面向高效低比特大语言模型的量化感知训练。

  • Quantization
  • Quantization-Aware Training
Jisen Li

Jisen Li

Student Researcher

学生研究员

Post-training quantization and KV-cache compression for efficient LLM serving; contributor to OSCAR.

面向高效 LLM 服务的训练后量化与 KV-cache 压缩;OSCAR 项目贡献者。

  • Post-Training Quantization
  • KV-Cache Quantization
Projects 项目

Open-source research

开源研究

Selected projects from the lab — open the preview page for details, papers, and code.

实验室的精选项目——点击进入可查看详情、论文与代码。

Contact 联系

Get in touch

联系我们

We welcome collaborators, prospective students, and contributors who care about efficient, open machine learning and systems.

我们欢迎关注高效、开放的机器学习与系统的合作者、有意申请的同学,以及开源贡献者。

Email the lab发邮件给我们 View our GitHub ↗访问我们的 GitHub ↗