Xin Tan | Computer Science and Engineering, Chinese University of Hong Kong

About Me

I am now a PhD candidate @CUHK CSE, supervised by Prof. Henry Xu. Prior to this, I got my B.E from @NWPU CS in July, 2022.
I was born in Yangzhou, a historic and picturesque city in Jiangsu Province, China.

UPDATE: I will be on the job market in 2025 Fall. Please feel free to contact me!

Research Interests

I am broadly interested in system design for Machine Learning (MLSys), including the following topics:

Resource Scheduling: Maximize the allocation and utilization of available resources to accomodate workloads in the cluster.
ML Inference: Design highly effective and scalable systems capable of efficiently serving a large volume of requests.
Distributed Training: Develop and optimize strategies for efficient training of large models at scale.

News

[06/2025] DSV accepted to ACM ASPLOS’26.
[01/2025] Ayo accepted to ACM ASPLOS’25.
[06/2024] Arlo accepted to ACM ICPP’24.
[08/2022] Join CUHK CSE as a PhD student.

Publications

ASPLOS'26

DSV: Exploiting Dynamic Sparsity to Accelerate Large-Scale Video DiT Training

Xin Tan, Yuetao Chen, Yimin Jiang, Xing Chen, Kun Yan, Nan Duan, Yibo Zhu, Daxin Jiang, Hong Xu

ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS), 2026.

Arxiv
(Artifact Available, Functional, Reproduced)

ASPLOS'25

Towards End-to-End Optimization of LLM-based Applications with Ayo

Xin Tan, Yimin Jiang, Yitao Yang, Hong Xu

ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS), 2025.

PDF Arxiv Code

ICPP'24

Arlo: Serving Transformer-based Language Models with Dynamic Input Lengths

Xin Tan, Jiamin Li, Yitao Yang, Jingzong Li, Hong Xu

ACM International Conference on Parallel Processing (ICPP), 2024.

PDF

Education

	B.E: Northwestern Polytechnical University. Period: 2018.9 - 2022.6 Rank: 1/247
	Ph.D.: The Chinese University of Hong Kong. Period: 2022.8 - current