profile photo

Xinle Cheng

 |  Research Interests  |  Publications  |  Contact  | 

Email: adacheng [at] stu [dot] pku [dot] edu [dot] cn

"Wir müssen wissen, wir werden wissen."  --David Hilbert

I'm an incoming CS Ph.D. student at Princeton University, advised by Prof. Ravi Netravali and Prof. Tri Dao. Previously, I completed my undergraduate studies in Computer Science at Peking University with honors, where I was fortunate to be advised by Prof. Di He and Prof. Liwei Wang.

I have the privilege of working with Prof. Zhihao Jia at CMU's Catalyst as a research intern in summer 2024.

Feel free to drop me an e-mail if you would like to connect!

 ~  Email  |  Google Scholar  |  GitHub  |  Twitter  ~ 


I am passionate about machine learning and systems.

• As for machine learning, I focus on Generative AI such as Large Language Models and Diffusion Models.

• As for systems, I am interested in building efficient and scalable systems for machine learning applications.

I am enthusiastic about contributing to the synergy between these fields.


Image FMap

Playing with Transformer at 30+ FPS via Next-Frame Diffusion
Xinle Cheng, Tianyu He†, Jiayi Xu, Junliang Guo, Di He, Jiang Bian (†project lead)
[paper][project page]

Image FMap

VidTok: A Family of Versatile and State-Of-The-Art Video Tokenizers
Anni Tang, Tianyu He†, Junliang Guo, Xinle Cheng, Li Song, Jiang Bian (†project lead)
[paper][code]

Image FMap

CAT Pruning: Cluster-Aware Token Pruning For Text-to-Image Diffusion Models
Xinle Cheng, Zhuoming Chen, Zhihao Jia
Neurips'24 Workshop AFM [paper][code]

Image FMap

Zero-Shot Image Feature Consensus with Deep Functional Maps
Xinle Cheng, Congyue Deng†, Adam Harley, Yixin Zhu†, Leonidas Guibas† (†corresponding author)
European Conference on Computer Vision (ECCV), 2024 [paper]

RTO

DPO Meets PPO: Reinforced Token Optimization for RLHF
Han Zhong*, Zikang Shan*, Guhao Feng*, Wei Xiong*, Xinle Cheng, Li Zhao, Di He, Jiang Bian, Liwei Wang (*equal contribution)
ICML'25 Spotlight [paper]


• Reviewer for ACL 2025, ICLR 2025, CVPR 2024-2025.

• Teaching Assistant for Introduction to Computer Systems (CSAPP) at Peking Univeristy, Fall 2024.


• Research Intern at Microsoft Research Asia, ML Group, Oct 2024 - June 2025.

• Research Intern at Catalyst, Carnegie Mellon University, Summer 2024.

• Research Intern at CoRe Lab, Peking University, Summer 2023.


I have a passion for enjoying delicious food and watching musicals. My current favorite musical is Sleep No More.


This template is a modification to Jon Barron's website.