Shangyuan Tong

Hi, welcome! I am a final-year Ph.D. candidate in Computer Science at MIT CSAIL advised by Tommi Jaakkola. I am also fortunate to work closely with Saining Xie.

My current research interests broadly lie in generative models, focusing on pushing the boundaries of both scalability and efficiency. During my doctoral studies, I have interned at the MIT-IBM Watson AI Lab and Google DeepMind.

Before MIT, I earned my B.S. from UC San Diego with a double major in Computer Science and Applied Mathematics (Summa Cum Laude, GPA 3.96/4.0), where I was introduced to the world of research by Lawrence Saul.

I am currently on the industry job market!

Contact: sytong [at] csail [dot] mit [dot] edu

Recent News [all]

Nov 24, 2025	Checkout our new paper Flow Map Distillation Without Data!
Sep 18, 2025	Next Semantic Scale Prediction via Hierarchical Diffusion Language Models is accepted to NeurIPS 2025! See you in San Diego!
Apr 05, 2025	Inference-Time Scaling for Diffusion Models is accepted to CVPR 2025 as a highlight paper!

Selected Publications [all]

arXiv

Flow Map Distillation Without Data

Shangyuan Tong^*, Nanye Ma^*, Saining Xie, and Tommi Jaakkola

arXiv preprint arXiv:2511.19428, 2025
CVPR

Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps

Nanye Ma^*, Shangyuan Tong^*, Haolin Jia, Hexiang Hu, Yu-Chuan Su, Mingda Zhang, Xuan Yang, Yandong Li, Tommi Jaakkola, Xuhui Jia, and Saining Xie

In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (CVPR), 2025

Highlight

Highlight
ICLR

Stable Target Field for Reduced Variance Score Estimation in Diffusion Models

Yilun Xu^*, Shangyuan Tong^*, and Tommi Jaakkola

In International Conference on Learning Representations (ICLR), 2023
ICLR

Adversarial Support Alignment

Shangyuan Tong^*, Timur Garipov^*, Yang Zhang, Shiyu Chang, and Tommi Jaakkola

In International Conference on Learning Representations (ICLR), 2022

Spotlight

Spotlight