Shangyuan Tong
CS PhD at MIT CSAIL

Welcome! I am a final-year Ph.D. candidate in Computer Science at MIT CSAIL advised by Tommi Jaakkola.
My current research focuses on making generative models, especially diffusion models, both more efficient and more scalable. During my doctoral studies, I have had the opportunity to intern at the MIT-IBM Watson AI Lab. I also interned at Google DeepMind, where I was fortunate to be mentored by Saining Xie.
Before MIT, I earned my B.S. from UC San Diego with a double major in Computer Science and Applied Mathematics, graduating Summa Cum Laude (GPA 3.96/4.0). There, I was first introduced to the world of research by Lawrence Saul.
I am on the industry job market and am excited to apply my research expertise to solving real-world challenges.
Contact: sytong [at] csail [dot] mit [dot] edu
Recent News [all]
Apr 05, 2025 | Inference-Time Scaling for Diffusion Models is accepted to CVPR 2025 as a highlight paper! ![]() |
---|
Selected Publications [all]
- CVPRInference-Time Scaling for Diffusion Models beyond Scaling Denoising StepsIn Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (CVPR), 2025Highlight
- ICLRStable Target Field for Reduced Variance Score Estimation in Diffusion ModelsIn International Conference on Learning Representations (ICLR), 2023
- ICLRAdversarial Support AlignmentIn International Conference on Learning Representations (ICLR), 2022Spotlight