Yutong (Kelly) He 何雨桐
Contact: yutonghe [at] cs [dot] cmu [dot] edu
PhD Student @ MLD, SCS, CMU
yutonghe [at] cs [dot] cmu [dot] edu
I am a forth-year PhD student in the Machine Learning Department, School of Computer Science at Carnegie Mellon University, advised by Prof. Zico Kolter and Prof. Ruslan Salakhutdinov. During my PhD, I have interned at Sony AI working with Naoki Murata and Yuki Mitsufuji, and Meta FAIR working with Ricky Chen.
Before coming to CMU, I was a master’s student at Stanford Computer Science with distinction in research. I was advised by Prof. Stefano Ermon, and closely worked with Prof. Christopher Manning, Prof. David Lobell and Prof. Marshall Burke. I completed my B.S in Mathematics and B.S. in Data Science with highest distinction at University of Rochester, where I worked with Prof. Henry Kautz and Prof. Jiebo Luo.
I was selected as a Siebel Scholar and a Xerox Engineering Research Fellow. I was also awarded an Outstanding Paper Award at ICLR 2022 and Doris Ermine Smith Award for Achievement in Mathematics.
My research interests include generative models, more specifically diffusion models and flow matching related topics, and how to properly use them in broader contexts.
News
09/2025 | Two of our papers Accelerating Diffusion Models in Offline RL via Reward-Aware Consistency Trajectory Distillation and Blind Inverse Problem Solving Made Easy by Text-to-Image Latent Diffusion are accepted by NeurIPS 2025 SPIGM & ALERT workshop. |
---|---|
07/2025 | Our papers Towards Reporting Bias in Visual-Language Datasets: Bi-modal Data Augmentation by Decoupling Object-Attribute Association is accepted by ICCV 2025 MRR workshop. |
05/2025 | I started my internship as a student research scientist at Meta FAIR. |
Publications
- NeurIPS
Workshop Accelerating Diffusion Models in Offline RL via Reward-Aware Consistency Trajectory DistillationIn SPIGM & ALERT @ NeurIPS 2025 - arXivState combinatorial generalization in decision making with conditional diffusion modelsarXiv preprint 2025
- arXiv
- ICMLCSP: Self-Supervised Contrastive Spatial Pre-Training for Geospatial-Visual RepresentationsIn International Conference on Machine Learning (ICML) 2023
- SIGSPATIALUnderstanding Economic Development in Rural Africa using Satellite Imagery, Building footprints and Deep ModelsIn International Conference on Advances in Geographic Information Systems (ACM SIGSPATIAL) 2022
- NeurIPS
Workshop Tracking Urbanization in Developing Regions with Remote Sensing Spatial-Temporal Super-ResolutionIn Neural Information Processing Systems (NeurIPS) workshop on Machine Learning for the Developing World (ML4D) 2021 - arXiv