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 second-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.
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 controllable generation), representation learning, computational sustainability and broad deep learning topics in general.
News
01/2024 | Two of our papers Manifold Preserving Guided Diffusion and Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion are accepted by ICLR 2024. |
---|---|
08/2023 | I am invited to give several talks at University of Tokyo and RIKEN about diffusion models and their controllable generation. |
06/2023 | I start my internship as a student research scientist at Sony. |
04/2023 | Our paper CSP: Self-Supervised Contrastive Spatial Pre-Training for Geospatial-Visual Representations is accepted by ICML 2023. |
04/2023 | I am invited to give a guest lecture talks at CMU 10707 about diffusion models and their applications. |
11/2022 | I am invited to give a guest lecture talks at CMU 10417 about diffusion models and their applications. |
09/2022 | Our paper SatMAE: Pre-training Transformers for Temporal and Multi-Spectral Satellite Imagery is accepted by NeurIPS 2022. |
08/2022 | I start my PhD in the Machine Learning Department, School of Computer Science at Carnegie Mellon University. |
07/2022 | Our paper Neural Generation Meets Real People: Building a Social, Informative Open-Domain Dialogue Agent is accepted by SIGDial 2022. |
04/2022 | Our paper Comparing Distributions by Measuring Differences that Affect Decision Making is awarded as an Outstanding Paper at ICLR 2022 (Top 7/4492). |
03/2022 | I graduate from Stanford University with a Master of Science in Computer Science with distinction in reasearch. |
01/2022 | Two of our papers Comparing Distributions by Measuring Differences that Affect Decision Making (oral presentation, top 1.6%) and SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations are accepted by ICLR 2022. |
01/2022 | I am TAing CS 228 in Winter 2022. If you are in the class, please feel free to come to my office hours! |
09/2021 | Our paper Spatial-Temporal Super-Resolution of Satellite Imagery via Conditional Pixel Synthesis is accepted by NeurIPS 2021. |
09/2021 | I am TAing CS 236 in Fall 2021. If you are in the class, please feel free to come to my office hours! |
08/2021 | Our team Chirpy Cardinal stands 2nd place in Alexa Prize 2021. |
06/2021 | I am an AI4ALL computer vision mentor in summer 2021 at Stanford. |
01/2021 | I am TAing CS 228 in Winter 2021. If you are in the class, please feel free to come to my office hours! |
09/2020 | I am awarded as a Siebel Scholar for Class of 2021. |
06/2020 | I start my internship as a machine learning engineer at Adobe Inc. . I am featured in one of the Adobe Intern Insider videos, check it out here. |
02/2020 | Our paper Fine-grained Image-to-Image Transformation towards Visual Recognition is accepted by CVPR 2020. |
09/2019 | I start my Master of Science program in computer science at Stanford University. |
05/2019 | I graduate from University of Rochester as a magna cum laude with double Bachelor of Science degrees in Data Science and Mathematics. |
Publications
- arXiv
- arXivTowards reporting bias in visual-language datasets: bimodal augmentation by decoupling object-attribute associationarXiv preprint 2023
- 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