Scholar
Minkyu Jeon
Google Scholar ID: kyQR6ecAAAAJ
Princeton University
Citations & Impact
Citations
92
H-index
4
i10-index
3
Publications
7
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- Two papers accepted at NeurIPS 2025 Machine Learning for Structural Biology (one poster and one oral presentation).
- Preprint released: R3eVision (Survey on Robust Rendering, Restoration, and Enhancement for 3D Low-Level Vision) in June 2025.
- Work on cryo-EM heterogeneous reconstruction datasets, benchmarks, and metrics accepted to NeurIPS 2024 (spotlight).
- Delivered an invited lecture on k-SALSA at CMU MetaMobility Lab in February 2024.
- Research on self-supervised representation learning for localization task accepted to Information Sciences Journal 2023.
- Saliency-guided point cloud data mixup work accepted to NeurIPS 2022.
- GAN-based approach to preserve the privacy of retina images accepted to ECCV 2022.
- Proposed a framework that learns to adaptively train each layer of deep neural networks via meta-learning, published in IEEE ACCESS 2021.
Research Experience
- Starting summer internship at Genentech's Prescient Design from June 2025.
- Pursuing Ph.D. journey at Princeton since September 2023.
- Held an Associate Computational Biologist role at the Broad Institute of MIT and Harvard from January to August 2023.
- Started as a visiting graduate student at the Broad Institute of MIT and Harvard in September 2021.
- Presented CryoBench paper at Flatiron Institute in August 2024.
- Gave an invited lecture on k-SALSA at CMU MetaMobility Lab in February 2024.
- Instructed high school students at AI4ALL Princeton in July 2024.
- Involved in multiple research projects including datasets, benchmarks, and metrics for heterogeneous reconstruction in cryo-EM; GAN-based approach to preserve the privacy of retina images; SageMix for point cloud mixup; and k-SALSA for synthesizing retinal images.
Education
- Ph.D. candidate in Computer Science at Princeton University under the guidance of Prof. Ellen D. Zhong.
Background
- Main research focuses on 3D reconstruction and generative models, particularly their applications to inverse problems in computer vision. Special emphasis is placed on scientific imaging modalities such as protein design and cryo-EM, leveraging generative approaches like diffusion and autoregressive models. Additionally, interested in developing methods to address the limitations of current machine learning models in generalizing beyond their training distributions.
Co-authors