Minkyu Jeon

Hello! I'm a Ph.D. candidate in Computer Science at Princeton University, advised by Prof. Ellen D. Zhong, and a part-time research intern at Prescient Design (Frontier Research).

My main research focuses on 3D reconstruction and generative models, particularly their applications to inverse problems in computer vision. I place special emphasis on scientific imaging modalities such as protein design and cryo-EM, leveraging generative approaches like diffusion and autoregressive model. Furthermore, I am interested in developing methods to address the limitations of current machine learning models in generalizing beyond their training distributions.

Email  /  CV  /  Google Scholar  /  Twitter  /  LinkedIn

Activities

• 11-2025:  Started my part-time research internship at Prescient Design (Genentech).
• 10-2025:  Two papers got accepted at NeurIPS 2025 Machine Learning for Structural Biology (1 poster and 1 Oral).
• 06-2025:  Excited to begin my summer internship at Genentech's Prescient Design.
1
• 06-2025:  A preprint released; Checkout R3eVision (Survey on Robust Rendering, Restoration, and Enhancement for 3D Low-Level Vision).
• 05-2025:  I passed the general exam. Now I'm a PhD candidate!
• 09-2024:  Our work on cryo-EM heterogeneous reconstruction datasets, benchmarks, and metrics has been accepted to NeurIPS2024 (spotlight).
• 08-2024:  I present my CryoBench paper at Flatiron Institute.
• 07-2024:  Instructed high school students at AI4ALL Princeton.
• 02-2024:  I gave an invited lecture on k-SALSA at CMU MetaMobility Lab.
• 09-2023:  Starting my Ph.D journey at Princeton!
• 01-2023:  Starting an Associate Computational Biologist role at the Broad Institute of MIT and Harvard.
• 11-2022:  Our work on self-supervised representation learning for localization task has been accepted to Information Science Journal 2023.
• 09-2022:  Our work on saliency-guided point cloud data mixup has been accepted to NeurIPS2022.
• 07-2022:  Our work on GAN-based approach to preserve the privacy of retina images has been accepted to ECCV2022.
• 09-2021:  Starting as a visiting graduate student at the Broad Institute of MIT and Harvard.

Research

*: co-first author

We propose CryoBench, a suite of datasets, metrics, and performance benchmarks for heterogeneous reconstruction in cryo-EM.

We propose a simple and effective self-supervised learning method that uses the positional relationships between the entities in an image by shuffling the convolution kernels.

We propose SageMix, a saliency-guided Mixup for point clouds to preserve salient local structures. We extract salient regions from two point clouds and smoothly combine them into one continuous shape.

We presented an end-to-end pipeline for synthesizing a k-anonymous retinal image dataset given a private input dataset. We leverage local style alignment, our new approach for summarizing source images in a cluster while preserving local texture information.

We propose a general framework that learns to adaptively train each layer of deep neural networks via meta-learning. Our framework leverages the local error signals from layers and identifies which layer needs to be trained more at every iteration.

Teaching

Credit: Jon Baron.