About

I am a postdoc at Stanford CS working with Profs. Tatsu Hashimoto, Percy Liang, and James Zou. I did my PhD at MIT, where I was advised by Prof. Aleksander Mądry. Prior to that, I studied Computer Science at Cornell, where I was fortunate to work with Prof. Ramin Zabih and Prof. Bobby Kleinberg.

I’m broadly interested in the science of machine learning.

Recently, my interests have been in understanding and improving machine learning methodology through the lens of data:

• How do we attribute model predictions back to training data? (e.g., see our recent ICML tutorial [video] [notes])
• How do we select (and optimize) the right data for a given task?
• Can we derive insights about ML phenomena (e.g., scaling laws, emergence, optimization dynamics) through this lens?

 

Research

Selected | All

Attribute-to-Delete: Machine Unlearning via Datamodel Matching
Kristian Georgiev*, Roy Rinberg*, Sung Min Park*, Shivam Garg*, Andrew Ilyas, Aleksander Mądry, Seth Neel
ICLR 2025
[arxiv] [blog]

The Journey, Not the Destination: How Data Guides Diffusion Models
Kristian Georgiev*, Josh Vendrow*, Hadi Salman, Sung Min Park, Aleksander Mądry
[arxiv]

TRAK: Attributing Model Behavior at Scale
Sung Min Park*, Kristian Georgiev*, Andrew Ilyas*, Guillaume Leclerc, Aleksander Mądry
ICML 2023 (Oral presentation)
[arxiv] [blog][code] [website][talk]

ModelDiff: A Framework for Comparing Learning Algorithms
Harshay Shah*, Sung Min Park*, Andrew Ilyas*, Aleksander Mądry
ICML 2023
[arxiv] [blog][code]

FFCV: Accelerating Training by Removing Data Bottlenecks
Guillaume Leclerc, Andrew Ilyas, Logan Engstrom, Sung Min Park, Hadi Salman, Aleksander Mądry
CVPR 2023
[code]

A Data-Based Perspective on Transfer Learning
Saachi Jain*, Hadi Salman*, Alaa Khaddaj*, Eric Wong, Sung Min Park, Aleksander Mądry
CVPR 2023
[arxiv] [blog]

Datamodels: Predicting Predictions from Training Data
Andrew Ilyas*, Sung Min Park*, Logan Engstrom*, Guillaume Leclerc, Aleksander Mądry
ICML 2022
[arxiv] [blog part 1 part 2] [code][data]

On Distinctive Properties of Universal Perturbations
Sung Min Park, Kuo-An Wei, Kai Xiao, Jerry Li, Aleksander Mądry
2021
[arxiv]

Sparse PCA from Sparse Linear Regression
(α-β order) Guy Bresler, Sung Min Park, Madalina Persu
NeurIPS 2018
[arxiv] [poster] [code]

Structured learning of sum-of-submodular higher order energy functions
Alexander Fix, Thorsten Joachims, Sung Min Park, Ramin Zabih
ICCV 2013
[pdf]

 

Theses & Misc

Machine Learning through the Lens of Data
MIT, PhD thesis, 2024
[link]

On the Equivalence of Sparse Statistical Problems
MIT, SM thesis, 2016
[pdf]

Region Detection and Geometry Prediction
Patent from work during Summer 2020 internship at Waymo
[pdf]

Fourier Theoretic Probabilistic Inference over Permutations
Cornell, Spring 2014
[pdf]

Analysis of pipage method for k-max coverage
Cornell, Fall 2012
[pdf]

 

Talks

• Mar 2024 Stanford ML lunch
• Jul 2023 ICML Oral
• May 2023 LIDS & Stats Tea
• May 2023 MIT MLTea
• Apr 2023 ML Collective Reading group
• Feb 2023 MIT LIDS Student Conference
• Aug 2022 UMN ML Seminar
• Feb 2022 LIDS & Stats Tea
• Jan 2022 MIT LIDS Student Conference

 

Bio

Earlier in grad school, I worked on understanding statistical-computational tradeoffs in high-dimensional statistics with Prof. Guy Bresler for my SM thesis. During my PhD, I was partially supported by the MIT Akamai Presidential Fellowship and the Samsung Scholarship.

From 2016-18, I took a leave from grad school to serve in the Republic of Korea Army in the top signals intelligence unit as a researcher.

I have interned at Waymo, Dropbox, and Google.

 

Personal

I grew up between the Bay Area, Seoul, and Singapore, where I attended SAS.

In my free time, I enjoy working out, playing basketball, rowing, watching the NBA (nuggets!), watching movies, and learning theoretical physics and math.