Sejun Park

Assistant Professor, Korea University

Joined

March 2019

Names

Sejun Park (Preferred)

Emails

****@kaist.ac.kr (Confirmed)

****@vectorinstitute.ai (Confirmed)

****@gmail.com (Confirmed)

Personal Links

DBLP

Career & Education History

Assistant Professor

Korea University (korea.ac.kr)

Present

Advisors, Relations & Conflicts

No relations added

Expertise

No areas of expertise listed

Publications

Floating-Point Neural Networks Can Represent Almost All Floating-Point Functions
Geonho Hwang, Yeachan Park, Wonyeol Lee, Sejun Park
- ICML 2025 poster
- Readers: Everyone
Minimum Width for Universal Approximation using Squashable Activation Functions
Jonghyun Shin, Namjun Kim, Geonho Hwang, Sejun Park
- ICML 2025 poster
- Readers: Everyone
Minimum width for universal approximation using ReLU networks on compact domain
Namjun Kim, Chanho Min, Sejun Park
- ICLR 2024 poster
- Readers: Everyone
What does automatic differentiation compute for neural networks?
Sejun Park, Sanghyuk Chun, Wonyeol Lee
- ICLR 2024 spotlight
- Readers: Everyone
On the Correctness of Automatic Differentiation for Neural Networks with Machine-Representable Parameters
Wonyeol Lee, Sejun Park, Alex Aiken
- ICML 2023 Poster
- Readers: Everyone
Neural Networks Efficiently Learn Low-Dimensional Representations with SGD
Alireza Mousavi-Hosseini, Sejun Park, Manuela Girotti, Ioannis Mitliagkas, Murat A Erdogdu
- Published: 23 Nov 2022, Last Modified: 05 May 2023
- OPT 2022 Poster
- Readers: Everyone
Guiding Energy-based Models via Contrastive Latent Variables
Hankook Lee, Jongheon Jeong, Sejun Park, Jinwoo Shin
- Published: 01 Feb 2023, Last Modified: 14 Jan 2026
- ICLR 2023 notable top 25%
- Readers: Everyone
Neural Networks Efficiently Learn Low-Dimensional Representations with SGD
Alireza Mousavi-Hosseini, Sejun Park, Manuela Girotti, Ioannis Mitliagkas, Murat A Erdogdu
- Published: 01 Feb 2023, Last Modified: 14 Apr 2023
- ICLR 2023 notable top 25%
- Readers: Everyone
Generalization Bounds for Stochastic Gradient Descent via Localized $\varepsilon$-Covers
Sejun Park, Umut Simsekli, Murat A Erdogdu
- Published: 31 Oct 2022, Last Modified: 14 Jan 2023
- NeurIPS 2022 Accept
- Readers: Everyone
SmoothMix: Training Confidence-calibrated Smoothed Classifiers for Certified Adversarial Robustness
Jongheon Jeong, Sejun Park, Minkyu Kim, Heung-Chang Lee, Doguk Kim, Jinwoo Shin
- Published: 21 Jun 2021, Last Modified: 30 Dec 2025
- ICML 2021 Workshop AML Poster
- Readers: Everyone

View all 16 publications

Co-Authors

View all 26 co-authors