Sungjun Cho

Research Scientist, LG AI Research

sungjun.cho [AT] lgresearch.ai

Bio

Hello. I am a Research Scientist at the Advanced ML Lab of LG AI Research. My current research interests broadly include topics in machine learning, natural langauge processing, geometric deep learning, continual learning, machine unlearning, computational linguistics, and cognitive neuroscience.

I received my M.S. in Computer Science from Cornell University under the supervision of Prof. David Bindel and Prof. David Mimno. I also received my B.A. from Cornell in Computer Science and Mathematics.

Publications

My most up-to-date list of publications can be found in Google Scholar.
‡ indicates equal contribution.

3D Denoisers are Good 2D Teachers: Molecular Pretraining via Denoising and Cross-Modal Distillation

Sungjun Cho, Dae-Woong Jeong, Sung Moon Ko, Jinwoo Kim, Sehui Han, Seunghoon Hong, Honglak Lee, Moontae Lee

Preprint

Paper

Learning to Unlearn: Instance-wise Unlearning for Pre-trained Classifiers

Sungmin Cha‡, Sungjun Cho‡, Dasol Hwang‡, Honglak Lee, Taesup Moon, Moontae Lee

AAAI 2024

Paper

Using Spectral Characterization to Identify Healthcare-Associated Infection (HAI) Patients for Clinical Contact Precaution

Jiaming Cui‡, Sungjun Cho‡, Methun Kamruzzaman, Matthew Bielskas, Anil Vullikanti, B. Aditya Prakash

Scientific Reports 2023

Paper

Mixed-Curvature Transformers for Graph Representation Learning

Sungjun Cho, Seunghyuk Cho, Sungwoo Park, Hankook Lee, Honglak Lee, Moontae Lee

TAG-ML Workshop at ICML 2023

Paper

Rebalancing Batch Normalization for Exemplar-based Class-Incremental Learning

Sungmin Cha, Sungjun Cho, Dasol Hwang, Sunwon Hong, Moontae Lee, Taesup Moon

CVPR 2023

Paper

Grouping-matrix based Graph Pooling with Adaptive Number of Clusters

Sung Moon Ko, Sungjun Cho, Dae-Woong Jeong, Sehui Han, Moontae Lee, Honglak Lee

AAAI 2023

Paper

Transformers meet Stochastic Block Models: Attention with Data-Adaptive Sparsity and Cost

Sungjun Cho, Seonwoo Min, Jinwoo Kim, Moontae Lee, Honglak Lee, Seunghoon Hong

NeurIPS 2022

Paper

Pure Transformers are Powerful Graph Learners

Jinwoo Kim, Tien Dat Nguyen, Seonwoo Min, Sungjun Cho, Moontae Lee, Honglak Lee, Seunghoon Hong

NeurIPS 2022

Paper

Equivariant Hypergraph Neural Networks

Jinwoo Kim, Saeyoon Oh, Sungjun Cho, Seunghoon Hong

ECCV 2022

Paper

On-the-fly Rectification for Robust Large-Vocabulary Topic Inference

Moontae Lee, Sungjun Cho, Kun Dong, David Mimno, David Bindel

ICML 2021

Paper

Practical Correlated Topic Modeling and Analysis via the Rectified Anchor Word Algorithm

Moontae Lee, Sungjun Cho, David Bindel, David Mimno

EMNLP 2019

Paper

Vitæ

My full CV can be found in this PDF.

  • LG AI Research 2022 - now
    Research Scientist, Full-time
    Advanced ML Lab
  • LG AI Research 2021 - 2022
    Research Scientist, Intern
    Fundamental Research Lab
  • Georgia Tech 2020 - 2021
    Ph.D. Student (left in good standing)
    Computational Science & Engineering
  • Cornell University 2018 – 2020
    M.S. Student
    Computer Science
  • Cornell University 2011 - 2017
    B.A. Student
    Computer Science & Mathematics
Sungjun Cho
sungjun.cho [AT] lgresearch.ai