"We always overestimate the change that will occur in the next two years and underestimate the change that will occur in the next ten. Don't let yourself be lulled into inaction."
- Bill Gates -
"We always overestimate the change that will occur in the next two years and underestimate the change that will occur in the next ten. Don't let yourself be lulled into inaction."
- Bill Gates -
Jinsung Jeon
I am currently a Visiting Scholar in the Dept. of Computer Science and Engineering at the University of California San Diego, where I am working with Prof. Julian McAuley. I received my Ph.D. from the Dept. of Artificial Intelligence at Yonsei University, South Korea, where I was advised by Prof. Noseong Park. I'm interested in applying the following keywords to real-world applications:
Generation models (Diffusion, GAN),
Neural Ordinary Differential Equations (Neural ODE),
Time-Series Tasks (Long-term Forecasting, Anomaly Detection) ,
Next Point of Interest,
Data Analytics + Decision Making.
Previously, I completed my undergraduate studies at Seoul National University of Science and Technology (2014-2020), where I majored in industrial engineering. During this time, I had the opportunity to be advised by Prof. Sangheum Hwang and Prof.Jae-Kyoung Ahn.
E-mail : jij014@ucsd.edu, jjsjjs0902@gmail.com
[NEW] (May 15, 2025) I was accepted one paper, titled "Generating Long Semantic IDs in Parallel for Recommendation" in KDD 2025.
[NEW] (Mar 25, 2025) I was accepted one paper, titled "A Geometric Diffusion Model for Macro Placement Generation" in Late Breaking Results @ DAC 2025.
[NEW] (Mar 5, 2025) I was accepted one paper, titled "Possibility for Proactive Anomaly Detection" in I Can't Believe It's Not Better: Challenges in Applied Deep Learning Workshop @ ICLR 2025.
(Sep 3, 2024) I participated as a visiting scholar in Julian McAuley's Lab at UCSD!
(June 7, 2024) I successfully completed my Ph.D thesis defense!
Thesis: Generative Models Empowered by Continuous Models: Focusing on Generative Adversarial Networks with Neural Ordinary Differential Equations
(May 28, 2024) I was selected for the NRF fellowship program (Overseas Track)!
(March 3, 2024) I was accepted one paper, titled "SPI-GAN: Denoising Diffusion GANs with Straight-Path Interpolations" in Practical ML for Low Resource Settings Workshop @ ICLR 2024.
University of California San Diego, San Diego, California, USA (Sep. 2024 - Present)
Visiting Scholar
Conducted research on improving data representation using LLMs
Yonsei University, Seoul, Republic of Korea (Mar. 2020 - Aug. 2024)
Ph.D. in Artificial Intelligence
Thesis: Generative Models Empowered by Continuous Models: Focusing on Generative Adversarial Networks with Neural Ordinary Differential Equations
GPA: 4.34/4.50
Seoul National University of Science and Technology, Seoul, Republic of Korea (Mar. 2014 - Feb. 2020)
B.S. in Industrial and Information Systems Engineering (minor. Computer Engineering)
GPA : 3.94/4.5
PAC-FNO: Parallel-Structured All-Component Fourier Neural Operators for Recognizing Low-Quality Images
Jinsung Jeon, Hyundong Jin, Sanghyun Hong, Jonghyun Choi, Dongeun Lee, Kookjin Lee, Noseong Park
The International Conference on Learning Representations (ICLR 2024)
GT-GAN: General Purpose Time Series Synthesis with Generative Adversarial Networks
Jinsung Jeon, JEONGHAK KIM, Haryong Song, Seunghyeon Cho, Noseong Park
2022 Conference on Neural Information Processing Systems (NeurIPs 2022)
LORD: Lower-Dimensional Embedding of Log-Signature in Neural Rough Differential Equations
Jaehoon Lee, Jinsung Jeon, Jihyeon Hyeong, Jayoung Kim, Minju Jo, Kook Seungji, Noseong Park
The International Conference on Learning Representations (ICLR 2021)
LightMove: A Lightweight Next-POI Recommendation forTaxicab Rooftop Advertising
Jinsung Jeon, Soyoung Kang, Minju Jo, Seunghyeon Cho, Noseong Park, Seonghoon Kim, Chiyoung Song
Proceedings of the 30th ACM International Conference on Information & Knowledge Management (CIKM 2021)
Oct-gan: Neural ode-based conditional tabular gans
Jayoung Kim, Jinsung Jeon, Jaehoon Lee, Jihyeon Hyeong, Noseong Park
Proceedings of the Web Conference 2021 (WWW 2021)
SAS Korea, Seoul, Republic of Korea(Jan. 2019 - Feb. 2019)
Intern in the 'Pre-Sales Support' department
Using AML(Anti-Money Laundering) program for anomaly detection
Postdoctoral Fellowship Program (Overseas Track)
National Research Foundation of Korea (2024)
Yonsei AI Workshop
"General Purpose Time Series Synthesis with Generative Adversarial Networks"
Best research paper (Machine learning)
16th SAS Analysis Championship
"Prediction of Traffic Accident Zone and Proposal for Transportation Safety"
Honorable mention