Hello, I'm Jaehoon Lee.
Hello, I'm Jaehoon Lee.
Contact me: jaehoon.lee@lgresearch.ai
Embedded Files
I am currently working at LG AI Research as a Research Scientist under the leadership of Wonbin Ahn and Soonyoung Lee. My research specializes in time series forecasting. At LG AI Research, I focus on building foundation models for large-scale time series data and improving forecasting performance through the integration of LLMs and multimodal learning. My research interests also extend to explainable AI (xAI) for trustworthy forecasting systems. Currently, I am applying these technologies to the financial domain, with the goal of generating high-quality investment signals through accurate forecasting and providing more reliable and interpretable decision-making via explainability.
Publication
Publication
Cross-RAG: Zero-Shot Retrieval-Augmented Time Series Forecasting via Cross-Attention [arxiv]
Seunghan Lee, Jaehoon Lee, Jun Seo, Sungdong Yoo, Minjae Kim, Tae Yoon Lim, Dongwan Kang, Hwanil Choi, SoonYoung Lee, Wonbin Ahn
2026, Arxiv(Preprint)
FinSTaR: Towards Financial Reasoning with Time Series Reasoning Models [arxiv]
Seunghan Lee, Jun Seo, Jaehoon Lee, Sungdong Yoo, Minjae Kim, Tae Yoon Lim, Dongwan Kang, Hwanil Choi, Soonyoung Lee, Wonbin Ahn
2026, Arxiv(Preprint)
FinTexTS: Financial Text-Paired Time-Series Dataset via Semantic-Based and Multi-Level Pairing [arxiv]
Jaehoon Lee, Suhwan Park, Tae Yoon Lim, Seunghan Lee, Jun Seo, Dongwan Kang, Hwanil Choi, Minjae Kim, Sungdong Yoo, SoonYoung Lee, Yongjae Lee, Wonbin Ahn
2026, Arxiv(Preprint)
Rethinking Multimodal Fusion for Time Series: Auxiliary Modalities Need Constrained Fusion [arxiv]
Seunghan Lee, Jun Seo, Jaehoon Lee, Sungdong Yoo, Minjae Kim, Tae Yoon Lim, Dongwan Kang, Hwanil Choi, SoonYoung Lee, Wonbin Ahn
2026, Arxiv(Preprint)
Partial-Multivariate Model for Forecasting [arxiv]
Jaehoon Lee, Hankook Lee, Sungik Choi, Sungjun Cho, Montae Lee
2024, Arxiv(Preprint)
FrAug: Enhanced Fraud Detection in Interbank Transfers via Augmented Account Features [IEEE]
Seonkyu Lim*, Jeongwhan Choi*, Jaehoon Lee*, Noseong Park
2024, ICAIF Workshop (Foundation Models for Time Series: Exploring New Frontiers) [openreview]
2025 IEEE International Conference on Big Data and Smart Computing (BigComp)
HyperNetwork Approximating Future Parameters for Time Series Forecasting under Temporal Drifts [arxiv]
Jaehoon Lee, Chan Kim, Gyumin Lee, Haksoo Lim, Jeongwhan Choi, Kookjin Lee, Dongeun Lee, Sanghyun Hong and Noseong Park
2023, Neurips 2023 Workshop (DistShift)
Precursor-of-Anomaly Detection for Irregular Time Series [arxiv]
Sheo Yon Jhin, Jaehoon Lee, Noseong Park
2023, 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)
MadSGM: Multivariate Anomaly Detection with Score-based Generative Modelsular Time Series [arxiv]
Haksoo Lim, Sewon Park, Minjung Kim, Jaehoon Lee, Seonkyu Lim, Noseong Park
2023, Conference on Information and Knowledge Management (CIKM)
EXIT: Extrapolation and Interpolation-based Neural Controlled Differential Equations for Time-series Classification and Forecasting [arxiv][pdf]
Sheo Yon Jhin, Jaehoon Lee, Minju Jo, Seungji Kook, Jinsung Jeon, Jihyeon Hyeong, Jayoung Kim and Noseong Park
2022, World Wide Web Conference(WWW)
LORD: Lower-Dimensional Embedding of Log-Signature in Neural Rough Differential Equations [openreview][arxiv][github]
Jaehoon Lee, Jinsung Jeon, Sheo yon Jhin, Jihyeon Hyeong, Jayoung Kim, Minju Jo, Kook Seungji, Noseong Park
2022, International Conference on Learning Representations(ICLR)
A high average review score of 7.5, ranked 116/3328
Invertible Tabular GANs: Killing Two Birds with One Stone for Tabular Data Synthesis [openreview][arxiv][neurips proceedings][github]
Jaehoon Lee*, Jihyeon Hyeong*, Jinsung Jeon, Noseong Park, Jihoon Cho
2021, Advances in Neural Information Processing Systems(NeurIPS)
Supported by Samsung SDS
OCT-GAN: Neural ODE-based Conditional Tabular GANs [arxiv]
Jayoung Kim, Jinsung Jeon, Jaehoon Lee, Jihyeon Hyeong, Noseong Park
2021, World Wide Web Conference(WWW)
Scalable Graph Synthesis with Adj and 1 — Adj [pdf]
Jinsung Jeon, Jing Liu, Jayoung Kim, Jaehoon Lee, Noseong Park, Jamie Jooyeon Lee, Ozlem Uzuner, and Sushil Jajodia
2021, SIAM International Conference on Data Mining (SDM)
Services
Services
Reviewer: I served as reviewers in ICML, NeurIPS, ICLR, SDM, KDD, AAAI, and AISTATS from 2023
Area Chair: NeurIPS (2024, 2026)
Page updated
Google Sites
Report abuse