Publications
Our research focuses on understanding and improving the reliability of deep learning systems, with an emphasis on information-theoretic analysis, tabular prediction, and practical machine learning applications.
Information-Theoretic Analysis
π Towards a Rigorous Analysis of Mutual Information in Contrastive Learning
Neural Networks (IF: 6.0), 2024
π A Benchmark Suite for Evaluating Neural Mutual Information Estimators on Unstructured Datasets
NeurIPS, 2024
π Statistical Characteristics of Deep Representations: An Empirical Investigation
International Conference on Artificial Neural Networks (ICANN), 2021
Tabular Prediction
π MultiTabPFN: Codebook-based Extensions of TabPFN for High-Class-Count Tabular Classification
Neural Networks (IF: 6.0, To Appear), 2026
π Range-limited Augmentation for Few-shot Learning in Tabular Data with Comprehensive Benchmark
KDD (Research Track), 2025
π Representation Space Augmentation for Effective Self-Supervised Learning on Tabular Data
AAAI, 2025
π AGATa: Attention-Guided Augmentation for Tabular Data in Contrastive Learning
NeurIPS Workshop on Table Representation Learning, 2024
π Binning as a Pretext Task: Improving Self-Supervised Learning in Tabular Domains
ICML, 2024
β³ MultiTab: A Comprehensive Benchmark Suite for Multi-Dimensional Evaluation in Tabular Domains
Under review, 2025
β³ Anomaly Detection Framework in Tabular Domains
Under review, 2025
β³ Enhancing Embedding Modules in Tabular Learning
Under review, 2025
Practical Applications
π Diffusion-based Semantic Outlier Generation via Nuisance Awareness for Out-of-Distribution Detection
AAAI, 2025
π Diffusion-based Semantic-Discrepant Outlier Generation for Out-of-Distribution Detection
NeurIPS Workshop on SyntheticData4ML, 2023
π DDP-GCN: Multi-graph Convolutional Network for Spatiotemporal Traffic Forecasting
Transportation Research Part C: Emerging Technologies (IF: 9.02), 2022
π Short-term Traffic Prediction with Deep Neural Networks: A Survey
IEEE Access (IF: 3.37), 2021
π Defining Virtual Control Group to Improve Customer Baseline Load Calculation of Residential Demand Response
Applied Energy (IF: 8.85), 2019
π Assuring Explainability on Demand Response Targeting via Credit Scoring
Energy (IF: 6.23), 2018
π Extended TAM Analysis of a Residential DR Pilot Program
Journal of the HCI Society of Korea (KCI), 2017
π Role of Demand Response in Small Power Consumer Market and a Pilot Study
Journal of the Korean Institute of Communications and Information Sciences (KCI), 2017
π λ₯λ¬λ λͺ¨λΈμ νμ©ν κ΅ν΅ νΌμ‘λ μμΈ‘ λ° Geometric λ₯λ¬λ λͺ¨λΈμ νμ©λ°©μ
νκ΅κ²½μκ³Όνν νμ λνλ
Όλ¬Έμ§, 2018
π λ₯λ¬λ μ μ©μ ν΅ν 곡μ νΌμ‘λ λ° λ¦¬μ€ν¬ λͺ¨λΈλ§
νκ΅κ²½μκ³Όνν νμ λνλ
Όλ¬Έμ§ (KCI), 2017