Hyunjin Seo

Hyunjin Seo

I am a Ph.D. student at Machine Learning and Intelligence Lab (MLILAB) at KAIST, under the supervision of Prof. Eunho Yang. My primary research focuses on the practical applications of geometric deep learning. This includes relation-guided multimodal understanding, where I integrate large language models/vision-language models with geometric deep learning to enhance their reasoning capabilities across diverse data modalities. Additionally, I have developed data and model pruning techniques to address the computational challenges associated with training large-scale graphs, maximizing the utility of deep learning for structured data. My research also extends into the domain of chemistry and materials informatics, where I am designing an AI-based framework for polymer representation learning.

NEWS


Oct. 2024 🎁  New paper, "ReBind: Enhancing Ground-state Molecular Conformation Prediction via Force-Based Graph Rewiring", released on arXiv
May. 2024 🎁  New paper, "Unleashing the Potential of Text-attributed Graphs: Automatic Relation Decomposition via Large Language Models", released on arXiv
May. 2024 🛫  ICLR '24 @ Vienna, Austria
Jan. 2024 🎀  Paper accepted at ICLR '24
Jul. 2023 🎀  Paper accepted at ICCV '23
Mar. 2023 🙌  Became a new member at MLILAB

PUBLICATIONS


ReBind: Enhancing Ground-state Molecular Conformation Prediction via Force-Based Graph Rewiring

Taewon Kim*, Hyunjin Seo*, Sungsoo Ahn, Eunho Yang (*: equal contribution)

Preprint  paper

Unleashing the Potential of Text-attributed Graphs: Automatic Relation Decomposition via Large Language Models

Hyunjin Seo*, Taewon Kim*, June Yong Yang, Eunho Yang (*: equal contribution)

Preprint  paper

TEDDY: Trimming Edges with Degree-based Discrimination strategY

Hyunjin Seo*, Jihun Yun*, Eunho Yang (*: equal contribution)

ICLR 2024  paper

PC-Adapter: Topology-Aware Adapter for Efficient Domain Adaption on Point Clouds with Rectified Pseudo Label

Joonhyung Park, Hyunjin Seo, Eunho Yang

ICCV 2023  paper

Efficient Subword Segmentation for Korean Language Classification

Hyunjin Seo*, Jeongjae Nam*, Minseok Kim* (*: equal contribution)

HCLT 2022

Analysis and Utilization of Hypergraph Neural Networks

Hyunjin Seo, Seongjun Yun, Jaewoo Kang

KCC 2021 (Recipient of the Best Undergraduate Award)  paper

Towards Precise Prediction Uncertainty in GNNs: Refining GNNs with Topology-grouping Strategy

Hyunjin Seo, Kyusung Seo*, Joonhyung Park*, Eunho Yang (*: equal contribution)

Under Review

Relation-aware Pseudo-labeling for Link Prediction with Graph Neural Networks

Hyunjin Seo*, Seongjun Yun*, Buru Chang, Jaewoo Kang (*: equal contribution)  paper

Under Review

EDUCATION


KAIST Logo

Korea Advanced Institute of Science and Technology (KAIST)

2023.02 - Present

  • M.S. & Ph.D. integrated student
  • Kim Jaechul Graduate School of Artificial Intelligence
KU Logo

Korea University

2018.02 - 2022.08

  • Bachelor’s degree
  • History, Artificial Intelligence (Double Major)

EXPERIENCE


AI Research Intern

2024.10 - Present

Teaching Assistant

2023.09 - 2023.12, 2024.03 - 2024.06

  • Machine Learning for Artificial Intelligence (KAIST)

Research Intern at Machine Learning and Intelligence Lab (MLILAB), KAIST

2022.04 - 2023.02

Research Intern at Data Mining and Information Systems Lab (DMIS), Korea University

2021.01 - 2022.02

PROJECTS


Molecular Property Prediction via Denoising-based Graph Neural Networks

2024.02 - Present

Samsung Electronics

Predicting Food Product Satisfaction using Large Language Models

2023.05 - 2023.11

LAB-EAT

AWARDS


Recipient of the Best Undergraduate Award

2021

Korea Computer Congress (KCC)

Top 2.7%

Great Honors Award

2019, 2020, 2021

Korea University

SERVICES


Conference Reviewer

  • International Conference on Learning Representations (ICLR)