About
I am a postdoctoral researcher at Texas A&M University, working with Prof. Yang Shen. My research aims to build foundational models for biology and chemistry that understand and integrate multiple data modalities such as graphs and texts. The goal of my work is to accelerate scientific discovery by enabling AI systems to reason over complex relational and hierarchical structures found in biological, chemical, and biomedical domains.
During my Ph.D. at KAIST School of Computing, advised by Prof. Alice Oh, I studied representation learning for structured data, focusing on the intersection of graph neural networks (GNNs) and large language models (LLMs). My Ph.D. research contributed to graph representation learning methods that leverage pairwise and higher-order interactions for graph-structured data (edges [C2], partial subgraphs [C3], subgraphs [C4], and k-hop subgraphs [C6]).
Selected Publications (See all)
Dongkwan Kim and Alice Oh. "Generalizing Weisfeiler-Lehman Kernels to Subgraphs", International Conference on Learning Representations (ICLR), 2025
Dongkwan Kim and Alice Oh. "Translating Subgraphs to Nodes Makes Simple GNNs Strong and Efficient for Subgraph Representation Learning", International Conference on Machine Learning (ICML), 2024
Chani Jung, Dongkwan Kim, Jiho Jin, Jiseon Kim, Yeon Seonwoo, Yejin Choi, Alice Oh, and Hyunwoo Kim. "Perceptions to Beliefs: Exploring Precursory Inferences for Theory of Mind in Large Language Models", Empirical Methods in Natural Language Processing (EMNLP), 2024
Jiseon Kim, Dongkwan Kim, Joohye Jeong, Alice Oh, In Song Kim. "Measuring Interest Group Positions on Legislation: An AI-Driven Analysis of Lobbying Reports", Arxiv, 2025
Dongkwan Kim and Alice Oh. "How to Find Your Friendly Neighborhood: Graph Attention Design with Self-Supervision", International Conference on Learning Representations (ICLR), 2021
Education
- Ph.D., School of Computing, KAIST, Aug 2025
- M.S., School of Computing, KAIST, Aug 2019
- B.S., Major in Computer Science and Minor in Chemistry, KAIST, Feb 2018
Talks & Presentations
Dongkwan Kim. "Bridging Structural Data and Language Models for Scientific Discovery", SKKU AI Graduate School Seminar, 2026
Yining Yang, Zhiyan Song, Yuhan Zheng, Dongkwan Kim, Yiming Gao, Yihong Yang, Ruihong Huang, Yang Shen. "SwissProt-Evidence & Pannot-FG: Fine-Grained Evidence-Grounded Protein Function Annotation with Homology Shift", Texas NLP Symposium, 2026
Dongkwan Kim, Yiming Gao, Yining Yang, Yang Shen. "PerturbReason: A Knowledge-Grounded Benchmark for Cell-State–Conditioned Mechanistic Reasoning of Perturbation Effects", TMC AI Summit, 2026
Dongkwan Kim. "Graph Representation Learning with Local Structures, Higher Order Interactions, and Knowledge Augmentation", Shen-Lab @ TAMU, 2025
Dongkwan Kim, Junho Myung, Alice Oh. "Salad-Bowl-LLM: Multi-Culture LLMs by Mixed In-Context Demonstrations", International NLP Workshop at KAIST 2024, 2024
Dongkwan Kim. "Leveraging Structure for Graph Neural Networks", IBS Data Science Group Seminar, 2022
Dongkwan Kim and Alice Oh. "How to Find Your Friendly Neighborhood: Graph Attention Design with Self-Supervision", KAIST AI Workshop 21/22, 2022
Academic Services
- Reviewer: ICLR (2026, 2025, 2024, 2022, 2020), NeurIPS (2025, 2024, 2023, 2022), ACL ARR (2024/06, 2021/09), LoG (2023, 2022), ICML (2023), GLB Workshop (2023), GTRL Workshop (2022), GRL+ Workshop (2020)
- Student volunteer: NYU-KAIST Talk Series on LMs (2023), NeurIPS 2022 at KAIST (2022), ICLR (2021), ICLR Social ML in Korea (2020)
- Organizer: KAIST AI Workshop (21/22), International NLP Workshop at KAIST (2024)
- Contributor: KAIST ILP Tech (2022/03)
Teaching Experiences
- TA of AI Tech Boostcamp at NAVER Connect Foundation (Fall 2024)
- Head TA, TA of Machine Learning for Natural Language Processing (Spring 2021, Fall 2019), Best TA Award at Fall 2019
- Head TA of Deep Learning for Real-world Problems (Fall 2020, Spring 2020), Best TA Award at Spring 2020
- TA, Head TA of Data Structure (Fall 2018, Spring 2018)