|
Jinwoo Kim jinwoo-kim [at] kaist.ac.kr I am a Ph.D. student at KAIST advised by Seunghoon Hong. My name 진우 眞友 is pronounced [jeen-oo] in Korean. I am interested in making current deep learning models generalize better out of their training data. I have been studying this problem primarily in the context of geometric deep learning, focusing on making general neural networks such as vision and language models behave predictably when they encounter novel, transformed inputs. For this I often use tools from theories of graphs, (semi)groups and manifolds, and Markov processes such as random walks, diffusions and flows. CV / Google Scholar / GitHub / X / LinkedIn |
|
Experience
New York University
LG AI Research |
Selected Publications
|
|
Flock: A Knowledge Graph Foundation Model via Learning on Random Walks
Jinwoo Kim*, Xingyue Huang*, Krzysztof Olejniczak, Kyungbin Min, Michael Bronstein, Seunghoon Hong, İsmail İlkan Ceylan Preprint, 2025 paper / code |
|
Sequence Modeling with Spectral Mean Flows
Jinwoo Kim, Max Beier, Petar Bevanda, Nayun Kim, Seunghoon Hong NeurIPS, 2025 paper / code |
|
Revisiting Random Walks for
Learning on Graphs
Jinwoo Kim, Olga Zaghen*, Ayhan Suleymanzade*, Youngmin Ryou, Seunghoon Hong ICLR, 2025 Spotlight Presentation; ICML GRaM Workshop, 2024 paper / code / poster |
|
Learning Probabilistic
Symmetrization for Architecture Agnostic
Equivariance
Jinwoo Kim, Tien Dat Nguyen, Ayhan Suleymanzade, Hyeokjun An, Seunghoon Hong NeurIPS, 2023 Spotlight Presentation paper / code / poster / slides / extended slides |
|
Universal Few-shot Learning
of Dense Prediction Tasks with Visual Token Matching
Donggyun Kim, Jinwoo Kim, Seongwoong Cho, Chong Luo, Seunghoon Hong ICLR, 2023 Outstanding Paper Award paper / code |
|
Pure Transformers are
Powerful
Graph Learners
Jinwoo Kim, Tien Dat Nguyen, Seonwoo Min, Sungjun Cho, Moontae Lee, Honglak Lee, Seunghoon Hong NeurIPS, 2022 paper / code / talk / poster / slides / extended slides |
Full Publications
|
|
Inverting Data Transformations via Diffusion Sampling
Jinwoo Kim*, Sékou-Oumar Kaba*, Jiyun Park, Seunghoon Hong, Siamak Ravanbakhsh Under review, 2025 |
|
Flock: A Knowledge Graph Foundation Model via Learning on Random Walks
Jinwoo Kim*, Xingyue Huang*, Krzysztof Olejniczak, Kyungbin Min, Michael Bronstein, Seunghoon Hong, İsmail İlkan Ceylan Preprint, 2025 paper / code |
|
Sequence Modeling with Spectral Mean Flows
Jinwoo Kim, Max Beier, Petar Bevanda, Nayun Kim, Seunghoon Hong NeurIPS, 2025 paper / code |
|
Revisiting Random Walks for
Learning on Graphs
Jinwoo Kim, Olga Zaghen*, Ayhan Suleymanzade*, Youngmin Ryou, Seunghoon Hong ICLR, 2025 Spotlight Presentation (380/11672=3.26%); ICML GRaM Workshop, 2024 paper / code / poster |
|
3D Denoisers are Good 2D
Teachers: Molecular Pretraining via Denoising and
Cross-Modal Distillation
Sungjun Cho, Dae-Woong Jeong, Sung Moon Ko, Jinwoo Kim, Sehui Han, Seunghoon Hong, Honglak Lee, Moontae Lee AAAI, 2025 Oral Presentation paper |
|
Simulation-Free Training of
Neural ODEs on Paired Data
Semin Kim*, Jaehoon Yoo*, Jinwoo Kim, Yeonwoo Cha, Saehoon Kim, Seunghoon Hong NeurIPS, 2024 paper / code |
|
Learning Symmetrization for
Equivariance with Orbit Distance Minimization
Tien Dat Nguyen*, Jinwoo Kim*, Hongseok Yang, Seunghoon Hong NeurIPS NeurReps Workshop, 2023 paper / code / poster |
|
Learning Probabilistic
Symmetrization for Architecture Agnostic
Equivariance
Jinwoo Kim, Tien Dat Nguyen, Ayhan Suleymanzade, Hyeokjun An, Seunghoon Hong NeurIPS, 2023 Spotlight Presentation (378/12345=3.06%) paper / code / poster / slides / extended slides |
|
Universal Few-shot Learning
of
Dense Prediction Tasks with Visual Token
Matching
Donggyun Kim, Jinwoo Kim, Seongwoong Cho, Chong Luo, Seunghoon Hong ICLR, 2023 Outstanding Paper Award (4/4955=0.08%) paper / code |
|
Pure Transformers are
Powerful
Graph Learners
Jinwoo Kim, Tien Dat Nguyen, Seonwoo Min, Sungjun Cho, Moontae Lee, Honglak Lee, Seunghoon Hong NeurIPS, 2022 paper / code / talk / poster / slides / extended slides |
|
Transformers Meet Stochastic
Block Models: Attention with Data-Adaptive Sparsity
and Cost
Sungjun Cho, Seonwoo Min, Jinwoo Kim, Moontae Lee, Honglak Lee, Seunghoon Hong NeurIPS, 2022 paper / code / poster |
|
Equivariant Hypergraph Neural
Networks
Jinwoo Kim, Saeyoon Oh, Sungjun Cho, Seunghoon Hong ECCV, 2022 paper / code / poster / slides |
|
Transformers Generalize
DeepSets and Can be Extended to Graphs and
Hypergraphs
Jinwoo Kim, Saeyoon Oh, Seunghoon Hong NeurIPS, 2021 paper / code / poster / slides |
|
SetVAE: Learning Hierarchical
Composition for Generative Modeling of
Set-Structured
Data
Jinwoo Kim*, Jaehoon Yoo*, Juho Lee, Seunghoon Hong CVPR, 2021 paper / code / project page / poster / slides |
|
Spontaneous Retinal Waves Can
Generate Long-Range Horizontal Connectivity in
Visual
Cortex
Jinwoo Kim*, Min Song*, Jaeson Jang, Se-Bum Paik The Journal of Neuroscience 40(34), 2020 paper |
Honors
Outstanding Researcher Award,
KAIST-Mila Prefrontal AI Research Center, 2024 |
Invited Talks
Extrinsic Symmetries for Neural Networks
Universal Few-shot Learning of Dense
Prediction
Tasks with Visual Token Matching
Pure Transformers are Powerful Graph
Learners
Transformers Generalize DeepSets and Can be
Extended to Graphs and Hypergraphs
SetVAE: Learning Hierarchical Composition for
Generative Modeling of Set-Structured Data
Spontaneous Retinal Waves Can Generate
Long-Range Horizontal Connectivity in Visual
Cortex |
Academic Services
Conference Reviewer, AISTATS 2025–2026,
ICLR 2025–2026, NeurIPS 2022–2025, ICML 2023–2025,
IJCNN 2025, LoG 2022–2025, ICCV 2025 SP4V Workshop,
ICML 2024 GRaM Workshop, CVPR 2022, ACCV 2022
|
Teaching
Teaching Assistant, Computer Vision
(CS576), Spring 2022 / 2023 |
MusicI love listening to and making music! My favorite musicians include Lamp, Radiohead, and Ryuichi Sakamoto. Below are some of my original compositions: |
|
|
I occasionally post music stuff on my blog. |
|
|
Built from Jon Barron's academic website |