|
Publications
Work in Progress
The Interplay of Harness Design and Post-Training in LLM Agents
Kyungmin Kim*, Youngbin Choi*, Seoyeon Lee, Suhyeon Jun, Dongwoo Kim†, Sangdon Park†
RLxF at ICML 2026 Long Live the Librarian! A Persistent Search Sub-Agent for Energy-Efficient Multi-Agent Software Engineering Systems
Seunghyuk Cho, Sunghyun Choi, Jaeseung Heo, Youngbin Choi, Saemi Moon, MoonJeong Park, Dongwoo Kim
[arXiv] Concept Unlearning via Cross-Attention Activation Projection for Diffusion Models
Saemi Moon, Suhyeon Jun, Seoyeon Lee, Dongwoo Kim
AI4GOOD at ICML 2026 [arXiv] [Project] Interaction-Aware Influence Functions for Group Attribution
Jaeseung Heo, Kyeongheung Yun, Youngbin Choi, Sehyun Hwang, Jungseul Ok, Dongwoo Kim
MechInterp at ICML 2026 [arXiv] Transductive Generalization via Optimal Transport and Its Application to Graph Node Classification
MoonJeong Park*, Seungbeom Lee*, Kyungmin Kim, Jaeseung Heo, Seunghyuk Cho, Shouheng Li, Sangdon Park, Dongwoo Kim
[arXiv] In-Place Feedback: A New Paradigm for Guiding LLMs in Multi-Turn Reasoning
Youngbin Choi*, Minjong Lee*, Saemi Moon, Seunghyuk Cho, Chaehyeon Chung, MoonJeong Park, Dongwoo Kim
FoGen at ICML 2026 [arXiv] The Oversmoothing Fallacy: A Misguided Narrative in GNN Research
MoonJeong Park, Sunghyun Choi, Jaeseung Heo, Eunhyeok Park, Dongwoo Kim
[arXiv] Taming Gradient Oversmoothing and Expansion in Graph Neural Networks
Moonjeong Park, Dongwoo Kim
[arXiv]
2026
Representation-Centric Survey of Skeletal Action Recognition and the ANUBIS Benchmark
Yang Liu, Jiyao Yang, Madhawa Perera, Pan Ji, Dongwoo Kim, Min Xu, Tianyang Wang, Saeed Anwar, Tom Gedeon, Lei Wang, Zhenyue Qin
Pattern Recognition [arXiv] Training-free Composition of Pre-trained GFlowNets for Multi-Objective Generation
Seokwon Yoon, Youngbin Choi, Seunghyuk Cho, Seungbeom Lee, MoonJeong Park, Dongwoo Kim
ICML [arXiv] Plane Geometry Problem Solving with Multi-modal Reasoning: A Survey
Seunghyuk Cho, Zhenyue Qin, Yang Liu, Youngbin Choi, Seungbeom Lee, Dongwoo Kim
EACL Findings [arXiv] Exploring Iterative Controllable Summarization with Large Language Models
Sangwon Ryu, Heejin Do, Daehui Kim, Hwanjo Yu, Dongwoo Kim, Yunsu Kim, Gary Lee, Jungseul Ok
EACL Findings [arXiv] Posterior Label Smoothing for Node Classification
Jaeseung Heo, Moonjeong Park, Dongwoo Kim
AAAI (Oral) [arXiv]
2025
Influence Functions for Edge Edits in Non-Convex Graph Neural Networks
Jaeseung Heo, Kyeongheung Yun, Seokwon Yoon, MoonJeong Park, Jungseul Ok, Dongwoo Kim
NeurIPS [arXiv] High-order Equivariant Flow Matching for Density Functional Theory Hamiltonian Prediction
Seongsu Kim, Nayoung Kim, Dongwoo Kim, Sungsoo Ahn
NeurIPS (Spotlight) [arXiv] CoPL: Collaborative Preference Learning for Personalizing Large Language Models
Youngbin Choi, Seunghyuk Cho, Minjong Lee, MoonJeong Park, Yesong Ko, Jungseul Ok, Dongwoo Kim
EMNLP [arXiv] Retrieval-Augmented Generation with Estimation of Source Reliability
Jeongyeon Hwang, Junyoung Park, Hyejin Park, Dongwoo Kim, Sangdon Park, Jungseul Ok
EMNLP [arXiv] GeoDANO: Geometric VLM with Domain Agnostic Vision Encoder
Seunghyuk Cho, Zhenyue Qin, Yang Liu, Youngbin Choi, Seungbeom Lee, Dongwoo Kim
EMNLP Findings [arXiv] ChronoBias: A Benchmark for Evaluating Time-conditional Group Bias in the Time-sensitive Knowledge of Large Language Models
Kyungmin Kim, Youngbin Choi, Hyounghun Kim, Dongwoo Kim, Sangdon Park
EMNLP Findings [PDF] Holistic Unlearning Benchmark: A Multi-Faceted Evaluation for Text-to-Image Diffusion Model Unlearning
Saemi Moon*, Minjong Lee*, Sangdon Park, Dongwoo Kim
ICCV [arXiv] [Code] [Project] Delving into Instance-Dependent Label Noise in Graph Data: A Comprehensive Study and Benchmark
Suyeon Kim, SeongKu Kang, Dongwoo Kim, Jungseul Ok, Hwanjo Yu
KDD Datasets and Benchmarks [ACM] Enhancing Ligand Validity and Affinity in Structure-Based Drug Design with Multi-Reward Optimization
Seungbeom Lee*, Munsun Jo*, Jungseul Ok, Dongwoo Kim
ICML [PDF] Towards Bridging Generalization and Expressivity of Graph Neural Networks
Shouheng Li, Floris Geerts, Dongwoo Kim, Qing Wang
ICLR [arXiv]
In loving memory of our collaborator and friend, Qing.
2024
Mitigating over-smoothing through reverse process GNN for heterophilic graphs
MoonJeong Park, Jaeseung Heo, Dongwoo Kim
ICML [arXiv] EPIC: Graph Augmentation with Edit Path Interpolation via Learnable Cost
Jaeseung Heo*, Seungbeom Lee*, Sungsoo Ahn, Dongwoo Kim
IJCAI [arXiv] Few-shot unlearning
Youngsik Yoon*, Jinhwan Nam*, Jaeho Lee, Dongwoo Kim, Jungseul Ok
IEEE S&P [arXiv] [Code] Position-Sensing Graph Neural Networks: Proactively Learning Nodes Relative Positions
Zhenyue Qin, Saeed Anwar, Dongwoo Kim, Yang Liu, Pan Ji, Tom Gedeon
TNNLS [IEEE] Hierarchical Graph Generation with K2-trees
Yunhui Jang, Dongwoo Kim, Sungsoo Ahn
ICLR [arXiv] Feature Unlearning for Pre-trained GANs and VAEs
Saemi Moon, Seunghyuk Cho, Dongwoo Kim
AAAI [arXiv]
2023
Hyperbolic VAE via Latent Gaussian Distributions
Seunghyuk Cho, Juyong Lee, Dongwoo Kim
NeurIPS [arXiv] [Code] Test-time Embedding Normalization for Popularity Bias Mitigation
Dain Kim*, Jinhyeok Park*, Dongwoo Kim
CIKM Short Paper [arXiv] [Code] Robust Evaluation of Diffusion-Based Adversarial Purification
Minjong Lee, Dongwoo Kim
ICCV (Oral) [arXiv] [Code] Local Vertex Colouring Graph Neural Network
Shouheng Li, Dongwoo Kim, Qing Wang
ICML [OpenReview] Restructuring Graph for Higher Homophily via Learnable Spectral Clustering
Shouheng Li, Dongwoo Kim, Qing Wang
AAAI [arXiv] Anonymization for Skeleton Action Recognition
Saemi Moon*, Myeonghyeon Kim*, Zhenyue Qin, Yang Liu, Dongwoo Kim
AAAI [arXiv] [Code]
2022
A Rotated Hyperbolic Wrapped Normal Distribution for Hierarchical Representation Learning
Seunghyuk Cho, Juyong Lee, Jaesik Park, Dongwoo Kim
NeurIPS [arXiv] [Code] Fusing Higher-Order Features in Graph Neural Networks for Skeleton-Based Action Recognition
Zhenyue Qin, Yang Liu, Pan Ji, Dongwoo Kim, Lei Wang, Bob McKay, Saeed Anwar, Tom Gedeon
TNNLS [IEEE] MetaSSD: Meta-Learned Self-Supervised Detection
MoonJeong Park, Jungseul Ok, Yo-Seb Jeon, Dongwoo Kim
ISIT [arXiv] [Code] Robust Deep Learning from Crowds with Belief Propagation
Hoyoung Kim*, Seunghyuk Cho*, Dongwoo Kim, Jungseul Ok
AISTATS [arXiv] Item-based Variational Auto-encoder for Fair Music Recommendation
Jinhyeok Park*, Dain Kim*, Dongwoo Kim
CIKM EvalRS DataChallenge (Best Paper) [PDF]
2021
Beyond Low-Pass Filters: Adaptive Feature Propagation on Graphs
Sean Li, Dongwoo Kim, Qing Wang
ECML-PKDD [arXiv] Invertible Denoising Network: A Light Solution for Real Noise Removal
Yang Liu, Zhenyue Qin, Saeed Anwar, Pan Ji, Dongwoo Kim, Sabrina Caldwell, Tom Gedeon
CVPR [arXiv]
2019
Visualizing Graph Differences from Social Media Streams
Minjeong Shin, Dongwoo Kim, Umanga Bista, Jae Hee Lee, Lexing Xie
WSDM Demo Analysing user identity via time-sensitive semantic edit distance (t-SED): A case study of Russian trolls on Twitter
Dongwoo Kim, Timothy Graham, Zimin Wan, Marian Andrei Rizoiu
Journal of Computational Social Science [Link]
2018
Self-Bounded Prediction Suffix Tree via Approximate String Matching
Dongwoo Kim, Christian Walder
ICML [arXiv] Neural Dynamic Programming for Musical Self Similarity
Christian Walder, Dongwoo Kim
ICML [arXiv]
2017
Computer Assisted Composition with Recurrent Neural Networks
Christian Walder, Dongwoo Kim
ACML [arXiv] Joint Modeling of Topics, Citations, and Topical Authority in Academic Corpora
Jooyeon Kim, Dongwoo Kim, Alice Oh
TACL [PDF] Hierarchical Dirichlet Scaling Process
Dongwoo Kim, Alice Oh
Machine Learning Journal [Link]
2016
Probabilistic Knowledge Graph Construction: Compositional and Incremental Approaches
Dongwoo Kim, Lexing Xie, Cheng Soon Ong
CIKM [arXiv] Hierarchical learning of grids of microtopics
Nebojsa Jojic, Alessandro Perina, Dongwoo Kim
UAI [PDF]
2014
2013
2012
Modeling Topic Hierarchies with the Recursive Chinese Restaurant Process
Joon Hee Kim, Dongwoo Kim, Suin Kim, Alice Oh
CIKM [PDF] Dirichlet Process with Mixed Random Measures: A Nonparametric Topic Model for Labeled Data
Dongwoo Kim, Suin Kim, Alice Oh
ICML [PDF]
2011
Accounting for Data Dependencies within a Hierarchical Dirichlet Process Mixture Model
Dongwoo Kim, Alice Oh
CIKM [Link] Topic Chains for Understanding a News Corpus
Dongwoo Kim, Alice Oh
CICLING [Link]
2010
Analysis of Twitter Lists as a Potential Source for Discovering Latent Characteristics of Users
Dongwoo Kim, Yohan Jo, Il-Chul Moon, Alice Oh
CHI Workshop [PDF]
|