Publications

2024

  1. System-2 Reasoning via Generality and Adaptation
    Sejin Kim, and Sundong Kim
    In NeurIPS Workshop on System-2 Reasoning at Scale, 2024
  2. Reasoning Abilities of Large Language Models through the Lens of Abstraction and Reasoning (Extended Abstract)
    Seungpil Lee, Woochang Sim, Donghyeon Shin, Sejin Kim, and Sundong Kim
    In NeurIPS Workshop on System-2 Reasoning at Scale, 2024
  3. Addressing and Visualizing Misalignments in Human Task-Solving Trajectories
    Sejin Kim, Hosung Lee, and Sundong Kim
    arXiv:2409.14191, 2024
  4. From Generation to Selection: Findings of Converting Analogical Problem-Solving into Multiple-Choice Questions
    Donghyeon Shin, Seungpil Lee, Klea Lena Kovacec, and Sundong Kim
    In EMNLP Findings, 2024
  5. Abductive Symbolic Solver on Abstraction and Reasoning Corpus
    Mintaek Lim, Seokki Lee, Liyew Woletemaryam Abitew, and Sundong Kim
    In IJCAI Workshop on Logical Foundations of Neuro-Symbolic AI, 2024
  6. Enhancing Analogical Reasoning in the Abstraction and Reasoning Corpus via Model-Based RL
    Jihwan Lee, Woochang Sim, Sejin Kim, and Sundong Kim
    In IJCAI Workshop on the Interactions between Analogical Reasoning and Machine Learning, 2024
  7. Regulation Using Large Language Models to Generate Synthetic Data for Evaluating Analogical Ability
    Donghyeon Shin, Seungpil Lee, Klea Lena Kovacec, and Sundong Kim
    In IJCAI Workshop on Analogical Abstraction in Cognition, Perception, and Language, 2024
  8. O2ARC 3.0: A Platform for Solving and Creating ARC Tasks
    Suyeon Shim, Dohyun Ko, Hosung Lee, Seokki Lee, Doyoon Song, Sanha Hwang, Sejin Kim, and Sundong Kim
    In IJCAI (Demo track), 2024
  9. Reasoning Abilities of Large Language Models: In-Depth Analysis on the Abstraction and Reasoning Corpus
    Seungpil Lee, Woochang Sim, Donghyeon Shin, Wongyu Seo, Jiwon Park, Seokki Lee, Sanha Hwang, Sejin Kim, and Sundong Kim
    arXiv:2403.11793 (Under revision at ACM TIST), 2024
  10. ARCLE: The Abstraction and Reasoning Corpus Learning Environment for Reinforcement Learning
    Hosung Lee, Sejin Kim, Seungpil Lee, Sanha Hwang, Jihwan Lee, Byung-Jun Lee, and Sundong Kim
    In CoLLAs, 2024
  11. Explainable Product Classification for Customs
    Eunji Lee, Sihyeon Kim, Sundong Kim, Soyeon Jung, Heeja Kim, and Meeyoung Cha
    ACM Transactions on Intelligent Systems and Technology, 2024

2023

  1. Towards Attack-Tolerant Federated Learning via Critical Parameter Analysis
    Sungwon Han, Sungwon Park, Fangzhao WuSundong Kim, Bin Benjamin Zhu, Xing Xie, and Meeyoung Cha
    In ICCV, 2023
  2. Unraveling the ARC Puzzle: Mimicking Human Solutions with Object-Centric Decision Transformer
    Jaehyun Park, Jaegyun Im, Sanha Hwang, Mintaek Lim, Sabina Ualibekova, Sejin Kim, and Sundong Kim
    In ICML Workshop on Interactive Learning with Implicit Human Feedback, 2023
  3. FedDefender: Client-Side Attack-Tolerant Federated Learning
    Sungwon Park, Sungwon HanFangzhao WuSundong Kim, Bin Benjamin Zhu, Xing Xie, and Meeyoung Cha
    In KDD, 2023
  4. Customs Import Declaration Datasets
    Chaeyoon Jeong, Sundong Kim, Jaewoo Park, and Yeonsoo Choi
    In KDD Workshop on Machine Learning in Finance, 2023
  5. Machine Learning Driven Aid Classification for Sustainable Development
    Junho Lee, Hyeonho Song, Dongjoon Lee, Sundong Kim, Jisoo Sim, Meeyoung Cha, and Kyung-Ryul Park
    In IJCAI, 2023
  6. DualFair: Fair Representation Learning at Both Group and Individual Levels via Contrastive Self-supervision
    Sungwon Han, Seungeon Lee, Fangzhao WuSundong Kim, Chuhan Wu, Xing Xie, and Meeyoung Cha
    In TheWebConf, 2023

2022

  1. Playgrounds for Abstraction and Reasoning
    Subin Kim, Prin Phunyaphibarn, Donghyun Ahn, and Sundong Kim
    In NeurIPS Workshop on neuro Causal and Symbolic AI, 2022
  2. FedX: Unsupervised Federated Learning with Cross Knowledge Distillation
    Sungwon Han, Sungwon Park, Fangzhao WuSundong Kim, Chuhan Wu, Xing Xie, and Meeyoung Cha
    In ECCV, 2022
  3. Response to COVID-19 with Probabilistic Programming
    Assem ZhunisTung-Duong Mai, and Sundong Kim
    Frontiers in Public Health, 2022
  4. Coherence-based Label Propagation over Time Series for Accelerated Active Learning
    Yooju Shin, Susik Yoon, Sundong KimHwanjun SongJae-Gil Lee, and Byung Suk Lee
    In ICLR, 2022
  5. Active Learning for Human-in-the-Loop Customs Inspection
    Sundong KimTung-Duong MaiSungwon Han, Sungwon Park, Thi Nguyen Duc Khanh, Jaechan So, Karandeep Singh, and Meeyoung Cha
    IEEE Transactions on Knowledge and Data Engineering, 2022
  6. Knowledge Sharing via Domain Adaptation in Customs Fraud Detection
    Sungwon Park, Sundong Kim, and Meeyoung Cha
    In AAAI, 2022

2021

  1. Customs fraud detection in the presence of concept drift
    Tung-Duong Mai, Kien Hoang, Aitolkyn Baigutanova, Gaukhartas Alina, and Sundong Kim
    In ICDM IncrLearn Workshop, 2021
  2. Improving Unsupervised Image Clustering With Robust Learning
    Sungwon Park, Sungwon HanSundong Kim, Danu Kim, Sungkyu Park, Seunghoon Hong, and Meeyoung Cha
    In CVPR, 2021
  3. Disruption in the Chinese E-Commerce During COVID-19
    Yuan Yuan, Muzhi Guan, Zhilun Zhou, Sundong KimMeeyoung Cha, Depeng Jin, and Yong Li
    Frontiers in Computer Science, 2021
  4. Embedding Heterogeneous Hierarchical Structures
    Sundong Kim
    In IC2S2 (Extended Abstract), 2021

2020

  1. Ada-Boundary: Accelerating the DNN Training via Adaptive Boundary Batch Selection
    Hwanjun SongSundong Kim, Minseok Kim, and Jae-Gil Lee
    Machine Learning, 2020
  2. Carpe Diem, Seize the Samples Uncertain “At the Moment” for Adaptive Batch Selection
    Hwanjun Song, Minseok Kim, Sundong Kim, and Jae-Gil Lee
    In CIKM, 2020
  3. Mitigating Embedding and Class Assignment Mismatch in Unsupervised Image Classification
    Sungwon Han, Sungwon Park, Sungkyu ParkSundong Kim, and Meeyoung Cha
    In ECCV, 2020
  4. Revisit Prediction by Deep Survival Analysis
    Sundong KimHwanjun Song, Sejin Kim, Beomyoung Kim, and Jae-Gil Lee
    In PAKDD, 2020
  5. Neural User Embedding From Browsing Events
    Mingxiao An, and Sundong Kim
    In ECML-PKDD, 2020
  6. DATE: Dual Attentive Tree-aware Embedding for Customs Fraud Detection
    Sundong KimYu-Che TsaiKarandeep Singh, Yeonsoo Choi, Etim Ibok, Cheng-Te Li, and Meeyoung Cha
    In KDD, 2020

2019

  1. A Systemic Framework of Predicting Customer Revisit with In-Store Sensors
    Sundong Kim, and Jae-Gil Lee
    Knowledge and Information Systems, 2019

2018

  1. Utilizing In-Store Sensors for Revisit Prediction
    Sundong Kim, and Jae-Gil Lee
    In ICDM, 2018

2016

  1. Behavior of Self-Motivated Agents in Complex Networks
    Sundong Kim, and Jin-Jae Lee
    arXiv:1604.03747, 2016

2015

  1. Friend Recommendation with a Target User in Social Networking Services
    Sundong Kim
    In ICDE Workshop (Ph.D. Symposium), 2015

Domestic Journal

  • ARC 문제 해결을 위한 프롬프트 엔지니어링의 가능성
    (The Possibility of Prompt Engineering for ARC Problem Solving)
    Woochang Sim, Hyebin Jin, Sejin Kim, Sundong Kim
    KIISE Transactions on Computing Practices, Vol. 30, No. 2, Feb 2024.
    Shorter version: Presented at KSC 2023.
    [PDF]

  • 인지 및 추론 연구를 위한 테스트베드
    (Test Bed for Abstraction and Reasoning)
    Subin Kim, Prin Phunyaphibarn, Donghyun Ahn, Sundong Kim
    Journal of KIISE, Vol. 51, No. 1, Jan 2024.
    Shorter version: Presented at KSC 2022.
    [PDF]


Domestic Conference

  • ARCLE: 추상화 및 추론을 위한 강화학습 환경
    (ARCLE: Gymnasium Environment for Abstraction and Reasoning Corpus)
    Hosung Lee, Sejin Kim, Sundong Kim
    Korea Software Congress (KSC), 2023.
    (Selected as one of the best presentations in KSC 2023)
    [PDF] [Github]

  • 월드 모델을 이용한 ARC 문제의 사전 지식 평가
    (Evaluating Prior Knowledge of ARC Using World Models)
    Seungpil Lee, Jihwan Lee, Sundong Kim
    Korea Software Congress (KSC), 2023.
    [PDF] [Poster]

  • 월드모델을 통한 ARC의 핵심 지식 추출
    (Extracting the Core Knowledge of ARC with the World Model)
    Jihwan Lee, Seungpil Lee, Sejin Kim, Sundong Kim
    Korea Software Congress (KSC), 2023.
    [PDF]

  • 귀납 편향 제공을 위한 색채 어텐션 학습
    (Color Attention for Inductive Bias Provision)
    Jiwon Park, Hosung Lee, Jaehyun Park, Sundong Kim
    Korea Software Congress (KSC), 2023.
    (Selected as one of the best papers in KSC 2023)
    [PDF] [Poster]

  • 추상화 및 추론 문제 해결을 위한 대조학습
    (Using Contrastive Learning for Abstraction and Reasoning Task)
    Gyojoon Gu, Woochang Sim, Jaegyun Im, Sejin Kim, Sundong Kim
    Korea Software Congress (KSC), 2023.
    [PDF] [Poster]

  • 대형 언어 모델을 활용한 퓨샷 추론 문제의 데이터 증강
    (Augmenting Few-Shot Demonstrations with Large Language Model)
    Wongyu Seo, Woochang Sim, Sundong Kim
    Korea Software Congress (KSC), 2023.
    (Selected as one of the best presentations in KSC 2023)
    [PDF] [Github] [Poster]

  • 거대언어모델의 추론능력 평가를 위한 MC-LARC 데이터셋
    (MC-LARC Benchmark to Measure LLM Reasoning Capability)
    Donghyeon Shin, Sanha Hwang, Seokki Lee, Yunho Kim, Sundong Kim
    Korea Software Congress (KSC), 2023.
    [PDF] [Dataset] [Poster]

  • ARC 문제에서 그래프를 활용한 객체 탐지연구
    (Object Detection On The ARC Problem Using Graph Abstraction)
    Mintaek Lim, Sanha Hwang, Sabina Ualibekova, Sundong Kim
    Korea Computer Congress (KCC), 2023.
    [PDF] [Library]

  • 의사결정 트랜스포머를 사용한 추상화와 추론
    (Abstraction and Reasoning Challenge with Decision Transformer)
    Jaehyun Park, Jaegyun Im, Youngdo Lee, Donghyeon Shin, Sejin Kim, Sundong Kim
    Korea Computer Congress (KCC), 2023.
    [PDF] [ICMLW version]

  • ARC 문제 해결을 위한 프롬프트 엔지니어링의 가능성
    (Engineering Prompts for the ARC Challenge)
    Woochang Sim, Hyebin Jin, Sejin Kim, Sundong Kim
    Korea Computer Congress (KCC), 2023.
    (Selected as one of the best presentations in KCC 2023)
    Longer version: Published at KIISE Transactions on Computing Practices.
    [PDF]

  • 인지 및 추론 연구를 위한 Mini-ARC 벤치마크 데이터
    (Playgrounds for Abstraction and Reasoning)
    Subin Kim, Prin Phunyaphibarn, Donghyun Ahn, Sundong Kim
    Korea Software Congress (KSC), 2022.
    (Selected as one of the best papers in KSC 2022)
    Longer version: Published at Journal of KIISE.
    [PDF]

  • 텍스트와 이미지 데이터를 활용한 관세 품목 분류 모델 분석
    (Text and Image Data Analysis for Customs Item Classification)
    Sihyeon Kim, Eunji Lee, Sundong Kim, Meeyoung Cha
    Korea Computer Congress (KCC), 2022.
    [PDF]

  • 집단 공정성을 고려하는 자기 지도 대조 학습
    (Group-Wisely Fair Self-Supervised Contrastive Learning)
    Chaeyoon Jeong, Sungwon Han, Sundong Kim, Meeyoung Cha
    Korea Software Congress (KSC), 2021.
    [PDF]

  • Classification of Goods Using Text Descriptions With Sentences Retrieval
    Eunji Lee, Sundong Kim, Sihyun Kim, Sungwon Park, Meeyoung Cha, Soyeon Jung, Suyoung Yang, Yeonsoo Choi, Sungdae Ji, Minsoo Song, and Heeja Kim
    Korean Artificial Intelligence Association (KAIA), 2021.
    Longer version: ACM TIST 2023.
    [PDF] [TIST version]

  • 쇼핑몰 상품 카테고리 분류를 위한 Hyperbolic Interaction Model의 적용과 분석
    (Hyperbolic Interaction Model for Category Classification in E-Commerce)
    Sihyeon Kim, Eunji Lee, Sungwon Park, Meeyoung Cha, Sundong Kim
    Korea Computer Congress (KCC), 2021.
    [PDF] [Video]

  • 거시적 동선 정보에 기반한 고객 재방문 예측
    (Customer Revisit Prediction Using Macroscale Mobility Information)
    Beomyoung Kim, Sundong Kim, Sejin Kim, Jae-Gil Lee
    Korea Software Congress (KSC), 2019.
    [PDF] [Poster] [Technical Report] [Slides]

  • 과거 상황 정보의 변동 양상을 활용한 인간의 중단 가능성 예측 모델 연구
    (Exploiting Change Patterns of the Past Context Data on Human Interruptibility Prediction)
    Minsoo Choy, Minseo Kang, Minseok Kim, Sundong Kim
    Korea Computer Congress Winter Conference (KCC), 2017. (Best Paper Award)
    [Link] [PDF]

  • 와이파이 모니터링 기술로 센싱된 고객들의 매장 내부 이동 패턴들을 이용한 재방문 예측
    (Predicting Customer’s Revisit Intention Using Indoor Movements in Stores by Wi-Fi Monitoring)
    Sundong Kim, Jae-Gil Lee
    Korea Software Congress (KSC), 2016.
    [Link] [PDF]

  • 한국어 디비피디아의 자동 스키마 진화를 위한 방법
    (A Method of Automatic Schema Evolution on DBpedia Korea)
    Sundong Kim, Minseo Kang, Jae-Gil Lee
    Spring Conference of the Korea Information Processing Society (KIPS), 2014.
    [PDF] [Slides]


Thesis

  • Customer Revisit Prediction Using In-Store Sensor Data
    (매장 내 센서 데이터를 활용한 고객 재방문 예측)
    Sundong Kim
    Ph.D. dissertation, Industrial & Systems Engineering (Graduate School of Knowledge Service Engineering), KAIST, 2019.
    [PDF] [Slides]

  • Maximizing Influence over a Target User through Friend Recommendation
    (특정 사용자로의 영향력을 최대화하는 친구 추천 방법)
    Sundong Kim
    Master’s thesis, Industrial & Systems Engineering, KAIST, 2015.
    [PDF] [Slides]