Compiled on November 14, 2026
조판일: 2026년 11월 14일
WONJAE (DAN) KIM / 김원재
INDUSTRY EXPERIENCE
경력
TwelveLabs South KoreaFeb. 2025 - present
TwelveLabs 대한민국2025년 2월 - 현재
Director of ResearchNov. 2026 - present
Director of Research2026년 11월 - 현재
Lead research and productization across TwelveLabs’ model families.
TwelveLabs의 여러 모델 패밀리의 연구와 제품화를 이끕니다.
ML Research ManagerAug. 2026 - Nov. 2026
ML Research Manager2026년 8월 - 2026년 11월
Set the research direction that separates video structure from semantics, which produced the
temporal segmentation model in Marengo 3.5.
영상의 구조와 의미를 나누는 연구 방향을 세웠고, 이 방향에서 Marengo 3.5의 시간 분할 모델이 나왔습니다.
Grew team leads into owners of priorities and resourcing, and wrote research editorials that set a
shared technical direction for video embedding, search and AI-assisted research.
팀 리드들이 우선순위와 자원 배분을 직접 맡도록 키웠고, 영상 임베딩, 검색, AI 보조 연구의 기술 방향을 함께 잡는 연구 글을 썼습니다.
Lead ML Research ScientistFeb. 2025 - Aug. 2026
Lead ML Research Scientist2025년 2월 - 2026년 8월
Led the Marengo & Search team, building multimodal embeddings and video search systems.
Launched the video embedding research pillar and hired its researchers and engineering manager.
Marengo & Search 팀을 이끌며 멀티모달 임베딩과 영상 검색 시스템을 만들었습니다. 영상 임베딩 연구 분야를 새로 열고, 연구원과 엔지니어링 매니저를 채용해 팀을 꾸렸습니다.
Naver South KoreaApr. 2021 - Feb. 2025
Naver 대한민국2021년 4월 - 2025년 2월
Research Scientist @ Naver AI Lab
One team throughout; the legal entity changed from Naver to Naver Cloud in Jan. 2023.
한 팀에서 계속 일했고, 2023년 1월 소속 법인이 Naver에서 Naver Cloud로 바뀌었습니다.
HYPE (ECCV 2024 Oral, first author): hyperbolic entailment filtering of underspecified image-text
pairs.
HYPE(ECCV 2024 Oral, 제1저자): 쌍곡 함의(entailment) 필터링으로 내용이 구체적이지 않은 이미지-텍스트 쌍을 걸러냅니다.
ProLIP (ICLR 2025): probabilistic vision-language pre-training on a billion-scale image-text dataset.
ProLIP(ICLR 2025): 10억 규모의 이미지-텍스트 데이터셋으로 하는 확률적 비전-언어 사전학습입니다.
CompoDiff (TMLR 2024) and a language-only training method (CVPR 2024) for composed image
retrieval.
CompoDiff(TMLR 2024)와 언어만으로 학습하는 방법(CVPR 2024), 모두 합성 질의 검색 연구입니다.
ViDT (ICLR 2022): a fully transformer-based object detector that extends the Swin Transformer.
ViDT(ICLR 2022): Swin Transformer를 확장해 만든, 완전한 트랜스포머 기반 객체 검출기입니다.
ECCV Caption (ECCV 2022): corrects false negatives in MS-COCO caption matching with verified
annotations.
ECCV Caption(ECCV 2022): 검증된 주석으로 MS-COCO 캡션 매칭의 거짓 음성(false negative)을 바로잡았습니다.
Kakao South KoreaFeb. 2018 - Apr. 2021
Kakao 대한민국2018년 2월 - 2021년 4월
Research Scientist @ AI Technology Team
One team throughout; the legal entity changed from Kakao to Kakao Enterprise in Mar. 2021.
한 팀에서 계속 일했고, 2021년 3월 소속 법인이 Kakao에서 Kakao Enterprise로 바뀌었습니다.
ViLT (ICML 2021, Long Presentation, co-first author): vision-and-language transformer without
convolution or region supervision, now part of Hugging Face Transformers.
ViLT(ICML 2021, Long Presentation, 공동 제1저자): 합성곱과 영역 지도 없이 만든 비전-언어 트랜스포머로, 현재 Hugging Face Transformers에 포함되어 있습니다.
Learning Dynamics of Attention (NeurIPS 2019): regularizes attention-based visual reasoning by
modeling it as a continuous dynamical system with neural ordinary differential equations.
Learning Dynamics of Attention(NeurIPS 2019): 어텐션 기반 시각 추론을 신경 상미분방정식으로 연속 동역학계처럼 모델링해 규제합니다.
Naver LABS South KoreaJun. 2017 - Sep. 2017
Naver LABS 대한민국2017년 6월 - 2017년 9월
Research Intern @ Intelligence Team, Mentor: Hyeonseob Nam
Research Intern @ Intelligence Team, 멘토: Hyeonseob Nam
SELECTED MODELS AND RELEASES
주요 모델과 릴리스
Research and technical direction, TwelveLabs
연구·기술 방향 총괄, TwelveLabs
Embedding model separating video structure from meaning, incl. visual docs; with MRL, 512 dims beat Gemini
Embedding 2’s 3,072 dims.
구조와 의미를 나눈 임베딩 모델로 시각 문서까지 다루며, MRL 512차원이 Gemini Embedding 2의 3,072차원을 앞섭니다.
Research and technical direction, TwelveLabs
연구·기술 방향 총괄, TwelveLabs
Unified multimodal embedding model with composed search and sports understanding, launched on Amazon
Bedrock; training-stage optimization shortened development cycles.
통합 멀티모달 임베딩 모델로, 합성 질의 검색과 스포츠 이해를 갖추고 Amazon Bedrock에 출시했으며, 학습 단계 최적화로 개발 주기를 줄였습니다.
ViLT2021
Co-first author
공동 제1저자
Efficient vision-and-language transformer, now part of Hugging Face Transformers. Its VQA checkpoint was
the library’s default visual question answering model and has been downloaded more than 6 million times.
효율적인 비전-언어 트랜스포머로, 현재 Hugging Face Transformers에 포함되어 있습니다. VQA 모델은 이 라이브러리의 시각 질의응답 기본 모델이었고, 내려받기가 600만 회를 넘었습니다.
PUBLICATIONS
논문
PEER-REVIEWED PAPERS
심사를 거친 논문
19. Jaeseok Byun, Seokhyeon Jeong, Wonjae Kim, Sanghyuk Chun, Taesup Moon. “An Efficient Post-hoc Framework for Reducing Task Discrepancy of Text Encoders for Composed Image Retrieval” . 20th International Conference on Computer Vision (ICCV 2025)
18. Sanghyuk Chun, Wonjae Kim, Song Park, Sangdoo Yun. “Probabilistic Language-Image Pre-Training” . 13th International Conference on Learning Representations (ICLR 2025)
17. JeongYeon Nam, Jinbae Im, Wonjae Kim, Taeho Kil. “Extract Free Dense Misalignment from CLIP” . 39th AAAI Conference on Artificial Intelligence (AAAI 2025)
16. Wonjae Kim, Sanghyuk Chun, Taekyung Kim, Dongyoon Han, Sangdoo Yun. “HYPE: Hyperbolic Entailment Filtering for Underspecified Images and Texts” . 18th European Conference on Computer Vision (ECCV 2024, Oral Presentation, Oral Presentation Acceptance Rate: 2.3%)
15. Geonmo Gu*, Sanghyuk Chun*, Wonjae Kim, HeeJae Jun, Yoohoon Kang, Sangdoo Yun. “CompoDiff: Versatile Composed Image Retrieval With Latent Diffusion” . Transactions on Machine Learning Research (TMLR 2024)
14. Jaewoo Lee*, Jaehong Yoon*, Wonjae Kim, Yunji Kim, Sung Ju Hwang. “STELLA: Continual Audio-Video Pre-training with Spatio-Temporal Localized Alignment”. 41st International Conference on Machine Learning (ICML 2024)
13. Geonmo Gu*, Sanghyuk Chun*, Wonjae Kim, Yoohoon Kang, Sangdoo Yun. “Language-only Efficient Training of Zero-shot Composed Image Retrieval” . 41st Conference on Computer Vision and Pattern Recognition (CVPR 2024)
12. Hyungyung Lee, Da Young Lee, Wonjae Kim, Jin-Hwa Kim, Tackeun Kim, Jihang Kim, Leonard Sunwoo, Edward Choi. “Vision-Language Generative Model for View-Specific Chest X-ray Generation” . The 5th Annual Conference on Health, Inference, and Learning (CHIL 2024)
11. Song Park*, Sanghyuk Chun*, Byeongho Heo, Wonjae Kim, Sangdoo Yun. “SeiT: Storage-Efficient Vision Training with Tokens Using 1% of Pixel Storage”. 19th International Conference on Computer Vision (ICCV 2023)
10. Kyuyong Shin*, Hanock Kwak*, Wonjae Kim, Jisu Jeong, Seungjae Jung, Kyung-Min Kim, Jung-Woo Ha, Sang-Woo Lee. “Pivotal Role of Language Modeling in Recommender Systems: Enriching Task-specific and Task-agnostic Representation Learning” . 60th Annual Meeting of the Association for Computational Linguistics (ACL 2023)
9. Namuk Park, Wonjae Kim, Byeongho Heo, Taekyung Kim, Sangdoo Yun. “What Do Self-Supervised Vision Transformers Learn?” . 11th International Conference on Learning Representations (ICLR 2023)
8. Jong Hak Moon, Wonjae Kim, Edward Choi. “Correlation between Alignment-Uniformity and Performance of Dense Contrastive Representations” . 33rd British Machine Vision Conference (BMVC 2022)
7. Sanghyuk Chun, Wonjae Kim, Song Park, Minsuk Chang, Seong Joon Oh. “ECCV Caption: Correcting False Negatives by Collecting Machine-and-Human-verified Image-Caption Associations for MS-COCO” . 17th European Conference on Computer Vision (ECCV 2022)
6. Hee-Seung Moon, Seungwon Do, Wonjae Kim, Jiwon Seo, Minsuk Chang, Byungjoo Lee. “Speeding up Inference with User Simulators through Policy Modulation” . 40th Conference on Human Factors in Computing Systems (CHI 2022)
5. Yoonho Lee, Wonjae Kim, Wonpyo Park, Seungjin Choi. “Discrete Infomax Codes for Supervised Representation Learning” . Entropy special issue “Theory and Applications of Information Processing Algorithms” , 2022
4. Hwanjun Song, Deqing Sun, Sanghyuk Chun, Varun Jampani, Dongyoon Han, Byeongho Heo, Wonjae Kim, Ming-Hsuan Yang. “ViDT: An Efficient and Effective Fully Transformer-based Object Detector” . 10th International Conference on Learning Representations (ICLR 2022)
3. Wonjae Kim*, Bokyung Son*, Ildoo Kim. “ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision”. 38th International Conference on Machine Learning (ICML 2021, Long Presentation, Long Presentation Acceptance Rate: 3.0%)
2. Wonjae Kim, Yoonho Lee. “Learning Dynamics of Attention: Human Prior for Interpretable Machine Reasoning” . 32nd Conference on Neural Information Processing Systems (NeurIPS 2019)
1. Daekyoung Jung, Wonjae Kim, Hyunjoo Song, Jeong-in Hwang, Bongshin Lee, Bohyoung Kim, Jinwook Seo. “Chartsense: Interactive data extraction from chart images” . 35th Conference on Human Factors in Computing Systems (CHI 2017)
PREPRINTS AND WORKSHOP PAPERS
프리프린트 및 워크숍 논문
8. Jaeyoo Park, Sanghyuk Chun, Wonjae Kim, Sangdoo Yun, Bohyung Han. “Emergence of Text Readability in Vision Language Models”. 42nd Conference on Computer Vision and Pattern Recognition (CVPR 2025, 2nd Workshop on Emergent Visual Abilities and Limits of Foundation Models)
7. Geonmo Gu*, Sanghyuk Chun*, Wonjae Kim, HeeJae Jun, Yoohoon Kang, Sangdoo Yun. “CompoDiff: Versatile Composed Image Retrieval With Latent Diffusion”. 41st Conference on Computer Vision and Pattern Recognition (CVPR 2024, Workshop on Synthetic Data for Computer Vision)
6. Seokhyeon Park*, Wonjae Kim*, Young-Ho Kim, Jinwook Seo. “Computational Approaches for App-to-App Retrieval and Design Consistency Check”. 40th International Conference on Machine Learning (ICML 2023, Workshop on Artificial Intelligence & Human Computer Interaction)
5. Byungsoo Ko, Han-Gyu Kim, Byeongho Heo, Sangdoo Yun, Sanghyuk Chun, Geonmo Gu, Wonjae Kim. “Group Generalized Mean Pooling for Vision Transformer” .
4. Hwanjun Song, Deqing Sun, Sanghyuk Chun, Varun Jampani, Dongyoon Han, Byeongho Heo, Wonjae Kim, Ming-Hsuan Yang. “An Extendable, Efficient and Effective Transformer-based Object Detector” .
3. Jiyoung Lee, Wonjae Kim, Daehoon Gwak, Edward Choi. “Conditional Generation of Periodic Signals with Fourier-Based Decoder” . 34th Conference on Neural Information Processing Systems (NeurIPS 2021, Workshop on Deep Generative Models and Downstream Applications Poster Presentation)
2. Wonpyo Park*, Wonjae Kim*, Kihyun You, Minsu Cho. “Diversified Mutual Learning for Deep Metric Learning” . 15th European Conference on Computer Vision (ECCV 2020, Task-CV Workshop)
1. Jaemin Jo, Wonjae Kim, Seunghoon Yoo, Bohyoung Kim, Jinwook Seo. “Swifttuna: Responsive and incremental visual exploration of large-scale multidimensional data”. 10th IEEE Pacific Visualization Symposium (PacificVis 2017)
EDUCATION
학력
Seoul National University, M.S. South KoreaFeb. 2018
서울대학교 석사(M.S.) 대한민국2018년 2월
Department of Computer Science and Engineering, Advisor: Jinwook Seo
컴퓨터공학부, 지도교수: Jinwook Seo
Seoul National University, B.S. South KoreaFeb. 2016
서울대학교 학사(B.S.) 대한민국2016년 2월
Department of Computer Science and Engineering
컴퓨터공학부
ACADEMIC SERVICE
학술 활동
REVIEWER리뷰어
Venue학회20202021202220232024202520262027
ICML34242
ICLR325135
Blogposts Track2
NeurIPS572162
ImageNet workshopImageNet 워크숍2
AAAI664
CVPR6624*4
ICCV44
ECCV64
TMLR1221
CHI11
UIST1

Numbers are papers reviewed that year. * Outstanding Reviewer, CVPR 2025.숫자는 그해 심사한 논문 수, *는 CVPR 2025 우수 리뷰어(Outstanding Reviewer) 선정입니다.

Compiled on November 14, 2026WONJAE (DAN) KIM / 김원재contact@wonjae.kim dandelin wonjae.kim wjk Wonjae KimINDUSTRY EXPERIENCETwelveLabs South KoreaFeb. 2025 - presentDirector of ResearchNov. 2026 - presentLead research and productization across TwelveLabs’ model families.ML Research ManagerAug. 2026 - Nov. 2026Set the research direction that separates video structure from semantics, which produced thetemporal segmentation model in Marengo 3.5.Grew team leads into owners of priorities and resourcing, and wrote research editorials that set ashared technical direction for video embedding, search and AI-assisted research.Lead ML Research ScientistFeb. 2025 - Aug. 2026Led the Marengo & Search team, building multimodal embeddings and video search systems.Launched the video embedding research pillar and hired its researchers and engineering manager.Naver South KoreaApr. 2021 - Feb. 2025Research Scientist @ Naver AI LabOne team throughout; the legal entity changed from Naver to Naver Cloud in Jan. 2023.HYPE (ECCV 2024 Oral, first author): hyperbolic entailment filtering of underspecified image-textpairs.ProLIP (ICLR 2025): probabilistic vision-language pre-training on a billion-scale image-text dataset.CompoDiff (TMLR 2024) and a language-only training method (CVPR 2024) for composed imageretrieval.ViDT (ICLR 2022): a fully transformer-based object detector that extends the Swin Transformer.ECCV Caption (ECCV 2022): corrects false negatives in MS-COCO caption matching with verifiedannotations.Kakao South KoreaFeb. 2018 - Apr. 2021Research Scientist @ AI Technology TeamOne team throughout; the legal entity changed from Kakao to Kakao Enterprise in Mar. 2021.ViLT (ICML 2021, Long Presentation, co-first author): vision-and-language transformer withoutconvolution or region supervision, now part of Hugging Face Transformers.Learning Dynamics of Attention (NeurIPS 2019): regularizes attention-based visual reasoning bymodeling it as a continuous dynamical system with neural ordinary differential equations.Naver LABS South KoreaJun. 2017 - Sep. 2017Research Intern @ Intelligence Team, Mentor: Hyeonseob NamSELECTED MODELS AND RELEASESMarengo 3.52026Research and technical direction, TwelveLabsEmbedding model separating video structure from meaning, incl. visual docs; with MRL, 512 dims beat GeminiEmbedding 2’s 3,072 dims.Marengo 3.02025Research and technical direction, TwelveLabsUnified multimodal embedding model with composed search and sports understanding, launched on AmazonBedrock; training-stage optimization shortened development cycles.1
ViLT2021Co-first authorEfficient vision-and-language transformer, now part of Hugging Face Transformers. Its VQA checkpoint wasthe library’s default visual question answering model and has been downloaded more than 6 million times.PUBLICATIONSPEER-REVIEWED PAPERS19. Jaeseok Byun, Seokhyeon Jeong, Wonjae Kim, Sanghyuk Chun, Taesup Moon. “An Efficient Post-hocFramework for Reducing Task Discrepancy of Text Encoders for Composed Image Retrieval” . 20th Inter-national Conference on Computer Vision (ICCV 2025)18. Sanghyuk Chun, Wonjae Kim, Song Park, Sangdoo Yun. “Probabilistic Language-Image Pre-Training” .13th International Conference on Learning Representations (ICLR 2025)17. JeongYeon Nam, Jinbae Im, Wonjae Kim, Taeho Kil. “Extract Free Dense Misalignment from CLIP” . 39thAAAI Conference on Artificial Intelligence (AAAI 2025)16. Wonjae Kim, Sanghyuk Chun, Taekyung Kim, Dongyoon Han, Sangdoo Yun. “HYPE: Hyperbolic EntailmentFiltering for Underspecified Images and Texts” . 18th European Conference on Computer Vision (ECCV2024, Oral Presentation, Oral Presentation Acceptance Rate: 2.3%)15. Geonmo Gu*, Sanghyuk Chun*, Wonjae Kim, HeeJae Jun, Yoohoon Kang, Sangdoo Yun. “CompoDiff:Versatile Composed Image Retrieval With Latent Diffusion” . Transactions on Machine Learning Research(TMLR 2024)14. Jaewoo Lee*, Jaehong Yoon*, Wonjae Kim, Yunji Kim, Sung Ju Hwang. “STELLA: Continual Audio-VideoPre-training with Spatio-Temporal Localized Alignment”. 41st International Conference on Machine Learn-ing (ICML 2024)13. Geonmo Gu*, Sanghyuk Chun*, Wonjae Kim, Yoohoon Kang, Sangdoo Yun. “Language-only Efficient Train-ing of Zero-shot Composed Image Retrieval” . 41st Conference on Computer Vision and Pattern Recogni-tion (CVPR 2024)12. Hyungyung Lee, Da Young Lee, Wonjae Kim, Jin-Hwa Kim, Tackeun Kim, Jihang Kim, Leonard Sunwoo,Edward Choi. “Vision-Language Generative Model for View-Specific Chest X-ray Generation” . The 5thAnnual Conference on Health, Inference, and Learning (CHIL 2024)11. Song Park*, Sanghyuk Chun*, Byeongho Heo, Wonjae Kim, Sangdoo Yun. “SeiT: Storage-Efficient VisionTraining with Tokens Using 1% of Pixel Storage”. 19th International Conference on Computer Vision (ICCV2023)10. Kyuyong Shin*, Hanock Kwak*, Wonjae Kim, Jisu Jeong, Seungjae Jung, Kyung-Min Kim, Jung-Woo Ha,Sang-Woo Lee. “Pivotal Role of Language Modeling in Recommender Systems: Enriching Task-specificand Task-agnostic Representation Learning” . 60th Annual Meeting of the Association for ComputationalLinguistics (ACL 2023)9. Namuk Park, Wonjae Kim, Byeongho Heo, Taekyung Kim, Sangdoo Yun. “What Do Self-Supervised VisionTransformers Learn?” . 11th International Conference on Learning Representations (ICLR 2023)8. Jong Hak Moon, Wonjae Kim, Edward Choi. “Correlation between Alignment-Uniformity and Performanceof Dense Contrastive Representations” . 33rd British Machine Vision Conference (BMVC 2022)7. Sanghyuk Chun, Wonjae Kim, Song Park, Minsuk Chang, Seong Joon Oh. “ECCV Caption: Correcting FalseNegatives by Collecting Machine-and-Human-verified Image-Caption Associations for MS-COCO” . 17thEuropean Conference on Computer Vision (ECCV 2022)6. Hee-Seung Moon, Seungwon Do, Wonjae Kim, Jiwon Seo, Minsuk Chang, Byungjoo Lee. “Speeding upInference with User Simulators through Policy Modulation” . 40th Conference on Human Factors in Com-puting Systems (CHI 2022)2
5. Yoonho Lee, Wonjae Kim, Wonpyo Park, Seungjin Choi. “Discrete Infomax Codes for Supervised Represen-tation Learning” . Entropy special issue “Theory and Applications of Information Processing Algorithms” ,20224. Hwanjun Song, Deqing Sun, Sanghyuk Chun, Varun Jampani, Dongyoon Han, Byeongho Heo, Wonjae Kim,Ming-Hsuan Yang. “ViDT: An Efficient and Effective Fully Transformer-based Object Detector” . 10th In-ternational Conference on Learning Representations (ICLR 2022)3. Wonjae Kim*, Bokyung Son*, Ildoo Kim. “ViLT: Vision-and-Language Transformer Without Convolution orRegion Supervision”. 38th International Conference on Machine Learning (ICML 2021, Long Presentation,Long Presentation Acceptance Rate: 3.0%)2. Wonjae Kim, Yoonho Lee. “Learning Dynamics of Attention: Human Prior for Interpretable Machine Rea-soning” . 32nd Conference on Neural Information Processing Systems (NeurIPS 2019)1. Daekyoung Jung, Wonjae Kim, Hyunjoo Song, Jeong-in Hwang, Bongshin Lee, Bohyoung Kim, JinwookSeo. “Chartsense: Interactive data extraction from chart images” . 35th Conference on Human Factors inComputing Systems (CHI 2017)PREPRINTS AND WORKSHOP PAPERS8. Jaeyoo Park, Sanghyuk Chun, Wonjae Kim, Sangdoo Yun, Bohyung Han. “Emergence of Text Readabilityin Vision Language Models”. 42nd Conference on Computer Vision and Pattern Recognition (CVPR 2025,2nd Workshop on Emergent Visual Abilities and Limits of Foundation Models)7. Geonmo Gu*, Sanghyuk Chun*, Wonjae Kim, HeeJae Jun, Yoohoon Kang, Sangdoo Yun. “CompoDiff: Ver-satile Composed Image Retrieval With Latent Diffusion”. 41st Conference on Computer Vision and PatternRecognition (CVPR 2024, Workshop on Synthetic Data for Computer Vision)6. Seokhyeon Park*, Wonjae Kim*, Young-Ho Kim, Jinwook Seo. “Computational Approaches for App-to-App Retrieval and Design Consistency Check”. 40th International Conference on Machine Learning (ICML2023, Workshop on Artificial Intelligence & Human Computer Interaction)5. Byungsoo Ko, Han-Gyu Kim, Byeongho Heo, Sangdoo Yun, Sanghyuk Chun, Geonmo Gu, Wonjae Kim.“Group Generalized Mean Pooling for Vision Transformer” .4. Hwanjun Song, Deqing Sun, Sanghyuk Chun, Varun Jampani, Dongyoon Han, Byeongho Heo, Wonjae Kim,Ming-Hsuan Yang. “An Extendable, Efficient and Effective Transformer-based Object Detector” .3. Jiyoung Lee, Wonjae Kim, Daehoon Gwak, Edward Choi. “Conditional Generation of Periodic Signals withFourier-Based Decoder” . 34th Conference on Neural Information Processing Systems (NeurIPS 2021,Workshop on Deep Generative Models and Downstream Applications Poster Presentation)2. Wonpyo Park*, Wonjae Kim*, Kihyun You, Minsu Cho. “Diversified Mutual Learning for Deep Metric Learn-ing” . 15th European Conference on Computer Vision (ECCV 2020, Task-CV Workshop)1. Jaemin Jo, Wonjae Kim, Seunghoon Yoo, Bohyoung Kim, Jinwook Seo. “Swifttuna: Responsive and incre-mental visual exploration of large-scale multidimensional data”. 10th IEEE Pacific Visualization Symposium(PacificVis 2017)EDUCATIONSeoul National University, M.S. South KoreaFeb. 2018Department of Computer Science and Engineering, Advisor: Jinwook SeoThesis: Understanding Visualization Idioms Through Deep VisualizationSeoul National University, B.S. South KoreaFeb. 2016Department of Computer Science and Engineering3
ACADEMIC SERVICEREVIEWERVenue20202021202220232024202520262027International Conference on Machine Learning (ICML)34242International Conference on Learning Representations (ICLR)325135Blogposts Track2Neural Information Processing Systems (NeurIPS)572162Workshop on ImageNet: Past, Present, and Future2Association for the Advancement of Artificial Intelligence (AAAI)664Computer Vision and Pattern Recognition Conference (CVPR)6624*4International Conference on Computer Vision (ICCV)44European Conference on Computer Vision (ECCV)64Transactions on Machine Learning Research (TMLR)1221Conference on Human Factors in Computing Systems (CHI)11Symposium on User Interface Software and Technology (UIST)1Numbers are papers reviewed that year. * Outstanding Reviewer, CVPR 2025.4