Jin-Hwa Kim
Research · Teaching · Writing
Jin-Hwa Kim

Jin-Hwa Kim, Ph.D.

Leader, NAVER AI Lab

Guest Associate Professor, SNU AIIS

Jin-Hwa Kim has been the Leader of Generation Research at NAVER AI Lab, working since August 2021, and a Guest Associate Professor at the Artificial Intelligence Institute of Seoul National University (SNU AIIS) since August 2022. He has studied neural 3d, world models, multimodal generation, ethical and safe AI, and other related topics. In 2018, he received a Ph.D. from Seoul National University under the supervision of Professor Byoung-Tak Zhang for the work on “Multimodal Deep Learning for Visually-grounded Reasoning.” In September 2017, he received 2017 Google Ph.D. Fellowship in Machine Learning, Ph.D. Completion Scholarship by Seoul National University, and the VQA Challenge 2018 runners-up at the CVPR 2018 VQA Challenge and Visual Dialog Workshop. He was Research Intern at Facebook AI Research (Menlo Park, CA) mentored by Yuandong Tian, Devi Parikh, and Dhruv Batra, from January to May in 2017. He worked for SK Telecom (August 2018 to July 2021) and SK Communications (January 2011 to October 2012).

  • 2026.08.13🧑‍⚖️ Serving as an Area Chair for ICLR 2027, to be held in California, USA.
  • 2026.08.03📣 Welcoming Dr. Jungho Lee to Generation Research, NAVER AI Lab as a Research Scientist working on city-scale physical world models.
  • 2026.06.17🎉 Three papers by my interns accepted to ECCV 2026 — Seoul World Model (Spotlight), TetraSDF (Spotlight), and Relaxed Rigidity for 4DGS.
Research

Publications

Last updated Aug 2026
Filter by topic — sorted by most recent
* Equal contribution    † Co-corresponding author
Teaching

Courses

Graduate courses taught at
Seoul National University as guest faculty
Fall 2026 · Guest Faculty, SNU AIIS

Large Foundational Models and Physical World Models for Multimodal AI

Multimodal foundation models — multimodal LLMs and multimodal generative AI — together with physical world models that represent, simulate, and predict the 3D/4D physical world under actions, followed by a paper-driven seminar. Co-taught with Sangdoo Yun.

Fri 13:00–15:50Bldg. 302, Rm. 106Syllabus →
Fall 2025 · Guest Faculty, SNU AIIS

Multimodal Generative AI Theories and Applications

Multimodal generative AI from vision and language to audio and speech, with neural graphics (NeRFs, 3DGS) as an emerging topic in multi-view representation learning. Co-taught with Sangdoo Yun.

Fri 13:00–15:50Bldg. 302, Rm. 107Syllabus →
Fall 2024 · Guest Faculty, SNU AIIS

Multimodal Deep Learning Theories and Applications

Core theories and applications of multimodal deep learning across vision, language, audio, and speech, extending into neural graphics (NeRFs). Co-taught with Sangdoo Yun and Jiyoung Lee.

Fri 13:00–15:50Bldg. 302, Rm. 107Syllabus →
Fall 2023 · Guest Faculty, SNU AIIS

Multimodal Deep Learning Theories and Applications

Core theories and applications of multimodal deep learning across vision, language, audio, and speech, with neural graphics (NeRFs) as time permits. Co-taught with Jiyoung Lee.

Fri 13:00–15:50Bldg. 302, Rm. 107Syllabus →
Writing

Blog

Research notes, paper reviews, and essays on AI, math, and life.
About

Academic Services

Area Chair for ICLR 2027, NeurIPS 2024-2026, ICML 2025-2026, and ACL ARR 2024 June

Organizer for ICML 2026 Expo Talks and Panels — Seoul World Model

Reviewer for NeurIPS 2018-2023, ICLR 2019, 2021-2023, ICML 2019-2021, 2024, and COLING 2022

Reviewer for Neural Networks (2020)

Reviewer for IEEE Transactions on Neural Networks and Learning Systems (2019)

Topic Editor for “Identifying, Analyzing, and Overcoming Challenges in Vision and Language Research” in the Frontiers Research Topics

Program Committee for the “1st workshop on Video-Language Models” at NeurIPS 2024

Co-organizer for ICML 2023 Social — ML in Korea

Program Committee for the 2nd workshop on “Video Turing Test” at ECCV 2020

Invited Speaker for the 3rd Workshop on “Closing the Loop Between Vision and Language” at ICCV 2019

Program Committee for the 1st Workshop on “Video Turing Test” at ICCV 2019

Program Committee for Workshop on “SiVL” at ECCV 2018

Collaborators

None of the work above happened alone — it grew out of papers written together, ideas borrowed and returned, and the people who shaped how I think about research. Without these collaborations, there would be little to show for the years behind this page.

ColleaguesDongyoon Han, Gayoung Lee, Jungho Lee, Junho Kim, Sangdoo Yun

Interns MentoredHwan Heo, Hyunin Cho, Inho Kong, Injae Kim, Jaeseok Jeong, Jaeseong Lee, Jangho Park, Jiwook Kim, Jun-Seong Kim, Junha Hyung, Junoh Lee, Junyoung Seo, Min-Seop Kwak, Mingyu Kim, Minjung Shin, Minkyung Kwon, Seonghun Oh, Soohyun Kim, Suhyeon Lee, Susung Hong, Yong-Hyun Park

Collaborating ProfessorsByoung-Tak Zhang, Devi Parikh, Dhruv Batra, Hyunwoo J. Kim, Jun-Yan Zhu, Mohamed Elhoseiny, Seungryong Kim, Tae-Hyun Oh, Youngjung Uh, Yuandong Tian

Personal CollaboratorsDamien Teney, Jiasen Lu, Kushal Kafle, Sang-Woo Lee

Wity Works

A personal site for research, teaching, and writing under one roof. Bauhaus geometric discipline and a trace of Greek architectural proportion, rendered in a bold, direct primary-color palette.

Off the Record

Enjoys computer games — Diablo 2, Elden Ring, Lineage, Overwatch, Stellar Blade.
Amateur badminton player for about 10 years.
Collects deep learning memorabilia: a name card from Andrew Ng, a copy of Deep Learning signed by Ian Goodfellow, an official ICML 2016 poster, a bulldozer Lego set (Set 856, 1979–1981; the one behind the "Blender synthetic" renders), and a first-edition printing of Diederik P. Kingma's PhD thesis.
Once dreamed of becoming a graphic designer: won the 1st Korea Flash Award — Motion Graphics Finalist (Yoon Design Lab) at COEX in 2001. A crewmate from that era, Brand Visual Director and CEO of VBstudio, went on to become the most successful of the group after serving as head of the Brand Design Team at YG Entertainment.