I am Head of AI at PYLER. I received my Ph.D. in Electrical Engineering from KAIST in August 2026, advised by Professor Junmo Kim. My research focuses on multimodal representation learning across vision, language, and audio, with an emphasis on building more efficient and effective models.
Beyond this, I also explore related topics such as multimodal captioning, end-to-end autonomous driving, fairness in AI, and automatic speech recognition, aiming to bridge fundamental research with real-world applications.
Email: js.kim (at) pyler (dot) tech
Education
- Sep 2020 – Aug 2026
- Integrated M.S./Ph.D. in Electrical Engineering, KAIST
Thesis: Redesigning Positive Pairs for Contrastive Multimodal Representation Learning
Advisor: Junmo Kim - Mar 2016 – Aug 2020
- B.S. in Electrical Engineering, KAIST
Publications
Selected / All * denotes equal contribution. Selected lists first-author papers.
-
Continuous Audio Thinking for Large Audio Language Models
Gyojin Han*, Dong-Jae Lee*, Changho Choi*, Jongsuk Kim*, Junmo Kim
NeurIPS 2026 [paper] -
Learning Where It Matters: Geometric Anchoring for Robust Preference Alignment
Youngjae Cho, Jongsuk Kim, Ji-Hoon Kim
NeurIPS 2026 [paper] -
MLLMCLIP: Feature-Level Distillation of MLLM for Robust Vision-Language Representations
Jongsuk Kim, Qiyu Wu, Zhuoyuan Mao, Hiromi Wakaki, Junmo Kim, Yuki Mitsufuji
EMNLP 2026 [paper] -
FxSearcher: Gradient-free Text-driven Audio Transformation
Hojoon Ki, Jongsuk Kim, Minchan Kwon, Junmo Kim
ICASSP 2026 [paper] [code] [project page] -
SynAD: Enhancing Real-World End-to-End Autonomous Driving Models through Synthetic Data Integration
Jongsuk Kim*, Jaeyoung Lee*, Gyojin Han, Dongjae Lee, Minki Jeong, Junmo Kim
ICCV 2025 [paper] -
FairASR: Fair Audio Contrastive Learning for Automatic Speech Recognition
Jongsuk Kim, Jaemyung Yu, Minchan Kwon, Junmo Kim
Interspeech 2025 [paper] [code] -
StablePrompt: Automatic Prompt Tuning using Reinforcement Learning for Large Language Model
Minchan Kwon, Gaeun Kim, Jongsuk Kim, Haeil Lee, Junmo Kim
EMNLP 2024 [paper] [code] -
AVCap: Leveraging Audio-Visual Features as Text Tokens for Captioning
Jongsuk Kim, Jiwon Shin, Junmo Kim
Interspeech 2024 [paper] [code] -
EquiAV: Leveraging Equivariance for Audio-Visual Contrastive Learning
Jongsuk Kim*, Hyeongkeun Lee*, Kyeongha Rho*, Junmo Kim, Joon Son Chung
ICML 2024 [paper] [code] -
UniCLIP: Unified Framework for Contrastive Language-Image Pre-training
Janghyeon Lee*, Jongsuk Kim*, Hyounguk Shon, Bumsoo Kim, Seung Hwan Kim, Honglak Lee, Junmo Kim
NeurIPS 2022 [paper]
Preprints
-
TransMotion: Text-Guided Transformation Learning for Composed Human Motion Retrieval
Jongsuk Kim, Gyojin Han, Junmo Kim
Under review -
MARS: MAmmalian-specific RNA Sequence Modeling for Localization, Structure, and Stability
Jongsuk Kim, Hyeonsik Oh, Donggyun Kim, Won Do Heo, Junmo Kim
Preprint -
Supervised Dimension Contrastive Learning
Jaemyung Yu, SungHyun Baek, Jongsuk Kim, Junmo Kim
Preprint
Experience
- Nov 2025 – Present
- PYLER, Seoul, South Korea
Head of AI, Aug 2026 – Present
Research Scientist, Jun 2026 – Jul 2026
Research Intern, Nov 2025 – May 2026 · Mentor: Jihoon Kim - Mar 2025 – Jun 2025
- Research Intern, Sony Group Corporation
AI Technology Div., Creative AI Lab · Mentor: Qiyu Wu · Tokyo, Japan - Nov 2021 – May 2022
- Research Intern, LG AI Research
Vision Lab · Mentor: Janghyeon Lee · Seoul, South Korea - Aug 2021 – Nov 2021
- AI Engineering Intern, NAVER
G-place AI Development Team · Mentor: Yunsang Ju · Seongnam (remote), South Korea - Mar 2018 – Aug 2018
- Software Engineering Intern, KAKAO
AI Team, Multimedia Processing Part · Jeju, South Korea
Honors & Awards
- 2026
- NVIDIA Nemotron Developer Day Seoul Hackathon, 1st place
Domain-specific model track, with the PYLER team - 2024
- Kim Young Han Global Leader Scholarship
4,000,000 KRW - 2021
- CLOVA AI RUSH, NAVER
1st place, global menu name analysis (G-Place AI Development Team)
2nd place, document keyword extraction for UGC content (AiRS Team)
25,000,000 KRW - 2019
- Qualcomm Innovation Awards
5,000,000 KRW - 2019
- Dean's List, Spring 2019
Top 3% in College of Engineering, KAIST
Invited Talks
- Nov 2025
- End-to-end Autonomous Driving
Seoul Robotics, Seoul - Oct 2024
- Audio-Video Representation Learning
LG AI Research, Seoul - Apr 2023
- Equivariant Contrastive Learning
Samsung Research, Seoul - Dec 2022
- Contrastive Language-Image Pre-training
NAVER, Seongnam - Nov 2022
- Contrastive Language-Image Pre-training
Samsung Research, Seoul
Academic Service
Conference reviewer
- AAAI 2025, 2026
- AISTATS 2025, 2026
- CVPR 2024, 2025, 2026
- ICCV 2025
- ICLR 2026
Workshop organizer
- Generative AI Research Exchange, KAIST SIIT & Sony AI Japan