Hi, I am Junwan Kim

I am a Master’s student in Computer Science at New York University, Courant Institute of Mathematical Sciences. Prior to NYU, I earned my B.S. in Electrical and Electronic Engineering from Yonsei University. My research interests lie in artificial intelligence, with a focus on generative models and multi-modal learning.

Contact

junwan [dot] kim [at] nyu [dot] edu

Computer Vision, Multi-modal Learning
MSCS @ New York Univiersity
60 5th Ave, New York, NY 10011, US

Google Scholar
LinkedIn
CV

Publications

* denotes equal contribution | Listed in reverse chronological order

arXiv

Visual Representation Alignment for Multimodal Large Language Models
Heeji Yoon*, Jaewoo Jung*, Junwan Kim*, Hyungyu Choi, Heeseong Shin, Sangbeom Lim, Honggyu An, Chaehyun Kim, Jisang Han, Donghyun Kim, Chanho Eom, Sunghwan Hong, Seungryong Kim
arXiv preprint
Project Page arXiv

arXiv

URECA💡: Unique Region Caption Anything
Sangbeom Lim*, Junwan Kim*, Heeji Yoon, Jaewoo Jung, Seungryong Kim
arXiv preprint
Project Page arXiv

ICCV

V.I.P.: Iterative Online Preference Distillation for Efficient Video Diffusion Models
Jisoo Kim, Wooseok Seo, Junwan Kim, Seungho Park, Sooyeon Park, Youngjae Yu
International Conference of Computer Vision (ICCV) 2025
Project Page arXiv

ICCV

DisCoRD: Discrete Tokens to Continuous Motion via Rectified Flow Decoding
Jungbin Cho*, Junwan Kim*, Jisoo Kim, Minseo Kim, Mingu Kang, Sungeun Hong, Tae-Hyun Oh, Youngjae Yu
International Conference of Computer Vision (ICCV) 2025, Highlight (263/11239=2.34%)
Project Page arXiv

Technical Report

TWLV-I: Analysis and Insights from Holistic Evaluation on Video Foundation Models
TwelveLabs Team
Technical Report
Project Page arXiv

Technical Report

Pegasus-v1 Technical Report
TwelveLabs Team
Technical Report
Project Page arXiv

IJCAI

AVIN-Chat: An Audio-Visual Interactive Chatbot System with Emotional State Tuning
Chanhyuk Park*, Jungbin Cho*, Junwan Kim*, Seongmin Lee, Jungsu Kim, Sanghoon Lee
International Joint Conference on Artificial Intelligence (IJCAI) Demo Track 2024
Project Page arXiv

ACK

Design and Implementation of User-Interactive Crowd Accident Avoiding System
Junwan Kim*, Youngbae Kong*, Byeongho Kim*, Minjae Park*, Jeongeun Nah
Annual Conference of Korea Information Processing Society (ACK) 2023
Project Page arXiv




Careers

TwelveLabs March 2024 - August 2024
Seoul, South Korea / San Francisco, USA
TwelveLabs, a startup specializing in foundation models for video understanding, where I worked as a research intern in the video-language research team. (Advisor: Prof. Minjoon Seo)

Linq Alpha September 2023 - January 2024
Boston, USA (Remote)
Linq Alpha, a startup specializing in generative models for finance, where I participated in an industry-academic collaboration project. (Advisor: Prof. Jy-Yong Sohn)

Rebuilder AI July 2023 - August 2023
Seoul, South Korea
Rebuilder AI is a startup specializing in developing AI models for 3D assets, where I participated in an industry-academic collaboration project.

Educations

Yonsei University March 2019 - August 2025
Seoul, South Korea
B.S. in Elctrical and Electronic Engineering

New York University September 2025 - Present
New York, United States
M.S. in Computer Science

Research Experiences

MIRLAB Aug 2024 - Mar 2025
Yonsei University, Seoul, South Korea
Undergraduate Researcher (Supervisor: Prof. Yonugjae Yu)

CVLAB Sep 2024 - Present
KAIST (Korea Advanced Institute of Science & Technology), Seoul, South Korea
Undergraduate Researcher (Supervisor: Prof. Seungryong Kim)

VISIONx Sep 2025 - Present
New York University, New York, United States
Graduate Researcher (Supervisor: Prof. Saining Xie)