Junho Kim

About Me

I am a Postdoctoral Researcher at the University of Illinois Urbana–Champaign (UIUC), working with Prof. James M. Rehg on large-scale multimodal intelligence. I completed my Ph.D. at KAIST, where I was advised by Prof. Yong Man Ro.

My long-term research interest lies in understanding how multimodal models perceive and reason about the world—and why they sometimes fail. I study the factors that drive the behavior of large vision-language models and design methods that make them more reliable, robust, and interpretable. My goal is to build principled foundations that support multimodal systems capable of adapting across different tasks, domains, and real-world conditions.

Contact me for collaboration opportunities - I am always open to discussing research collaborations, industry partnerships, and new projects. Feel free to reach out if you’re interested in working together!

Research Interests

• Large Vision–Language Models: exploring how multi-modal models perceive, generate, and reason across visual, textual, and temporal data
• Multimodal Learning & Video Understanding: integrating vision, language, and time to analyze real-world interactions at scale
• Robustness, Safety & Causal Analysis: diagnosing failure modes, identifying causal relations, and designing explainable, trustworthy models

Work Experience

• University of Illinois Urbana-Champaign, USA (Sep. 2025 - Present)
  - Postdoctoral Research Associate
  - Advisor: Prof. James M. Rehg

Education

• KAIST, Daejeon, South Korea (2019 Aug. - 2025 Aug.)
  - Ph.D. in Electrical Engineering
  - Advisor: Prof. Yong Man Ro
  - Dissertation: Advancing Factuality in Large Vision-Language Models through Selective Visual Information and Textual Context Refinement
• Dongguk University, Seoul, South Korea (2012 Feb. - 2019 Feb.)
  - B.S. in Electrical and Electronic Engineering

News

• [Sep. 2025] I joined UIUC as a Postdoc!
• [Jul. 2025] One paper is accepted to PR!
• [Jun. 2025] I have successfully defended my PhD thesis!
• [Feb. 2025] One paper is accepted to CVPR 2025!
• [Sep. 2024] One paper is accepted to NeurIPS 2024!
• [Sep. 2024] One paper is accepted to EMNLP 2024!
• [Jul. 2023] One paper is accepted to ICCV 2023!
• [Jun. 2023] One paper is accepted to ICIP 2023!
• [Feb. 2023] One paper is accepted to CVPR 2023!
• [Mar. 2022] One paper is accepted to CVPR 2022!
• [Nov. 2021] One paper is accepted to IEEE TIP!
• [Sep. 2021] One paper is accepted to NeurIPS 2021!

Publications

Honors & Awards

• NeurIPS 2025 Top Reviewer Award (Top 8%) [Link] - Conference on Neural Information Processing Systems (NeurIPS), 2025
• KAIST Fellowship (2019 - 2025)
• The World Embedded software Contest [Link] - Finalist with AI six-legged robot ‘Homecoming’ (2017)

Services and Talk

Program Committee & Conference Reviewers

• CVPR 2023,2024,2025, 2026
• ICCV 2023,2025
• ECCV 2022,2024
• NeurIPS 2023,2024,2025
• AAAI 2025
• ICLR 2024,2025,2026
• WACV 2026

Journal Reviewers

• IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)
• IEEE Transactions on Audio, Speech, and Language Processing (TASLP)

Invited Talk

• Invited Talk at AMI LAB, KHU, Video Understanding with Large Vision-Language Models: Challenges and Progress, 2025
• Guest Lecture at CS 598 CVH — Computer Vision for Health, University of Illinois Urbana–Champaign, Evolutions of LLMs and VLMs, 2025
• Invited Talk (세상과 만나는 강연) at Gimpo High School, Shaping the Future of AI: from History to Large Language Model, 2025
• Invited Talk at SAIL LAB, KAIST, Advancing Factuality in Large Multi-Modal Models through Integrated Cross-Modal Consistency, 2025