Kyle Min

Biography

Kyle Min is a Principal Applied Scientist at Oracle, working on video generation, multimodal AI, and personalization. Previously, he was a Staff Research Scientist at Intel Labs, where he led work on multimodal learning, reliable AI, and video understanding. He received his Ph.D. from the University of Michigan, advised by Prof. Jason Corso.

Highlights

Technical focus: frontier video generation, multimodal AI, personalization, and reliable AI
Applied AI experience: post-training, customer-driven personalization, production-oriented prototyping, and model improvements
Publications: 20+ peer-reviewed papers at CVPR, ICCV, ECCV, and NeurIPS, with oral and spotlight recognitions
Service: Area Chair, NeurIPS 2026; Vice President, KSEA Seattle Chapter; AI Expert Committee Member, K-TAG U.S. Chapter

[ Github | LinkedIn | CV | Google Scholar | Publications ]

Research & Work Experience

Oracle

Principal Applied Scientist, 2025-Present
Seattle, WA USA

Develop frontier video generation and multimodal AI systems within Oracle Cloud Infrastructure (OCI)
Drive pretraining, post-training, and customer-driven personalization for enterprise GenAI applications
Develop production-oriented prototypes, customer demos, and model improvements for video generation systems

Intel Labs

Staff Research Scientist, 2021-2025
Santa Clara, CA USA

Led research initiatives in generative AI, multimodal learning, reliable AI, and video understanding
Served as Tech Lead for GraVi-T, a graph-based framework for active speaker detection and audio-visual diarization
Developed methods for text-to-image and text-to-3D diffusion models, VLM enhancement, and video understanding
Led and contributed to challenge-winning video understanding systems for Ego4D, ActivityNet, and AVA
Initiated academic collaborations that led to 10+ publications at top AI and computer vision venues

University of Michigan
Graduate Student Research Assistant, 2017-2021
Ann Arbor, MI USA

Conducted research on video understanding, temporal action localization, egocentric activity recognition, and video saliency prediction
Developed methods published at CVPR, ICCV, and ECCV

Seoul National University
Summer Intern, 2015-2016
Seoul, South Korea

Conducted research on visual question answering and implemented deep learning models for VQA systems

Xeron
Algorithm Developer, 2012-2015
Seoul, South Korea

Developed video analytics algorithms for neonatal monitoring systems in hospital environments
Built an event detection system for the i-LIDS benchmark, certified by the UK Home Office

Professional Service & Leadership

Area Chair: NeurIPS 2026, ICML 2027
Vice President: Korean-American Scientists and Engineers Association (KSEA), Seattle Chapter (2026-present)
AI Expert Committee Member: Korea Technology Advisory Group (K-TAG), U.S. Chapter (2025–Present)
Lead Organizer: Seattle AI & Energy Forum, co-hosted with the Consulate General of the Republic of Korea in Seattle (Nov 2026)
Organizing Committee Member: RBGM tutorial at ECCV 2024, RBFM workshop at NeurIPS 2024, and RVLGM tutorial at ICCV 2025
Conference Reviewer: CVPR (2021-present), ICCV (2021-present), ECCV (2020-present), NeurIPS (2022-present), ICLR (2022-present), and ICML (2023-present)
Journal Reviewer: IEEE TPAMI (2021-present), IEEE TIP (2021-present), IEEE TMM (2023-present), Pattern Recognition (2021-present), and IEEE Access (2025-present)

Education

University of Michigan
Ph.D. in EECS, 2021 (Advisor: Prof. Jason Corso)
University of Michigan
M.S. in EECS, 2018
Seoul National University
B.S. in EECS, 2016

Awards & Honors

1st place in the EgoExo4D Challenge for Keystep Recognition ($500)
EgoExo4D sponsored by Meta, CVPRW 2025
Distinguished Researcher Award ($250)
Intel Labs, 2023
1st place in the Ego4D Challenge for Audio-Visual Diarization ($3000)
Ego4D sponsored by Meta, ECCVW 2022
2nd place in the AVA Challenge for Active Speaker Detection
ActivityNet, CVPRW 2022
Best Achievement Award of Global Top Talent Forum ($3000)
Hyundai Motor Group, 2019
Richard F. and Eleanor A. Towner Prize for Distinguished Academic Achievement ($1000)
University of Michigan, 2018
College of Engineering Alumni Association Prize for the best academic achievement ($1000)
Seoul National University, 2016
B.S. summa cum laude
Seoul National University, 2016
Stipends for outstanding students ($8000)
Korea Foundation for Advanced Studies, 2011-2012
National Science & Technology scholarship (Full tuition)
Korea Student Aid Foundation, 2009-2012
Scholarship for Distinguished Academic Achievement ($1000)
Samsung Electronics, 2008

Professional Activities

Invited talk at Chung-Ang University (Seoul, Korea), 2026
Invited talk at Kyung Hee University (Seoul, Korea), 2026
Invited talk at Soongsil University (Seoul, Korea), 2025
Invited talk at SCAI AI Day, Arizona State University (Phoenix, AZ), 2023
Spotlight presentation at Ego4D workshop in CVPR (Vancouver), 2023
Hyundai Global Top Talent Forum - (San Diego, CA), 2019
Poster presentation at Intel Innovation (San Jose, CA), 2022
Student volunteer for ICCV (Seoul, Korea), 2019
Qualcomm IT Tour (San Diego, CA), 2015
LG Global Challenger (England, Sweden, Belgium, Netherlands), 2011

Teaching Experience

Graduate Student Instructor, EECS 442 (Computer Vision)
University of Michigan, Fall 2017
Freshman adviser, Physics and Mathematics
Seoul National University, Fall 2011

Interests

Python, MATLAB
PyTorch, PyG
Kubernetes, Slurm
Tennis, Squash, Rock Climbing