CV
Summary
Ph.D. candidate in Artificial Intelligence at Seoul National University, working on feature learning theory, metric learning, machine unlearning, and Spatial AI. Author of publications in leading venues including NeurIPS, CVPR, AAAI, ECCV, ICRA, and TMLR. Background spans both research and practice, including software development and founding a startup.
Education
- 2021 - 2026: MA/Ph.D. in Artificial Intelligence, Seoul National University, Korea
- Member of the Biointelligence Lab
- Research: feature learning theory, neural collapse, unlearning, metric learning, deep reinforcement learning dynamics, stochastic control, Schrodinger bridge, and equivariant convolution
- GPA: 3.52/4.30
- 2018 - 2021: B.S. in Computer Science and Engineering, Chung-Ang University, Korea
Work Experience
- Sep. 2026 - present: Assistant Professor, School of AI Software, Soongsil University, Seoul, Korea
- Mar. 2013 - Jan. 2019: Founder, CEO, and Head Architect, R inc., Seoul, Korea
- Architected and developed Android and web services
- Led consulting, requirement analysis, negotiation, sales, management, contracting, legal, and tax work
- Nov. 2021 - 2026: Researcher, Global Operations Support, SW, Yangju, Korea
- Designed process automation for wastewater treatment
- Coordinated overseas business trips, client meetings, and professional networking
- Apr. 2022 - May 2022: Product planning and market research, Tommoro Robotics
- Jul. 2020 - Aug. 2020: Internship, Jness, Seoul, Korea
- Managed maintenance channels, handled requests, coordinated development communication, and built maintenance management software
- Mar. 2017 - Aug. 2018: Computing Utilization Education Advisor, Hyper Metacognitive Lab, Gwangmyeong, Korea
- Mar. 2018 - Nov. 2020: Advisor and Judge for competitions, Yongsan High School, Seoul, Korea
Visiting and Collaborations
- Feb. 2026 - Mar. 2026: Visiting researcher, Centre for Data Science, Ecole Normale Superieure, Paris
- Hosted by Bruno Loureiro; studied feature learning theory in two-layer neural networks using statistical physics approaches
- Jun. 2024 - present: Collaborator, Learning, Reasoning & Intelligence Group, Hanyang University
- Collaborating with Sungyoon Lee on theoretical research for practical computer vision problems, including image retrieval and backdoor attacks
- 2021 - present: Collaborator, Computer Vision Machine Learning Lab, Chung-Ang University
- Collaborating with Junseok Kwon on fine-tuning, image retrieval, and 3D computer vision applications
Publications
Hee Bin Yoo, Seunghyeon Lim, Dong-Sig Han, and Byoung-Tak Zhang. "Explore Unseen Embedding via Spectral Information in Classifier-based Metric Learning." Working paper.
Seul Kim, Hee Bin Yoo†, and Byoung-Tak Zhang†. (2026). "Focus on the Moment: Real-Time Semantic Failure Detection in Vision-Language-Action Models." 3rd Workshop on Semantic Reasoning and Goal Understanding in Robotics, RSS.
Wooyul Jung, Hochan Bang, Hee Bin Yoo, and Byoung-Tak Zhang. (2026). "Deep Neural Networks as Finite-Step Hopfield Dynamics." New Frontiers in Associative Memories Workshop at ICLR.
Jaein Kim, Hee Bin Yoo, Dong-Sig Han, and Byoung-Tak Zhang. (2026). "Voronoi-based Second-order Descriptor with Whitened Metric in LiDAR Place Recognition." ICRA.
Jaein Kim, Hee Bin Yoo, Dong-Sig Han, and Byoung-Tak Zhang. (2026). "Equivariant and Scalable Convolution to Continuous SE(3) over Point Clouds." CVPR.
Hee Bin Yoo, Dong-Sig Han, Jaein Kim, and Byoung-Tak Zhang. (2026). "PeriUn: Enhancing Unlearning by Selectively Forgetting Peripheral Samples." Proceedings of the AAAI Conference on Artificial Intelligence, 40(14), 12072-12080.
Jinhee Park*, Hee Bin Yoo*, Minjun Kim, Byoung-Tak Zhang, and Junseok Kwon. (2026). "Neural Collapse-Informed Initialization with Perturbation Injection in Classification-based Metric Learning." Proceedings of the AAAI Conference on Artificial Intelligence, 40(10), 8287-8295.
Jinhee Park, Hee Bin Yoo, Byoung-Tak Zhang, and Junseok Kwon. (2026). "Confidence Controls Deep Metric Learning." Machine Learning, 115, 77.
Dong-Sig Han, Jaein Kim, Hee Bin Yoo, and Byoung-Tak Zhang. (2025). "Variational Online Mirror Descent for Robust Learning in Schrodinger Bridge." Transactions on Machine Learning Research.
Jinhee Park*, Hee Bin Yoo*, Byoung-Tak Zhang, and Junseok Kwon. (2025). "Rethinking Metric Learning: Enhancing Generalization to Unseen Classes." IEEE Access, 13, 201156-201165.
Hee Bin Yoo, Sungyoon Lee, Cheongjae Jang, Dong-Sig Han, Jaein Kim, Seunghyeon Lim, and Byoung-Tak Zhang. (2025). "How Classifier Features Transfer to Downstream: An Asymptotic Analysis in a Two-Layer Model." NeurIPS.
Jaein Kim, Hee Bin Yoo, Dong-Sig Han, Yeon-Ji Song, and Byoung-Tak Zhang. (2024). "Continuous SO(3) Equivariant Convolution for 3D Point Cloud Analysis." European Conference on Computer Vision, Springer, 59-75.
Junseok Park, Yoonsung Kim*, Hee bin Yoo*, Min Whoo Lee, Kibeom Kim, Won-Seok Choi, Minsu Lee, and Byoung-Tak Zhang. (2024). "Unveiling the Significance of Toddler-Inspired Reward Transition in Goal-Oriented Reinforcement Learning." Proceedings of the AAAI Conference on Artificial Intelligence, 38(1), 592-600.
Dong Wook Shu, Wonbeom Jang, Heebin Yoo, Hong-Chang Shin, and Junseok Kwon. (2022). "Deep-plane sweep generative adversarial network for consistent multi-view depth estimation." Machine Vision and Applications, 33(1), 1-10.
Talks and Seminars
July 28, 2026
Talk and lab tour at EWHA-CUHK Global Student Partnership Program, Seoul, Korea
November 27, 2025
Invited oral presentation at Seoul National University, Seoul, Korea
November 25, 2025
Poster at 6th Brown Bag Seminar, Seoul National University, Seoul, Korea
October 01, 2025
Seminar at Biointelligence Lab, Seoul, Korea
June 01, 2023
Seminar at Biointelligence Lab, Seoul, Korea
September 01, 2022
Seminar at Machine learning theory paper review seminar, Korea
June 01, 2022
Seminar at Biointelligence Lab, Seoul, Korea
March 02, 2022
Seminar at Biointelligence Lab, Seoul, Korea
March 01, 2022
Seminar at Biointelligence Lab, Seoul, Korea
Teaching and Advising
Training material development, Seoul National University / Hyundai NGV, 2024
Advising and judging, Yongsan High School, 2018
Education advising, Hyper Metacognitive Lab, 2017
Software Development Projects
Project construction and management application developed at R inc. from 2017 to 2018.
Psychological care application developed at R inc. in 2017.
Payment system for food truck orders developed at R inc. in 2018.
College recommendation platform developed at R inc. in 2018.
Power consumption calculation and prediction backend system developed at R inc. in 2018.
Reusable Java architecture for two-player board games.
Android routing system using real-time Seoul bus traffic information.
Home-playable survival game system using localization, 3D scanning, 3D reconstruction, and physics engines.
Calorie burn estimation through body posture graph inference.
Patents
- Method and Apparatus for Machine Unlearning Using Selective Forgetting of Peripheral Samples, patent applied 10-2026-0036559, Feb. 27, 2026
- Method and Apparatus for Classifier Initialization Using Neural Collapse-Informed Direction and Perturbation Injection, patent applied 10-2026-0023526, Feb. 5, 2026
- Method and Apparatus for Analyzing and Optimizing Feature Transfer Efficiency in Classifier-Trained Neural Network, patent applied 10-2025-0216810, Dec. 31, 2025
- Wastewater Treatment Apparatus and Wastewater Treatment Method for Adjusting the Input Amount of Organic Carbon Using Artificial Intelligence Control Agent, patent applied 10-2024-0038538, Mar. 20, 2024
- Reinforcement Learning Method Applying Toddler-Inspired Sequential Reward Transition And Reinforcement Learning Performing Apparatus, decision to grant 10-2024-0055610, Jan. 23, 2025
Scholarship
- Top Seat in the grade, Chung-Ang University, autumn 2020
- Excellent Student, Chung-Ang University, spring 2019, autumn 2019, spring 2020, spring 2021
- AI Fellowship, Seoul National University, autumn 2021, spring 2022, autumn 2022, spring 2023
Grants
- Artificial Intelligence Graduate School Program, Seoul National University, Apr. 2021 - Dec. 2030
- Ministry of Science and ICT; total grant KRW 42,300,000,000; personal funding received KRW 46,492,321
- Self-directed AI Agents with Problem-solving Capability, Seoul National University, Apr. 2022 - Dec. 2026
- Ministry of Science and ICT; total grant KRW 4,750,000,000; personal funding received KRW 15,060,000
- Artificial Intelligence Innovation Hub, Seoul National University, Jul. 2021 - Dec. 2025
- Ministry of Science and ICT; total grant KRW 47,076,000,000; personal funding received KRW 1,080,000
- Hyundai NGV Machine Learning Training Material Development, Seoul National University, Dec. 2024 - Feb. 2025
- Hyundai NGV; total grant KRW 72,727,273; personal funding received KRW 4,024,800
- SW Star Lab: Cognitive Agents That Learn Everyday Life, Seoul National University, Mar. 2015 - Dec. 2022
- Total grant KRW 2,348,000,000; personal funding received KRW 5,040,000
Skills
- Selected coursework: Statistical Foundations for Machine Learning and AI, Machine Learning, Statistical Machine Learning, Optimization Theory and Applications, Artificial Neural Networks
- Programming: Python, PyTorch, NumPy, Faiss, Java, Spring, C, C++, OpenCV, x86 assembly, SQL, JavaScript, Node.js, and React
- Communication: Korean native; English fluent, TOEFL MyBest 103 on Nov. 28, 2023; beginner Japanese, Chinese, and Spanish
References
- Junseok Kwon, Professor, School of Computer Science and Engineering, Chung-Ang University
- Byoung-Tak Zhang, Ph.D. Advisor, Professor, Interdisciplinary Program in Artificial Intelligence, Seoul National University
- Bruno Loureiro, Professeur Attache & Researcher, ENS & CNRS, Departement d’Informatique
- Sungyoon Lee, Assistant Professor, Department of Computer Science, Hanyang University
- Cheongjae Jang, Research Professor, BK-FOUR, Hanyang University
