Hee Bin Yoo
Notice: This website is currently under construction. Some content may be incomplete, inaccurate, or generated with AI and may contain hallucinations. Please check back later for updates.
I am an Assistant Professor in the School of AI Software at Soongsil University, Seoul, Korea. My research focuses on feature learning theory, neural collapse, metric learning, machine unlearning, deep reinforcement learning dynamics, stochastic control, Schrodinger bridge methods, equivariant convolution, and Spatial AI.
Before joining Soongsil University, I was a MA/Ph.D. student in Artificial Intelligence at Seoul National University, where I worked in the Biointelligence Lab. I received a B.S. in Computer Science and Engineering from Chung-Ang University, graduating summa cum laude.
My publications include work appearing in NeurIPS, CVPR, AAAI, ECCV, ICRA, TMLR, Machine Learning, IEEE Access, and Machine Vision and Applications. I also collaborate with researchers at Hanyang University, Chung-Ang University, and Ecole Normale Superieure on machine learning theory, image retrieval, backdoor attacks, fine-tuning, and 3D computer vision.
Research Interests
- Feature learning theory and neural collapse
- Metric learning, image retrieval, and point-cloud representation learning
- Machine unlearning and backdoor robustness
- Deep reinforcement learning dynamics and embodied intelligence
- Stochastic control, Schrodinger bridge methods, and equivariant convolution