We are pleased to announce that Professor Iksung Kang has joined the School of Electrical Engineering as of January 26, 2026. We warmly welcome him to our school.
Professor Kang’s temporary office is located in Room 1410, Saeneul-Dong. His research focuses on the design of intelligent imaging systems that integrate physics-based models with machine learning. He is particularly interested in computational imaging technologies for biomedical microscopy, neuroscience, and metrology. By combining the physical principles of optical systems with deep learning, he proposes novel approaches to overcome the limitations of conventional imaging techniques.
Through inverse problem modeling that efficiently reconstructs high-dimensional information from measured signals, as well as end-to-end imaging system development that integrates sensing, physics, and learning, Professor Kang aims to realize next-generation imaging technologies that are both highly accurate and broadly accessible.
For more detailed information about Professor Kang’s research, please visit his website below.
Website: https: https://iksungk.github.io/
<Academic and Professional Profile>
Major Field
- Physics- and Learning-driven Imaging System Design
- Computational Imaging (for Biomedical Microscopy, Neuroscience, and Metrology)
Educational Career
- Bachelor Degree: 2017, Seoul National University
- Master Degree: 2020, MIT
- Doctoral Degree: 2022, MIT
Career
- Sep. 2025 – Jan. 2026: Assistant Professor, Yonsei University
- Jul. 2022 – Jun. 2025: Postdoctoral Researcher, UC Berkeley
Publications
- Optical segmentation-based compressed readout of neuronal voltage dynamics, Nature Communications, 2025
- Coordinate-based neural representations for computational adaptive optics in widefield microscopy, Nature Machine Intelligence, 2024
- Accelerated deep self-supervised ptycho-laminography for three-dimensional nanoscale imaging of integrated circuits, Optica, 2023
- Attentional Ptycho-Tomography (APT) for three-dimensional nanoscale X-ray imaging with minimal data acquisition and computation time, Light: Science & Applications, 2023
- Simultaneous spectral recovery and CMOS micro-LED holography with an untrained deep neural network, Optica, 2022
- Dynamical machine learning volumetric reconstruction of objects’ interiors from limited angular views, Light: Science & Applications, 2021
Assigned Curricular Plan
- EE49904: Special Topics in Electrical Engineering
- <Computational Imaging>
- Other signal-related courses (e.g., signal/image processing, optical imaging)
Vision
- Develop intelligent imaging systems that seamlessly integrate physics and machine learning with system-level design to make advanced imaging more accessible.
Research Plan
- Generalizable Imaging Architectures: Create unified imaging frameworks that generalize across sensing modalities and sample types.
- Imaging-driven Inverse Intelligence: Build imaging-driven inverse modeling frameworks that connect measurements to high-level system understanding.
- End-to-end Intelligent Imaging: Develop end-to-end imaging systems that integrate sensing, physics, and learning for task-aware inference.
