I am a PhD student and a member of Computer Vision Lab at Yonsei University, advised by Prof. Bumsub Ham. My research interests include machine learning and deep learning, with a particular focus on developing efficient models. Recently, I have been interested in accelerating large-scale models, such as diffusion transformers, VideoLLMs, and diffusion-based LLMs (e.g., LLADA and LAVIDA).
Intro
Education
Publications
Projects
Edge artificial intelligence semiconductor IP development
Korea Technology & Information Promotion Agency for SMEs (TIPA), Aug. 2023 ~ Present
Korea Technology & Information Promotion Agency for SMEs (TIPA), Aug. 2023 ~ Present
- Developed quantization and pruning algorithms for In-Memory Computing (IMC) chips.
- Collaborated with hardware teams for efficient HW-SW co-design.
- Built deep learning models for circuit performance prediction and optimization.
Development of Fundamental Technology and Integrated Solution for Next-Generation Automatic Artificial Intelligence System
Institute for Information & Communications Technology Promotion (IITP), Apr. 2022 ~ Jul. 2023
Institute for Information & Communications Technology Promotion (IITP), Apr. 2022 ~ Jul. 2023
- Developed neural architecture search (NAS) algorithms for CNNs, ViTs, and quantized models..
- Designed Automatic Loss Function Search algorithms for adaptive optimization.
- Implemented low-bit training techniques for efficient deep learning model training.