Principal Investigator
#
Ph.D. track
#

Sangyoon Lee
Hyperefficient Neural Fields β‘οΈ
M.S.+Ph.D. @ POSTECH AI (24.02--)
Keywords: Fast Neural Fields, Editable Neural Fields, Neural Compression
webpage,
mail
Minjae Park
Accelerating Large-Scale Models for Videos π₯
M.S.+Ph.D. @ POSTECH EE (24.02--)
Keywords: State-Space Models, Model Compression
webpage,
mail
Hyunjong Ok
Advancing Audio Technologies for Multimodal Intelligence π
M.S.+Ph.D. @ POSTECH AI (24.02--)
Keywords: Efficient LLM, Multi-modal learning, Audio Technologies
webpage,
mail
Taesun Yeom
Understanding Training Dynamics of Neural Fields
M.S.+Ph.D. @ POSTECH AI (24.09--)
Keywords: Neural Fields, Learning Dynamics
Google Scholar
Hyeonjun Kim
Learning Vision Language Models with Many Applications
M.S.+Ph.D. @ POSTECH AI (25.02--)
Keywords: Multimodal Learning, Model Efficiency
mail,
webpage
M.S. track
#

Minkyu Kim
Harnessing Language Models for Multimodal Tasks ποΈποΈ
POSTECH AI (23.03--)
Keywords: Multimodal learning, Image processing, Audio captioning
webpage,
mail,
blog,
recent project,
twitter
Juyun Wee
Compressing Large Language Models π
POSTECH EE (23.09--)
Office Team Lead @ EffL
Keywords: LLM Compression, Model Pruning, Model Efficiency
webpage,
mail
Jiyun Bae
Data-dependent Visual Prompts πΆοΈ
POSTECH AI (24.02--)
Academic Team Lead @ EffL
Keywords: Visual Prompts, Black-box models, LLMs, Fairness
webpage,
mail
Jegwang Ryu
Compression in the Neural Network Weight Space
POSTECH EE (24.09--)
Keywords: Efficient LLM, Accelerated Training
Google Scholar,
mail
Seunghyun Kim
Low-precision Training of LLM
POSTECH EE (24.09--)
Keywords: LLM, Quantization

Minhee Lee
Compressing Large Language Models
POSTECH AI (25.02--)
Keywords: LLM pruning, Speculative decoding
webpage,
mail
Staff
#
Seung-Ah Song
#
Administrative Staff @ EffL (22.03–)
mail