Deep Representation Learning

Research Group.



Our primary research goal is to advance understanding of the inner workings of deep learning, with a particular emphasis on representation learning. Our research spans a broad range of topics in deep learning, including unsupervised learning, information-theoretic methods, representation in transformers, interpretability, text-to-image generation, video understanding, meta-learning, neural architecture search, continual learning, and deep neural network compression.

For potential students in Korea:  [연구분야소개영상] 

앞으로 한동안 학생을 선발하지 않습니다. 죄송합니다.