머신러닝 & 마인드 랩

Our research aims to develop general-purpose autonomous agent that can solve the difficult problems of humanity. We aim to achieve this by creating learning algorithms that are fundamental to perception, cognition, and action. We hope that this computational approach will also provide insights into the inner workings of the human mind. We tackle this problem using the tools of deep learning, reinforcement learning, and probabilistic generative learning. To draw insights from cognitive science and neuroscience, we also strive to understand the learning and memory algorithms of the brain. Despite significant advancements in large language models, current deep learning approaches still lack the higher cognitive functions needed for human-like and safe intelligence. Our collaboration with Prof. Yoshua Bengio at Mila aims to develop foundational deep learning algorithms that mimic the higher cognitive functions of the human prefrontal cortex, also known as System 2 Deep Learning. 20/08/26 - A research meeting with Prof. Yoshua Bengio was held at Montréal (RLC 2026). 06/21/25 - A PhD student from our lab, Junyeob Baek, joined Mila for a visiting research. 12/04/24 - The 1st KAIST-Mila Prefrontal AI Symposium is held at Mila. 11/03/24 - A research meeting with Prof. Yoshua Bengio was held in Korea. 08/12/24 - A PhD student from Mila, Ian Porada, joined MLML for a visiting research. 07/01/24 - We launch KAIST-Mila Prefrontal AI Research (PAIR) Center. This center is supported by the National Research Foundation of Korea.  I am currently an Associate Professor in the and the at and a joint appointment professor at New York University. Prior to joining KAIST, I served as an Assistant Professor of at , where I was also affiliated with the . I direct the , which operates at bo