Dongjun Kim
Dongjun Kim
I am a postdoctoral scholar at Prof. Stefano Ermon's group. My main research interest is in generative AI. My goal is to develop a simple yet effective new framework for the generation task that can broadly impact our real life.
Before joining Stanford, I worked with SONY AI. Also, I got Ph.D. at KAIST in 2023, advised by Prof. Il-Chul Moon.
Contact: dongjun@stanford.edu
Dongjun Kim*, Chieh-Hsin Lai*, Wei-Hsiang Liao, Naoki Murata, Yuhta Takida, Toshimitsu Uesaka, Yutong He, Yuki Mitsufuji, and Stefano Ermon
International Conference on Learning Representations (ICLR) 2024
Ph.D. Thesis
Ph.D. Thesis
A Study on the Score-based Diffusion Model for Improved Training, Flexible Inference, and Efficient Sampling [pdf]
A Study on the Score-based Diffusion Model for Improved Training, Flexible Inference, and Efficient Sampling [pdf]
Best Thesis Paper Award
Advisor: Il-Chul Moon
Committee: Il-Chul Moon, Hayong Shin, Seungki Min, Stefano Ermon, Pieter Abbeel