Publications

(J: Journals, C: Conferences, *: Equal contribution)

1st Authored Papers

[C4] Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion [pdf][code][project]

• 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

[C3] Refining Generative Process with Discriminator Guidance in Score-based Diffusion Models [pdf][code]

• Dongjun Kim*, Yeongmin Kim*, Se Jung Kwon, Wanmo Kang, and Il-Chul Moon

• International Conference on Machine Learning (ICML) 2023

• Oral Presentation (Top 2.37%)

[C2] Maximum Likelihood Training of Implicit Nonlinear Diffusion Models [pdf][code]

• Dongjun Kim*, Byeonghu Na*, Se Jung Kwon, Dongsoo Lee, Wanmo Kang, and Il-Chul Moon

• Neural Information Processing Systems (NeurIPS) 2022

[C1] Soft Truncation: A Universal Training Technique of Score-based Diffusion Model for High Precision Score Estimation [pdf][code]

• Dongjun Kim, Seungjae Shin, Kyungwoo Song, Wanmo Kang, and Il-Chul Moon

• International Conference on Machine Learning (ICML) 2022

[J2] Sequential Likelihood-Free Inference with Neural Proposal [pdf][code]

• Dongjun Kim, Kyungwoo Song, YoonYeong Kim, Yongjin Shin, Wanmo Kang, Il-Chul Moon, and Weonyoung Joo

• Pattern Recognition Letters (PRL) 2023

[J1] Automatic Calibration of Dynamic and Heterogeneous Parameters in Agent-based Models [pdf][code]

• Dongjun Kim, Tae-Sub Yun, Il-Chul Moon, and Jang Won Bae

• Journal of Autonomous Agents and Multi-Agent Systems (AAMAS) 2022

Co-Authored Papers

[C5] Mean-field Chaos Diffusion Models

• Sungwoo Park, Dongjun Kim, Ahmed Alaa

• International Conference on Machine Learning (ICML) 2024

• Oral Presentation (Top 1.65%)

[C4] Manifold Preserving Guided Diffusion [pdf]

• Yutong He*, Naoki Murata*,  Chieh-Hsin Lai, Yuhta Takida, Toshimitsu Uesaka, Dongjun Kim, Wei-Hsiang Liao, Yuki Mitsufuji, J Zico Kolter, Ruslan Salakhutdinov, and Stefano Ermon

• International Conference on Learning Representations (ICLR) 2024

[C3] Training Unbiased Diffusion Models from Biased Dataset [pdf]

• Yeongmin Kim, Byeonghu Na, JoonHo Jang, Minsang Park, Dongjun Kim, Wanmo Kang, and Il-Chul Moon

• International Conference on Learning Representations (ICLR) 2024

[C2] Implicit Kernel Attention [pdf][code]

• Kyungwoo Song, Yohan Jung, Dongjun Kim, and Il-Chul Moon

• Association for the Advancement of Artificial Intelligence (AAAI) 2021

[C1] Data-Driven Automatic Calibration for Validation of Agent-Based Social Simulations [pdf][code]

• Il-Chul Moon, Dongjun Kim, Tae-Sub Yun, Jang Won Bae, Dong-Oh Kang, and Euihyun Paik

• International Conference on Systems, Man, and Cybernetics (SMC) 2018

[J1] Agent-Based Model for Urban Administration: Focusing on the Traffic Aspect

• Tae-Sub Yun, Dongjun Kim, Il-Chul Moon, and Jang Won Bae

• Journal of Artificial Societies and Social Simulation (JASSS) 2022