Research Interests

My research interests lie in Generative AI grounded in probabilistic principles. My work has focused on improving the robustness, efficiency, and steerability of diffusion models. Building on these insights, I am currently exploring how probabilistic modeling can enhance the training and inference of large language models. 

1. Diffusion Models

   • Robust Training: [C3, C4, C5]

   • Efficient Inference: [C9, C10]

   • Controllable Generation: [W1, C6, C8]

2. Language Models 

   • RL-based Fine-Tuning: [C7, W2, P1]

3. Others 

   • Discriminative Tasks: [C1, C2]

[P1] Preference Optimization by Estimating the Ratio of the Data Distribution [pdf]

• Yeongmin Kim, Heesun Bae, Byeonghu Na, Il-Chul Moon

[C10] Autoregressive Distillation of Diffusion Transformers [pdf][code] 

• Yeongmin Kim,  Sotiris Anagnostidis, Yuming Du, Edgar Schönfeld, Jonas K Kohler, Markos Georgopoulos, Albert Pumarola, Ali Thabet, Artsiom Sanakoyeu

• Conference on Computer Vision and Pattern Recognition  (CVPR 2025) - Oral (Top 0.7%)

[C8] Diffusion Bridge AutoEncoders for Unsupervised Representation Learning [pdf][code]

• Yeongmin Kim,  Kwanghyeon Lee,  Minsang Park, Byeonghu Na, Il-Chul Moon

• International Conference on Learning Representations (ICLR 2025) - Spotlight (Top 5.1%)

[C5] Training Unbiased Diffusion Models From Biased Dataset [pdf][code]

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

• International Conference on Learning Representations (ICLR 2024)

[C3] Refining Generative Process with Discriminator Guidance in Score-based Diffusion Models [pdf][code][media1][media2]

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

• International Conference on Machine Learning (ICML 2023) - Oral (Top 2.3%) 

KAIST, Daejeon, Korea, B.S. (Mar. 2017 - Feb. 2022) 

• Department of Industrial & Systems Engineering (ISysE)

• Department of Computer & Science (CS) (Double Major)

• Dean's List (2019 Fall & 2020 Fall)

KAIST, Daejeon, Korea, Integrated MS. & Ph.D. (Mar. 2022 - Feb. 2027 (expected)) 

• Graduate School of Data Science (GSDS)

• Transferred from an MS program in 2023. 

Shinhan AI (Mar. 2020 ~ Aug. 2020) 

• Topic: Financial AI

Meta GenAI (June. 2024 ~ Nov. 2024) 

• Topic: Diffusion Model, Efficient Inference

• Manager: Artsiom Sanakoyeu

• Preference Optimization by Estimating the Ratio of Data Distribution, Tech Talk at Upstage AI, July 18, 2025. 

Conference Reviewer 

• International Conference on Machine Learning (ICML) 2024, 2025

• Neural Information Processing System (NeurIPS) 2024, 2025

• International Conference on Learning Representations (ICLR) 2025

• Conference on Computer Vision and Pattern Recognition (CVPR) 2025

• International Conference on Artificial Intelligence and Statistics (AISTATS) 2025

Workshop Reviewer 

• FPI@ICLR 2025

• SPIGM@ICML 2023, 2024, NeurIPS 2025

• NCW@ICML 2023