Jeongwoo Choi

🙋‍♂️ Hello, I’m Ph.D student and a member of Computer Vision Lab at Yonsei University advised by Prof. Bumsub Ham.

My research interests include computer vision, generative modeling, and efficient deep learning. Currently, I’m interested in efficient generative models that reduce computational and memory demands while maintaining generation quality. As modern generative models demand substantial computing resources, I believe designing efficient and hardware-frendly systems is essential to make generative models practical and widely usable.

If you have any questions or suggestions, please feel free to contact me via email or linkedin.

📢 News

[Sep. 2025]	One paper, AccuQuant, has been accepted to NeurIPS 2025. See you in San Diego!

🎓 Education

Ph.D. in Department of Electrical and Electronic Engineering
Yonsei University, Seoul, Korea
Mar. 2024 – Present
B.S. in Department of Electrical and Electronic Engineering
Yonsei University, Seoul, Korea
Mar. 2020 - Feb. 2024

📚 Publications

* equal contribution

NeurIPS 2025 (poster)
AccuQuant: Simulating Multiple Denoising Steps for Quantizing Diffusion Models

Seunghoon Lee^*, Jeongwoo Choi^* , Byunggwan Son, and 3 more authors

In Conference on Neural Information Processing Systems (NeurIPS), 2025

Abs Bib HTML PDF

We present in this paper a novel post-training quantization (PTQ) method, dubbed AccuQuant, for diffusion models. We show analytically and empirically that quantization errors for diffusion models are accumulated over denoising steps in a sampling process. To alleviate the error accumulation problem, AccuQuant mini5 mizes the discrepancies between outputs of a full-precision diffusion model and its quantized version within a couple of denoising steps. That is, it simulates multiple denoising steps of a diffusion sampling process explicitly for quantization, account8 ing the accumulated errors over multiple denoising steps, which is in contrast to previous approaches to imitating a training process of diffusion models, namely, minimizing the discrepancies independently for each step. We also present an efficient implementation technique for AccuQuant, together with a novel objective, which reduces a memory complexity significantly from O(n) to O(1), where n is the number of denoising steps. We demonstrate the efficacy and efficiency of AccuQuant across various tasks and diffusion models on standard benchmarks.
@inproceedings{lee2025accuquant, title = {AccuQuant: Simulating Multiple Denoising Steps for Quantizing Diffusion Models}, author = {Lee, Seunghoon and Choi, Jeongwoo and Son, Byunggwan and Moon, Jaehyeon and Jeon, Jeimin and Ham, Bumsub}, booktitle = {Conference on Neural Information Processing Systems (NeurIPS)}, year = {2025}, }