One-step Language Modeling via Continuous Denoising (arXiv 2026) [paper][project]
Chanhyuk Lee, Jaehoon Yoo, Manan Agarwal, Sheel Shah, Jerry Huang, Aditi Raghunathan, Seunghoon Hong, Nicholas M. Boffi*, Jinwoo Kim*
Reward-Agnostic Prompt Optimization for Text-to-Image Diffusion Models (arXiv 2025) [paper][code]
Semin Kim, Yeonwoo Cha, Jaehoon Yoo, Seunghoon Hong
ReDi: Rectified Discrete Flow (NeurIPS 2025) [paper] [code]
Jaehoon Yoo, Wonjung Kim, Seunghoon Hong
Simulation-Free Training of Neural ODEs on Paired Data (NeurIPS 2024) [paper] [code]
Semin Kim*, Jaehoon Yoo*, Jinwoo Kim, Yeonwoo Cha, Saehoon Kim, Seunghoon Hong
Learning to Compose: Improving Object Centric Learning by Injecting Compositionality (ICLR 2024) [paper] [code]
Whie Jung, Jaehoon Yoo, Sungjin Ahn, Seunghoon Hong
Towards End-to-End Generative Modeling of Long Videos with Memory-Efficient Bidirectional Transformers (CVPR 2023) [paper] [project]
Jaehoon Yoo, Semin Kim, Doyup Lee, Chiheon Kim, Seunghoon Hong
SetVAE: Learning Hierarchical Composition for Generative Modeling of Set-Structured Data (CVPR 2021) [paper] [code]
Jinwoo Kim*, Jaehoon Yoo*, Juho Lee, Seunghoon Hong