BISPL @ KAIST AI - BioImaging, Signal Processing, & machine Learning lab.
  • BISPL News
  • Professor
  • Members
  • Research Theme
  • Publications
  • BISPL Hall of Fame

Latest Research Highlight
PromptLoop: Plug-and-Play Prompt Refinement via Latent Feedback for Diffusion Model Alignment 

Suhyeon Lee et al,  CVPR 2026.

See more

This Semester’s Global Intern Dispatch from BISPL

5/13/2026

 
A little belated, but congratulations to seven BISPL students on starting their global internships this semester!
  • Suhyeon Lee, Adobe Research, UK
  • Chang Sun Lee, Siemens Corporate Research, USA
  • Jang Ho Park, Microsoft Research, USA
  • Jemin Kim,   Sony Research, Japan
  • ByungHee Cha, Sony Research, Japan
  • Beomsu Kim, Sony Research, Japan
  • Chunsan Hong, Sony Research, Japan

Congratulations -- Five papers (two splotlights) accepted to ICML 2026!

4/30/2026

 
Many congulations to the authors! The following papers have  been accepted to ICML 2026.
  • Chunsan Hong, Sanghyun Lee, Jong Chul Ye, "Unifying Masked Diffusion Models with Various Generation Orders and Beyond", International Conference on Machine Learning (ICML), 2026 (spotlight, top 2.2%)
  • Jaemin Kim, Hangeol Chang, Hyunmin Hwang, Choonghan Kim, Jong Chul Ye,"Universal Reasoner: A Single, Composable Plug-and-Play Reasoner for Frozen LLMs", International Conference on Machine Learning (ICML), 2026 
  • Jaa-Yeon Lee, Yeobin Hong, Taesung Kwon, Jong Chul Ye,"Alignment-Guided Score Matching for Text-to-Image Alignment in Diffusion Models",  International Conference on Machine Learning (ICML), 2026 (spotlight, top 2.2%)
  • Beomsu Kim, ByungHee Cha, Jong Chul Ye,"Align Your Trajectory Tangent: Training Better Consistency Models via Manifold-Aligned Tangents", International Conference on Machine Learning (ICML), 2026 
  • Jinho Chang, Changsun Lee, Hyungjin Chung, Jong Chul Ye,"ContrastiveCFG: Guiding Diffusion Sampling by Contrasting Positive and Negative Concepts",International Conference on Machine Learning (ICML), 2026 


Four papers (including one in Findings) accepted to CVPR 2026!

2/21/2026

 
The following papers have  been accepted to CVPR 2026. Congratulations for all authors!
  • Suhyeon Lee, Jong Chul Ye, "PromptLoop: Plug-and-Play Prompt Refinement via Latent Feedback for Diffusion Model Alignment",  in Proceedings of The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR),  2026.
  • Byeongjun Park, Byung-Hoon Kim, Hyungjin Chung, Jong Chul Ye,"ReDirector: Creating Any-Length Video Retakes with Rotary Camera Encoding", in Proceedings of The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR),  2026.
  • Taesung Kwon, Lorenzo Bianchi, Lennart Wittke, Felix Watine, Fabio Carrara, Jong Chul Ye, Romann M. Weber, Vinicius C. Azevedo, "Reviving ConvNeXt for Efficient Convolutional Diffusion Models",  in Proceedings of The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR),  2026.
  • Jangho Park, Taesung Kwon, Jong Chul Ye, "Zero4D: Training-Free 4D Video Generation From Single Video Using Off-the-Shelf Video Diffusion Models", in Proceedings of The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Findings,  2026.

Congratulations to BISPL's New Tenure-Track Faculty

2/20/2026

 
Congratulations! The following BISPL alumnus has been appointed as a tenure-track assistant professor, effective Spring 2026. To date, BISPL has placed 19 alumni in faculty positions in academia.
  • Yujin Oh (PhD. 2024. 2):  Yonsei University,  Assistant Professor (Spring 2026)​

Congratulations -- five papers accepted to ICLR 2026!

1/26/2026

 
We’re pleased to announce that the following papers have been accepted to ICLR 2026. Congratulations to all authors!​
  1. Jinho Chang, Jaemin Kim, Jong Chul Ye, "Training-Free Reward-Guided Image Editing via Trajectory Optimal Control",  in Proceedings of The Fourteenth International Conference on Learning Representations  (ICLR), 2026.
  2. Chunsan Hong, Seonho An, Min-Soo Kim, Jong Chul Ye,"Improving Discrete Diffusion Unmasking Policies Beyond Explicit Reference Policies", in Proceedings of The Fourteenth International Conference on Learning Representations  (ICLR), 2026.
  3. Jeongjae Lee, Jong Chul Ye, "PCPO: Proportionate Credit Policy Optimization for Preference Alignment of Image Generation Models",  in Proceedings of The Fourteenth International Conference on Learning Representations  (ICLR), 2026.
  4. Jeongsol Kim, Yeobin Hong, Jonghyun Park, Jong Chul Ye, "FlowAlign: Trajectory-Regularized, Inversion-Free Flow-based Image Editing", in Proceedings of The Fourteenth International Conference on Learning Representations  (ICLR), 2026.
  5. Byungjun Kim, Soobin Um, Jong Chul Ye,"Diverse Text-to-Image Generation via Contrastive Noise Optimization", in Proceedings of The Fourteenth International Conference on Learning Representations  (ICLR), 2026.
<<Previous

    BISPL@KAIST AI

    BISPL is a group of people at KAIST who are eager to dedicate their time and effort to investigate the beauty of bio-imaging, signal processing and machine learning for various applications like healthcare, computer vision,  scientific discovery, etc.
ABOUT US
Our research activities are primarily focused on the signal processing and machine learning  for high-resolution high-sensitivity image reconstruction from real world bomedical imaging systems. Such problems pose interesting challenges that often lead to investigations of fundamental problems in various branches of physics, mathematics, signal processing, biology, and medicine. While most of the biomedical imaging researchers are interested in addressing this problem using off-the-self tools from signal processing, machine learning, statistics, and optimization and combining their domain-specific knowledge, our approaches are unique in the sense that I believe that actual  imaging applications are a source of endless inspiration for new mathematical theories and we are eager to solve both specific applications and application-inspired fundamental theoretical problems. 
Our location
Graduate School of AI
KAIST
108  Taebong-ro, Seocho-gu,  Seoul,  06764
Republic of Korea

Copyright (c) 2025, BISPL
All Rights Reserved.
Picture
Advertisement
Advertisement