BISPL @ KAIST AI - BioImaging, Signal Processing, & machine Learning lab.
  • BISPL News
  • Professor
  • Members
  • Research
  • Publications
  • Github
  • Software
    • NIRS-SPM
    • k-t FOCUSS
    • Compressive MUSIC
    • Super-resolution Microscopy
    • Patch Low Rank MRI
    • Sparse SPM
    • ALOHA Inpainting
    • ALOHA for MR Recon
    • MR Artifact Removal using Robust ALOHA
    • MR Ghost Artifact correction using ALOHA
  • BISPL Hall of Fame
  • Recent Talks
  • COVID-19 data link
  • BISPL Snapshots
  • On the World Press
  • Intranet

Latest Research Highlight
Chain-of-Zoom: Extreme Super Resolution via Scale Auto- Regression and Preference Alignment"  

Bryan Sangwoo Kim et al,  NeurIPS  2025.

See more

Congratulations —four papers accepted at NeurIPS 2025!

9/18/2025

 
The following papers got accepted to NeurIPS 2025. Congratulations to all authors!
  1. Bryan Sangwoo Kim, Jeongsol Kim, Jong Chul Ye, "Chain-of-Zoom: Extreme Super-Resolution via Scale Autoregression and Preference Alignment", Conference on Neural Information Processing Systems (NeurIPS), 2025.  (spotlight)
  2. Jaa-Yeon Lee, ByungHee Cha, Jeongsol Kim, Jong Chul Ye,"Aligning Text to Image in Diffusion Models is Easier Than You Think", Conference on Neural Information Processing Systems (NeurIPS), 2025.
  3. Jiachen Yao, Abbas Mammadov, Julius Berner, Gavin Kerrigan, Jong Chul Ye, Kamyar Azizzadenesheli, Anima Anandkumar, "Guided Diffusion Sampling on Function Spaces with Applications to PDEs", Conference on Neural Information Processing Systems (NeurIPS), 2025.
  4. Noam Elata, Hyungjin Chung, Jong Chul Ye, Tomer Michaeli, Michael Elad,"InvFussion: Bridging Supervised and Zero-shot Diffusion for Inverse Problems", ​Conference on Neural Information Processing Systems (NeurIPS), 2025.

Congratulation on a new IEEE T-PAMI paper!

8/4/2025

 
The following paper has been accepted to IEEE T-PAMI. Congratulations!
​
  1. Taesung Kwon, Gookho Song, Yoosun Kim, Jong Chul Ye, Mooseok Jang,"Video Diffusion Posterior Sampling for Seeing Beyond Dynamic Scattering Layers",  IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2025 (in press).

Five papers accepted to ICCV 2025!

6/25/2025

 
Congratulations! Five BISPL papers have been accepted to ICCV 2025.​
  1. Hyeonho Jeong, Suhyeon Lee, Jong Chul Ye, "Reangle-A-Video: 4D Video Generation as Video-to-Video Translation",   Proceedings of the IEEE International Conference on Computer Vision (ICCV) 2025, Hawaii.
  2. Taesung Kwon, Jong Chul Ye, "VISION-XL: High Definition Video Inverse Problem Solver using Latent Image Diffusion Models",  Proceedings of the IEEE International Conference  on Computer Vision (ICCV) 2025, Hawaii.
  3. Jaemin Kim, Bryan Sangwoo Kim, Jong Chul Ye, "Free2Guide: Training-Free Text-to-Video Alignment using Image LVLM",  Proceedings of the IEEEE International Conference on Computer Vision (ICCV) 2025, Hawaii.
  4. Jeongsol Kim, Bryan Sangwoo Kim, Jong Chul Ye,"FlowDPS : Flow-Driven Posterior Sampling for Inverse Problems", Proceedings of the IEEEE International Conference on Computer Vision (ICCV) 2025, Hawaii.
  5. Geon Yeong Park, Sang Wan Lee, Jong Chul Ye, "Inference-Time Diffusion Model Distillation",Proceedings of the IEEEE International Conference on Computer Vision (ICCV) 2025, Hawaii.​​

Five BISPL Students’ 2025 Summer Internships at Top AI Companies

6/25/2025

 
Four PhD students and 1 master students from BISPL have begun their Summer 2025 internships at  top AI companies:
  • Jeongsol Kim,   Snap Inc
  • Geon Yeong Park, Meta 
  • Taesung Kwon, Disney Research Lab
  • Doheon Lee,  Adobe Research
  • Jangho Park, Naver Labs 
Congratulations!

Congraturations!  Two papers accepted for ICML 2025

5/1/2025

 
The following two papers are accepted for ICML 2025. Congratulations to the authors!
  1. Soobin Um, Beomsu Kim, and Jong Chul Ye, "Boost-and-Skip: A Simple Guidance-Free Diffusion for Minority Generation", International Conference on Machine Learning (ICML), 2025.
  2. Jinho Chang, and Jong Chul Ye,"LDMol: Text-to-Molecule Diffusion Model with Structurally Informative Latent Space Space Surpass the AR Models", International Conference on Machine Learning (ICML), 2025.
<<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