BISPL- BioImaging, Signal Processing & Learning Lab @ KAIST AI
  • 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
LLM-driven multimodal target volume contouring in radiation oncology

Yujin Oh et al,  Nature Communications, 2024.

See more

Congratulations! Five papers accepted for CVPR 2025.

2/26/2025

 
Congratulations!  Five papers have been accepted for CVPR 2025! The list is as follows:​
  1. Soobin Um, Jong Chul Ye, "Minority-Focused Text-to-Image Generation via Prompt Optimization", IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025.
  2. Hyelin Nam, Jaemin Kim, Dohun Lee, Jong Chul Ye,"Optical-Flow Guided Prompt Optimization for Coherent Video Generation", IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025.
  3. Won Jun Kim, Hyungjin Chung, Jaemin Kim, Sangmin Lee, Byeongsu Sim, Jong Chul Ye,"Derivative-Free Diffusion Manifold-Constrained Gradient for Unified XAI", IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025.
  4. Dohun Lee, Bryan Sangwoo Kim, Geon Yeong Park, Jong Chul Ye,"VideoGuide: Improving Video Diffusion Models without Training Through a Teacher's Guide", IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025.
  5. Hyeonho Jeong, Chun-Hao Paul Huang, Jong Chul Ye, Niloy Mitra, Duygu Ceylan, "Track4Gen: Teaching Video Diffusion Models to Track Points Improves Video Generation", IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025.

Congratulations! Two BISPL alumni have become tenure-track faculty members.

2/17/2025

 
We are proud to announce that two BISPL alumni have been appointed as tenure-track faculty members starting from the spring semester:
  • Dr. Boah Kim (PhD, 2022) – Sungkyunkwan University
  • Dr. Huisu Yoon (PhD, 2015) – Ulsan University
This brings the total number of BISPL alumni in academia to 13 faculty members!

Congratulation!  Seven papers accepted for ICLR 2025.

1/22/2025

 
The following papers from BISPL are accepted for ICLR 2025!
  1. Taesung Kwon, Jong Chul Ye, "Solving Video Inverse Problems Using Image Diffusion Models", The Thirteenth International Conference on Learning Representations (ICLR), 2025
  2. Hyungjin Chung, Jeongsol Kim, Geon Yeong Park, Hyelin Nam, Jong Chul Ye, "CFG++: Manifold-constrained Classifier Free Guidance for Diffusion Models", The Thirteenth International Conference on Learning Representations (ICLR), 2025.
  3. Jeongsol Kim, Geon Yeong Park, Hyungjin Chung, Jong Chul Ye, "Regularization by Texts for Latent Diffusion Inverse Solvers", The Thirteenth International Conference on Learning Representations (ICLR), 2025.
  4. Serin Yang, Taesung Kwon, Jong Chul Ye, "ViBiDSampler: Enhancing Video Interpolation Using Bidirectional Diffusion Sampler", The Thirteenth International Conference on Learning Representations (ICLR), 2025.
  5. Gihyun Kwon, Jong Chul Ye,"TweedieMix: Improving Multi-Concept Fusion for Diffusion-based Image/Video Generation", The Thirteenth International Conference on Learning Representations (ICLR), 2025.
  6. Beomsu Kim, Jaemin Kim, Jeongsol Kim, Jong Chul Ye,"Generalized Consistency Trajectory Models for Image Manipulation", The Thirteenth International Conference on Learning Representations (ICLR), 2025.
  7. Beomsu Kim, Yu-Guan Hsieh, Michal Klein, marco cuturi, Jong Chul Ye, Bahjat Kawar, James Thornton,"Simple ReFlow: Improved Techniques for Fast Flow Models",The Thirteenth International Conference on Learning Representations (ICLR), 2025.

Five papers accepted for ECCV 2024!!

7/2/2024

 
Congratulations!  The following five papers from BISPL are accepted for ECCV 2024.
  1. Hyeonho Jeong, Jinho Chang, Geon Yeong Park, Jong Chul Ye. "DreamMotion: Space-Time Self-Similarity Score Distillation for Zero-Shot Video Editing",  in Proceedings of 2024 European Conference on Computer Vision (ECCV).
  2. Soobin Um, and Jong Chul Ye "Self-Guided Generation of Minority Samples Using Diffusion Models",  in Proceedings of 2024 European Conference on Computer Vision (ECCV).
  3. Hyungjin Chung and Jong Chul Ye, "Deep Diffusion Image Prior for Efficient OOD Adaptation in 3D Inverse Problems",  in Proceedings of 2024 European Conference on Computer Vision (ECCV).
  4. Kwanyoung Kim, Yujin Oh, and Jong Chul Ye, "OTSeg: Multi-prompt Sinkhorn Attention for Zero-Shot Semantic Segmentation",  in Proceedings of 2024 European Conference on Computer Vision (ECCV).
  5. Jeongsol Kim, Geon Yeong Park, and Jong Chul Ye, "DreamSampler: Unifying Diffusion Sampling and Score Distillation for Image Manipulation", in Proceedings of 2024 European Conference on Computer Vision (ECCV).

Two papers are accepted for ICML 2024!

5/2/2024

 
Congratulations!  The following two papers have been accepted for ICML 2024.  
  1. Sangmin Lee, Abbas Mammadov, Jong Chul Ye, "Defining Neural Network Architecture through Polytope Structures of Dataset",  in the Proceedings of The  International Conference on Machine Learning (ICML), 2024.
  2. Hyungjin Chung, Jong Chul Ye, Peyman Milanfar, Mauricio Delbracio, "Prompt-tuning latent diffusion models for inverse problems",   in the Proceedings of The  International Conference on Machine Learning (ICML), 2024.
This year so far, we have 13 top-tier AI conference papers  (6 ICLR,  4 CVPR, 2 ICML, 1 AAA) and 7 journal papers (Nature Communications, etc.)

<<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- and medical imaging with the help of mathematics, machine learning, and physics.
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 bio-medical 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 bio-medical 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. 
CONTACT US
Bio Imaging. Signal Processing & Learning
Graduate School of AI
KAIST
108  Taebong-ro, Seocho-gu,  Seoul,  06764
Republic of Korea

Copyright (c) 2014, BISPL
All Rights Reserved.
Picture