BISPL @ KAIST

Latest Research Highlight

FILT3R: Latent Space Adaptive Kalman Filter for Streaming 3D Reconstruction

Seonghyun Jin et al., ECCV 2026

News

Jul 13, 2026	BISPL Students Awarded Funded Research Internships at Prestigious Research Institutes
Jun 18, 2026	Congratulations! Five papers accepted to ECCV 2026.
May 13, 2026	This Semester’s Global Intern Dispatch from BISPL
Apr 30, 2026	Congratulations -- Five papers (two splotlights) accepted to ICML 2026!
Feb 21, 2026	Four papers (including one in Findings) accepted to CVPR 2026!

About BISPL

BISPL —the Bio Imaging, Signal Processing, and Machine Learning Lab at KAIST AI — is led by Prof. Jong Chul Ye, an IEEE Fellow. Our research spans theory & reinforcement Learning (RL) for diffusion/flow Models, LLMs & agentic AI, vision-language-action (VLA) Models, world models, computer vision, AI for science & healthcare, and medical imaging.

Across these areas, we seek to uncover the mathematical beauty and fundamental principles of modern AI and translate them into real-world impact. We ask not only how AI works, but why it works, developing new theories and algorithms from challenging practical problems. Building on deep expertise in biomedical imaging, signal processing, inverse problems, and machine learning, we turn real-world applications into sources of fundamental insight—and fundamental advances into transformative technologies.

Explore our people, publications, and latest news.

Most Recent Publications

[C100] FILT3R: Latent State Adaptive Kalman Filter for Streaming 3D Reconstruction

Seonghyun Jin and Jong Chul Ye

In The 19th European Conference on Computer Vision (ECCV), 2026

Bib

@inproceedings{jin2026filt3r,
  author = {Jin, Seonghyun and Ye, Jong Chul},
  title = {FILT3R: Latent State Adaptive Kalman Filter for Streaming 3D Reconstruction},
  booktitle = {The 19th European Conference on Computer Vision (ECCV)},
  year = {2026},
}

[C99] InverseCrafter: Efficient Video ReCapture as a Latent Domain Inverse Problem

Yeobin Hong, Suhyeon Lee, Hyungjin Chung, and 1 more author

In The 19th European Conference on Computer Vision (ECCV), 2026

Bib

@inproceedings{hong2026inversec,
  author = {Hong, Yeobin and Lee, Suhyeon and Chung, Hyungjin and Ye, Jong Chul},
  title = {InverseCrafter: Efficient Video ReCapture as a Latent Domain Inverse Problem},
  booktitle = {The 19th European Conference on Computer Vision (ECCV)},
  year = {2026},
}

[C98] Tiled Prompts: Overcoming Prompt Misguidance in Image and Video Super-Resolution

Bryan Sangwoo Kim, Jonghyun Park, and Jong Chul Ye

In The 19th European Conference on Computer Vision (ECCV), 2026

Bib

@inproceedings{kim2026tiled,
  author = {Kim, Bryan Sangwoo and Park, Jonghyun and Ye, Jong Chul},
  title = {Tiled Prompts: Overcoming Prompt Misguidance in Image and Video Super-Resolution},
  booktitle = {The 19th European Conference on Computer Vision (ECCV)},
  year = {2026},
}

[C97] Memory-V2V: Memory-Augmented Video-to-Video Diffusion for Consistent Multi-Turn Editing

Dohun Lee, Chun-Hao Paul Huang, Xuelin Chen, and 3 more authors

In The 19th European Conference on Computer Vision (ECCV), 2026

Bib

@inproceedings{lee2026memoryv2,
  author = {Lee, Dohun and Huang, Chun-Hao Paul and Chen, Xuelin and Ye, Jong Chul and Ceylan, Duygu and Jeong, Hyeonho},
  title = {Memory-V2V: Memory-Augmented Video-to-Video Diffusion for Consistent Multi-Turn Editing},
  booktitle = {The 19th European Conference on Computer Vision (ECCV)},
  year = {2026},
}

[C96] 3D-ReGen: A Unified 3D Geometry Regeneration Framework

Geon Yeong Park, Roman Shapovalov, Rakesh Ranjan, and 3 more authors

In he 19th European Conference on Computer Vision (ECCV), 2026

Bib

@inproceedings{park20263dregen,
  author = {Park, Geon Yeong and Shapovalov, Roman and Ranjan, Rakesh and Ye, Jong Chul and Vedaldi, Andrea and Nguyen-Phuoc, Thu},
  title = {3D-ReGen: A Unified 3D Geometry Regeneration Framework},
  booktitle = {he 19th European Conference on Computer Vision (ECCV)},
  year = {2026},
}

[C95] Unifying Masked Diffusion Models with Various Generation Orders and Beyond

Chunsan Hong, Sanghyun Lee, and Jong Chul Ye

In International Conference on Machine Learning ( ICML ), 2026

spotlight, top 2.2%

Bib

@inproceedings{hong2026unifying,
  author = {Hong, Chunsan and Lee, Sanghyun and Ye, Jong Chul},
  title = {Unifying Masked Diffusion Models with Various Generation Orders and Beyond},
  booktitle = {International Conference on Machine Learning ( ICML )},
  year = {2026},
  note = {spotlight, top 2.2\%},
}