선도 연구 주제

고차원 생성 파운데이션 모델

이 연구는 영상, 시계열, 분자 구조처럼 복잡한 고차원 데이터를 다루는 생성 파운데이션 모델에 필요한 원천 기술을 개발합니다. 단순한 통계적 상관을 넘어 현실의 물리·생물학 법칙을 따르도록 하는 것이 핵심입니다. 이러한 충실한 AI 원칙 아래, 의료 영상부터 소재 과학, 산업 검사에 이르는 분야에서 초고해상도 이미지와 영상 생성을 구현합니다.

자세히 보기 →

COD-VAE — class-conditioned 3D shape generation (chair, car) vs VecSet baselines — “Representing 3D Shapes with 64 Latent Vectors for 3D Diffusion Models” · ICCV 2025

연구논문 목록

고차원 생성 파운데이션 모델

# High-dimensional Generative Foundation Models

AM-Adapter: Appearance Matching Adapter for Exemplar-based Semantic Image Synthesis in-the-Wild

Siyoon Jin, Jisu Nam, Jiyoung Kim, Dahyun Chung, Yeong-Seok Kim, Joonhyung Park, Heonjeong Chu, Seungryong Kim · ICCV · 2025

# High-dimensional Generative Foundation Models

Sparsely Labeled fMRI Data Denoising with Meta-Learning-Based Semi-Supervised Domain Adaptation

Keun-Soo Heo, Ji-Wung Han, Soyeon Bak, Minjoo Lim, Bogyeong Kang, Sang-Jun Park, Weili Lin, Han Zhang, Dinggang Shen, Tae-Eui Kam · MICCAI · 2025

# High-dimensional Generative Foundation Models

Sparse3Diff: A Diffusion Framework for 3D Reconstruction from Sparse 2D Slices in Volumetric Optical Imaging

Hyun Jung Lee, Eunjung Jo, Minjoo Lim, Young-Han Son, Bogyeong Kang, Hyeonyeong Nam, Ji-Hoon Jeong, Dong-Hee Shin, Tae-Eui Kam · MICCAI · 2025

# High-dimensional Generative Foundation Models

Pre-to-Post Operative MRI Generation with Retrieval-Based Visual In-Context Learning

Bogyeong Kang, Sang-Jun Park, Minjoo Lim, Myeongkyun Kang, Keun-Soo Heo, Ji-Hye Oh, Hyun Jung Lee, Tae-Eui Kam · MICCAI · 2025

# High-dimensional Generative Foundation Models

Diverse Sharpness-Aware Minimization for Machine Learning Force Fields in Semiconductor Simulations

Dong-Hee Shin, Young-Han Son, Tae-Eui Kam · ISOCC · 2025

# High-dimensional Generative Foundation Models

Perturb a Model, Not an Image: Towards Robust Privacy Protection via Anti-Personalized Diffusion Models

Tae-Young Lee, Juwon Seo, Jong Hwan Ko, Gyeong-Moon Park · NeurIPS · 2025

연구논문 더 보기 →