Prof. Mingyu Kim - Kookmin University AI·SW Graduate School

Research Overview 연구 개요

Research focuses on safe AI, generative models, probabilistic models, generalization, few-shot learning, meta-learning, Bayesian models, and variational inference. Recent work includes safety-guided diffusion generation and training-free safe denoisers.

안전한 AI, 생성 모델, 확률 모델, 일반화, 퓨샷 학습, 메타 학습, 베이지안 모델, 변분 추론을 중심으로 연구하고 있습니다. 최근에는 안전성 기반 확산 모델 생성 및 학습 없이 작동하는 안전한 디노이저 연구를 수행하고 있습니다.

Research Areas 연구 분야

Safe AI
Generative Models
Probabilistic Models
Few-shot Learning
Meta-Learning

안전한 AI
생성 모델
확률 모델
퓨샷 학습
메타 학습

Major Achievements 주요 연구 성과

Safety-Guided Flow (SGF) for safe generation - ICLR 2026 Oral (Top 1.2%)
Training-free safe denoisers for diffusion models (NeurIPS 2025)
Neural Processes with Stochastic Attention (ICLR 2022)

Honors & Awards 수상

Top Reviewer, NeurIPS 2025
Best Reviewer, AISTATS 2025
2nd Winner, ML4CO Challenge, NeurIPS 2021

Recent Publications 주요 논문

M. Kim, Y.-H. Kim, and M. Park, "Safety-Guided Flow (SGF): A Unified Framework for Negative Guidance in Safe Generation," ICLR (Oral), 2026
M. Kim, D. Kim, A. Yusuf, S. Ermon, and M. Park, "Training-Free Safe Denoisers For Safe Use of Diffusion Models," NeurIPS, 2025
M. Kim, J. Ko, and M. Park, "Bayesian Principles Improve Prompt Learning In Vision-Language Models," AISTATS, 2025
J.-S. Kim, M. Kim, G.-U. Kim, T.-H. Oh, and J.-H. Kim, "Factorized Multi-Resolution HashGrid for Efficient Neural Radiance Fields," IEEE RA-L / ICRA, 2025
M. Kim, J.-S. Kim, S.-Y. Yun, and J.-H. Kim, "Synergistic Integration of Coordinate Network and Tensorial Feature for Improving Neural Radiance Fields from Sparse Inputs," ICML, 2024
M. Kim, J. Lee, L. Choi, and M. Choi, "PolarGAN: Creating Realistic Arctic Sea Ice Concentration Images with User-Defined Geometric Preferences," Engineering Applications of Artificial Intelligence, 2023
M. Kim, K. R. Go, and S.-Y. Yun, "Neural Processes with Stochastic Attention: Paying more attention to the context dataset," ICLR, 2022
M. Kim, K. Yoo, and N. Kwak, "Position-based Scaled Gradient for Model Quantization and Sparse Training," NeurIPS, 2020