Yunji Kim

I am a research scientist at NAVER AI Lab, where I've worked on generative models and representation learning. I completed my Master's degree in Computer Science at Yonsei University under the supervision of Prof. Seon Joo Kim. Previously, I received my B.S. in Astronomy and Physics at Yonsei University.

Recently, my focus has been on detecting fake images generated by diffusion models and understanding how large models infer their outputs.

Google Scholar  /  Github  /  CV

Publications

Dense Text-to-Image Generation with Attention Modulation

Text-Conditioned Sampling Framework for Text-to-Image Generation with Masked Generative Models

Self-Supervised Set Representation Learning for Unsupervised Meta-Learning

Mutual information divergence: A unified metric for multimodal generative models

Contrastive Fine-grained Class Clustering via Generative Adversarial Networks

Unsupervised Keypoint Learning for Guiding Class-Conditional Video Prediction

Text-adaptive generative adversarial networks: manipulating images with natural language

Miscellanea

The webpage template is from this source code.