Wonjae Kim / 김원재
ML/HCI Research Scientist
I am a research scientist at Naver AI LAB. Prior to joining Naver, I worked as a research scientist at Kakao. I completed my M.Sc. and B.Sc. in computer science and engineering at Seoul National University.
I am interested in the following research topics:
- Multimodal (Vision-and-Language) Representation Learning
- Self-supervised Representation Learning
- Human-Computer Interaction
- Information Visualization
selected publications
news
2024/07 | One ECCV-2024 oral paper to appear: HYPE: Hyperbolic Entailment Filtering for Underspecified Images and Texts. |
---|---|
2024/07 | One TMLR paper: CompoDiff: Versatile Composed Image Retrieval With Latent Diffusion |
2024/05 | One ICML-2024 paper to appear: STELLA: Continual Audio-Video Pre-training with Spatio-Temporal Localized Alignment. |
2024/04 | One CVPR-2024 Synthetic Data for Computer Vision workshop paper: CompoDiff: Versatile Composed Image Retrieval With Latent Diffusion. |
2024/04 | One CHIL-2024 paper to appear: Vision-Language Generative Model for View-Specific Chest X-ray Generation. |