Donghyun Kim
6 papers · 47 citations
Most-cited papers
- Visual Delta Generator With Large Multi-modal Models For Semi-supervised Composed Image Retrieval2024 · 15 citations
- MULE: Multimodal Universal Language Embedding2019 · 15 citations
- Learning To Scale Multilingual Representations For Vision-language Tasks2020 · 10 citations
- MATE: Meet At The Embedding -- Connecting Images With Long Texts2024 · 4 citations
- Efficient And Versatile Robust Fine-tuning Of Zero-shot Models2024 · 3 citations
Topics