Donghyun Kim

Talk in Pieces, See in Whole: Disentangling and Hierarchical Aggregating Representations for Language-based Object Detection

Towards Robust Referring Expression Segmentation for Complex Reasoning in the Wild

ReSafe: Enhancing Safety of Text-to-Image Diffusion via Post-Hoc Image Back Translation

Personalized Visual Representation Alignment for Generative Multimodal Recommendation

Visual Representation Alignment for Multimodal Large Language Models

Weakly Supervised Video Scene Graph Generation via Natural Language Supervision

$\text{Slerp}^{+}$: Spherical Linear Interpolation for Unified Compositional Retrieval