Hyeonggon Ryu

SceneBind revolutionizes scene understanding by seamlessly integrating what and where across multiple modalities, achieving state-of-the-art retrieval and grounding capabilities.

SmellNet-V reveals that olfactory identities can be effectively paired with visual data, leading to a 7% improvement in smell classification accuracy.

Forget global alignment – fine-grained, touch-driven material segmentation in diverse, real-world scenes is now possible thanks to dense cross-modal feature interactions.