Jun Hu

Vision-based tactile sensors could revolutionize robotic interaction by providing high-resolution tactile data that enhances perception and manipulation capabilities.

A single foundation model can effectively leverage heterogeneous cardiac signals to achieve superior performance across multiple tasks, defying the limitations of modality-specific training.

NodeImport reveals that strategically filtering nodes based on importance can dramatically enhance GNN performance in imbalanced settings.

Localized ASR models could revolutionize human-robot interaction by enabling more intuitive and responsive communication in real-time environments.