Abstract: Spectral super-resolution (SSR) aims to enhance the spectral resolution of multispectral images (MSIs) to generate hyperspectral images (HSIs) while ...

We present MGM-Omni, an omni-chatbot capable of processing text, image, video, and speech inputs, and can generate both text and speech responses. Based on MiniGemini and MiniGemini v2 (Lyra), ...

A real-time implementation of Voice Activity Projection (VAP) is aimed at controlling behaviors of spoken dialogue systems, such as turn-taking. The VAP model takes stereo audio data (from two ...