Rhino

Rhino (originally MiniCPM-o-4.5) is a 9-billion-parameter end-to-end multimodal large language model with full-duplex streaming capabilities.

About

Rhino is designed for research on cross-modal temporal grounding and audio-visual understanding. It supports vision, speech, and full-duplex multimodal live streaming, enabling real-time processing of continuous video and audio input streams while generating concurrent text and speech output.

Modalities

Modality	Input	Output
Text	Yes	Yes
Image	Yes	—
Audio	Yes	Yes
Video	Yes	—

Intended Use

This model is intended for academic research on multimodal temporal reasoning, cross-modal attention analysis, and audio-visual language modeling.