Back to List
TechnologyAIMobileMultimodal

MiniCPM-o: A Gemini 2.5 Flash-Level MLLM for Vision, Speech, and Full-Duplex Multimodal Live Streaming on Mobile Devices

OpenBMB has introduced MiniCPM-o, a multimodal large language model (MLLM) designed for mobile applications. This model is positioned as a Gemini 2.5 Flash-level solution, specifically tailored to handle vision, speech, and full-duplex multimodal live streaming functionalities directly on mobile devices. The announcement was made via GitHub Trending, highlighting its potential for advanced mobile-centric AI applications.

GitHub Trending
Share

OpenBMB has unveiled MiniCPM-o, an innovative multimodal large language model (MLLM) engineered to operate efficiently on mobile devices. The model is described as achieving a performance level comparable to Gemini 2.5 Flash, indicating its advanced capabilities within a compact framework suitable for mobile integration. MiniCPM-o is specifically designed to support a range of complex multimodal interactions, including visual processing, speech recognition, and full-duplex multimodal live streaming. This focus on live streaming and comprehensive multimodal input suggests its utility in applications requiring real-time processing of diverse data types on portable platforms. The project was featured on GitHub Trending, drawing attention to its potential impact on mobile AI development. The release by OpenBMB signifies a step towards bringing sophisticated AI functionalities, traditionally requiring more robust computational resources, to the ubiquitous mobile ecosystem.

Read Original Article

Related News

Technology

Microsoft's HVE Core: Streamlined Hyper-Velocity Engineering Components for Project Acceleration and Copilot Integration

Microsoft has released 'hve-core,' a collection of refined hyper-velocity engineering components designed to accelerate project initiation and enhance existing projects. These components, which include instructions, prompts, agents, and skills, are specifically developed to help projects fully leverage the capabilities of various Copilots. The initiative aims to provide essential building blocks for developers looking to optimize their workflows and integrate advanced AI assistance into their development processes.

Technology

MiroFish: A Concise and Universal Swarm Intelligence Engine for Omnipresent Prediction Trends on GitHub

MiroFish, developed by 666ghj, is introduced as a concise and universal swarm intelligence engine designed for predicting a wide range of phenomena. The project, trending on GitHub since March 9, 2026, aims to leverage collective intelligence to offer predictive capabilities across various domains. Its core functionality focuses on providing a streamlined and adaptable solution for 'predicting all things,' highlighting its broad applicability in the realm of intelligent systems.

Technology

Alibaba's Page Agent: A JavaScript GUI Proxy for Natural Language Web Interface Control

Alibaba has released 'Page Agent,' a JavaScript-based GUI proxy designed to enable natural language control over web page interfaces. This tool, currently trending on GitHub, aims to simplify web interaction by allowing users to manage graphical user interfaces within web pages using natural language commands. The project is developed by Alibaba and was published on March 9, 2026.