# 面壁 MiniCPM-o 4.5 微调出多模态双工智能体 Gander

- 来源：OpenBMB (@OpenBMB)
- 发布时间：2026-09-16 21:00
- AIHOT 分数：34
- AIHOT 链接：https://aihot.news/items/cmu448jbr08u8ro4wpr06a0jp
- 原文链接：https://x.com/OpenBMB/status/2100208127702597951

## AI 摘要

开发者 @speechjsp 构建了 Gander，一个多模态双工交互智能体，将连续视听感知、实时对话与异步智能体执行整合进同一交互循环。其 Cerebellum 模块基于 MiniCPM-o 4.5 微调，并针对原生双工交互做了额外训练与系统级改进，不再把语音交互与智能体执行当作分离步骤。

## 正文

🤖 What if an AI agent could keep seeing, listening, talking, and working — all at the same time?

Developer @speechjsp built Gander, a multimodal duplex interaction agent that combines continuous audio-visual perception, real-time conversation, and asynchronous agent execution.

Gander’s Cerebellum is fine-tuned from MiniCPM-o 4.5, with additional training and system-level improvements for native duplex interaction.

Instead of treating voice interaction and agent execution as separate steps, Gander brings them together in one continuous interaction loop.