X · AI at Meta·2026-11-10 02:04· 2 小时前精选AI 评分72

Meta 发布 Muse Ember 模型，支持 1M-token 上下文与多模态输入

Today we're introducing Muse Ember, our smallest and most efficient model, built for complex reasoning execution and everyday agent work. Muse Ember can carry workflows across apps, call tools in sequence, run tests and make targeted code fixes. With a 1M-token context window and native understanding of text, images, audio and video, it can also work across large document sets and varied inputs.

AI 导读

Meta 发布 Muse Ember，称这是其最小、最高效的模型，面向复杂推理执行和日常智能体工作。该模型可跨应用承接工作流、按顺序调用工具、运行测试并做针对性代码修复，具备 1M-token 上下文窗口，原生理解文本、图像、音频和视频，可处理大规模文档集和多种输入。

打开原文x.com

选题角度

原文给出 Muse Ember 的 1M-token 上下文和多模态输入，适合围绕跨应用工作流与顺序调用工具做上手实测。

博主

AI at Meta@AIatMeta

粉丝 88万

认证：@Meta 的关联账号

We're building the future of personal superintelligence to help people create, connect, and achieve more in life.

互动数据