Multimodality
概念
核心技术
One model, many senses: text, image, audio, video in a single network.
您正在查看一条概念解释记录：该术语的通俗含义，以及它所关联的各条目。
Modern frontier models are natively multimodal — trained on interleaved text, images and audio so the same weights can watch, listen, read and respond. GPT-4o's real-time voice and Gemini's video understanding mark the shift; robotics VLAs extend it to action. Each added modality multiplies training-data and compute appetite.
它如何与整个技术栈相连
本记录的关联链接一览——点击分组可直接跳转。
来源
记录审阅截至 2026-01-15 — 查看 方法论.