StreamBridge:将您的离线视频大语言模型转变为主动流媒体助手
We present StreamBridge, a simple yet effective framework that seamlessly transforms offline Video-LLMs into streaming-capable models. It addresses two fundamental challenges in adapting existing...
StreamBridge是一个有效的框架,将离线视频大语言模型转化为流媒体模型,解决了多轮实时理解不足和缺乏主动响应的问题。通过记忆缓冲和轻量激活模型,StreamBridge构建了Stream-IT数据集,显著提升了离线视频模型的流媒体理解能力,超越了GPT-4o和Gemini 1.5 Pro等专有模型。
