OneStreamer：统一流式视频交互中的感知、记忆与主动响应
原标题：Paper page - OneStreamer: Unifying Perception, Memory, and Proactive Response in Streaming Video Interaction
AI 摘要
研究团队提出 OneStreamer，一个 4B 参数的流式视频交互模型，通过共享的主动生成过程统一感知、记忆与主动响应。其 Proactive Hierarchical Caption Memory（PHCM）生成带时间戳的局部细节描述与事件摘要，使模型无需回看历史视觉特征即可保留可复用的事实记忆；Proactive State Transition Learning（PSTL）仅监督 27.5% 的状态 token 即优于密集状态监督。团队还构建了包含超百万条记录的 OneStreamer-1M 数据集，该模型在八个流式视频理解基准上均取得对比方法中的最佳结果。
正文节选
OneStreamer: Unifying Perception, Memory, and Proactive Response in Streaming Video Interaction Abstract Streaming video LLMs must retain evidence before its relevance to future tasks is known and respond when sufficient evidence becomes available. The challenge is to form reusable factual memory without compromising real-time perception. We introduce OneStreamer, which jointly learns query-independent evidence recording and task response through a shared proactive generation process. Its Proact