StreamFlow：用于流视频理解的动态内存流
StreamFlow: Dynamic Memory Flows for Streaming Video Understanding
浏览论文内容
中文总结 AI 辅助
StreamFlow是一种动态视觉内存框架，通过中期内存过滤冗余、长期内存整合潜变量及注意力检索，在流视频理解任务中实现最优性能，同时提升视觉依据性并降低延迟与内存。
中文摘要 AI 辅助
流视频理解要求多模态大语言模型（MLLMs）在严格的因果性和有限内存约束下，保留来自持续演进流的相关证据。然而现有范式仍存在局限：基于模型的方法需要对主干进行侵入式更新，而基于内存的方法会在时间冗余内容上消耗大量视觉编码计算，并依赖对视觉历史的刚性访问。为解决这些局限，我们提出StreamFlow，一种高效的视觉内存框架，支持对历史视觉信息的动态按需访问。StreamFlow结合了轻量的、感知动态的中期内存（在视觉编码前过滤时间冗余）与潜在长期内存（将历史视频内容整合为后续推理可访问的视觉潜变量）。在生成过程中，注意力引导的检索机制会在模型对视觉证据的依赖减弱时注入相关视觉潜变量。StreamFlow在StreamingBench上达到了67.73%的总体准确率，实现了流视频理解的最优性能，同时在离线长视频基准上也表现出色。相较于基准设置，它将视觉注意力得分（VAS）提升了59.1%，同时将端到端延迟和峰值内存分别降低了50.4%和21.1%，实现了更具视觉依据且更高效的推理。
英文摘要
Streaming video understanding requires multimodal large language models (MLLMs) to preserve relevant evidence from continuously evolving streams under strict causality and bounded memory. Yet existing paradigms remain limited: model-based methods require intrusive backbone updates, while memory-based methods expend substantial visual-encoding computation on temporally redundant content and rely on rigid access to visual history. To address these limitations, we introduce StreamFlow, an efficient visual memory framework that enables dynamic, on-demand access to historical visual information. StreamFlow combines a lightweight, dynamics-aware mid-term memory that filters temporal redundancy before visual encoding with a latent long-term memory that consolidates historical video content into visual latents accessible to subsequent reasoning. During generation, an attention-guided retrieval mechanism injects relevant visual latents when the model's reliance on visual evidence weakens. StreamFlow achieves state-of-the-art streaming video understanding performance, reaching 67.73% overall accuracy on StreamingBench, while also delivering strong performance on offline long-video benchmarks. Relative to the vanilla setting, it improves the visual attention score (VAS) by 59.1% while reducing end-to-end latency and peak memory by 50.4% and 21.1%, respectively, enabling more visually grounded and efficient reasoning.
