X-Stream：探索將多模態大型語言模型用作多流理解的複用器

摘要

尽管视频流理解已取得显著进展，但诸如直播体育赛事、自动驾驶及多屏协同等实际应用场景，本质上需要持续的多流交互。然而，现有基准局限于单流范式，导致在线跨流推理评估的关键空白。为填补这一空白，我们引入X-Stream——首个专为多流流式理解设计的基准。该基准涵盖932个视频中的4,220对严格筛选的问答对，评估跨多窗口、多视图及多设备场景的11项子任务。关键在于，我们采用新颖的双重验证流程构建数据集，避免对单一流的过度依赖。此外，我们率先将多模态大语言模型（MLLMs）概念化为朴素复用器，通过信号复用理论的视角系统评估其性能。大规模在线推理实验揭示了一个严峻现实：最先进的MLLMs在处理并发流时面临显著困难，仅能达到约50%的得分，且主动能力薄弱。最终，X-Stream揭示了当前复用方案的权衡，为下一代多流智能体提供了实用评估方案与实证指导。

English

While video streaming understanding has made significant strides, real-world applications, such as live sports broadcasting, autonomous driving, and multi-screen collaboration, inherently demand continuous, multi-stream interactions. However, existing benchmarks are confined to single-stream paradigms, leaving a critical gap in evaluating online, cross-stream reasoning. To bridge this, we introduce X-Stream, the first benchmark dedicated to multi-stream streaming understanding. Comprising 4,220 rigorously curated QA pairs across 932 videos, X-Stream evaluates 11 subtasks across multi-window, multi-view, and multi-device scenarios. Crucially, our dataset is constructed using a novel dual-verification pipeline that prevents over-reliance on a single stream. Furthermore, we pioneer the conceptualization of multi-modal large language models (MLLMs) as naive multiplexers, systematically evaluating their performance through the lens of Signal Multiplexing Theory. Our extensive online inference experiments reveal a stark reality: state-of-the-art MLLMs struggle significantly with concurrent streams, achieving only about 50% score and exhibiting poor proactive ability. Ultimately, X-Stream exposes the trade-off of current multiplexing schemes, providing both a practical evaluation protocol and empirical guidance for next-generation multi-stream agents.