{"ID":2923537,"CreatedAt":"2026-06-02T04:05:25.881865328Z","UpdatedAt":"2026-06-04T18:58:18.388484401Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.02482","arxiv_id":"2606.02482","title":"X-Stream: Exploring MLLMs as Multiplexers for Multi-Stream Understanding","abstract":"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.","short_abstract":"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 critic...","url_abs":"https://arxiv.org/abs/2606.02482","url_pdf":"https://arxiv.org/pdf/2606.02482v1","authors":"[\"Peiwen Sun\",\"Xudong Lu\",\"Huadai Liu\",\"Yang Bo\",\"Dongming Wu\",\"Huankang Guan\",\"Minghong Cai\",\"Jinpeng Chen\",\"Xintong Guo\",\"Shuhan Li\",\"Rui Liu\",\"Xiangyu Yue\"]","published":"2026-06-01T16:52:11Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}