StreamReady：学习在长流式视频中何时回答与回答什么
StreamReady: Learning What to Answer and When in Long Streaming Videos
提出了一种基于证据窗口的时序就绪度机制，可集成到流式视频理解模型中，实现证据出现时及时回答，避免过早或过晚响应。
原文依据 a lightweight readiness mechanism that decides if sufficient evidence has been observed before responding
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论流式视频理解常涉及时间敏感场景，模型需要在支持性视觉证据出现时准确回答：在证据出现前回答属于推测，在证据过去后回答则降低实时效用。为刻画这一行为，我们引入流式视频理解的就绪感知公式，并提出答案就绪度分数（ARS），一种具有非对称早到和迟到惩罚的时间感知目标。结合正确性，ARS 定义了一种有效准确率，不仅衡量模型是否正确，还衡量模型是否在适当时机回答。基于此公式，我们提出 StreamReady，一个通过轻量级就绪机制将时序推理与准时回答统一的框架，该机制在响应前判断是否已观察到足够证据。为评估这一能力，我们进一步引入 ProReady-QA，一个包含标注答案证据窗口和跨局部与全局上下文主动多轮问题的基准。StreamReady 在 ProReady-QA 上取得优异性能，并在八个额外的流式和离线长视频基准上持续优于先前方法，展现出稳健且广泛泛化的视频理解能力。
英文原文摘要 1310 字符
Streaming video understanding often involves time-sensitive scenarios where models need to answer exactly when the supporting visual evidence appears: answering before the evidence reflects speculation, answering after it has passed reduces real-time utility. To capture this behavior, we introduce a readiness-aware formulation of streaming video understanding with the **Answer Readiness Score (ARS)**, a timing-aware objective with asymmetric early and late penalties. When combined with correctness, ARS defines an effective accuracy that measures not just whether a model is right, but whether it answers at the appropriate moment. Building on this formulation, we introduce **StreamReady**, a framework to unify temporal reasoning with on-time answering through a lightweight readiness mechanism that decides if sufficient evidence has been observed before responding. To evaluate this capability, we further introduce **ProReady-QA**, a benchmark with annotated answer evidence windows and proactive multi-turn questions across local and global contexts. StreamReady achieves superior performance on ProReady-QA, and consistently outperforms prior methods across eight additional streaming and offline long-video benchmarks, demonstrating robust and broadly generalizable video understanding capability.