用强化微调提升视频异常理解的推理能力，让AI看得懂、说得清异常事件。
VAU-R1: Advancing Video Anomaly Understanding via Reinforcement Fine-Tuning
- 基于多模态大模型，通过强化微调增强异常事件的因果推理能力。
- 在多个场景下显著提升问答准确率、时间定位和推理连贯性。
- 首次构建链式思维基准测试集，支持对推理过程的系统评估。
视频异常理解（VAU）在智慧城市场景、安防监控和灾害预警中至关重要，但因其需精细的时空感知与模糊情境下的鲁棒推理而极具挑战。现有方法常缺乏可解释性，难以捕捉异常事件的因果与上下文关系。这一问题还因缺乏针对推理能力的全面评估基准而加剧。为此，我们提出VAU-R1，一个基于多模态大语言模型（MLLMs）的数据高效框架，通过强化微调（RFT）提升异常推理能力。同时，我们构建了首个面向视频异常推理的链式思维基准（VAU-Bench），包含多项选择题、详细推理过程、时间标注和描述性字幕。实验证明，VAU-R1在多种情境下显著提升了问答准确率、时间定位精度和推理连贯性。本研究的方法与基准共同为可解释、推理驱动的视频异常理解奠定了坚实基础。代码已开源：https://github.com/GVCLab/VAU-R1。
原文摘要 · Abstract (English)
Video Anomaly Understanding (VAU) is essential for applications such as smart cities, security surveillance, and disaster alert systems, yet remains challenging due to its demand for fine-grained spatio-temporal perception and robust reasoning under ambiguity. Despite advances in anomaly detection, existing methods often lack interpretability and struggle to capture the causal and contextual aspects of abnormal events. This limitation is further compounded by the absence of comprehensive benchmarks for evaluating reasoning ability in anomaly scenarios. To address both challenges, we introduce VAU-R1, a data-efficient framework built upon Multimodal Large Language Models (MLLMs), which enhances anomaly reasoning through Reinforcement Fine-Tuning (RFT). Besides, we propose VAU-Bench, the first Chain-of-Thought benchmark tailored for video anomaly reasoning, featuring multiple-choice QA, detailed rationales, temporal annotations, and descriptive captions. Empirical results show that VAU-R1 significantly improves question answering accuracy, temporal grounding, and reasoning coherence across diverse contexts. Together, our method and benchmark establish a strong foundation for interpretable and reasoning-aware video anomaly understanding. Our code is available at https://github.com/GVCLab/VAU-R1.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。