Skyra：基于接地伪影推理的AI生成视频检测
Skyra: AI-Generated Video Detection via Grounded Artifact Reasoning
提出基于多模态大语言模型的伪影定位与推理框架，可复用于其他可解释视觉检测任务；构建的细粒度伪影标注数据集与基准为后续研究提供评测基础。
原文依据 we present Skyra, a specialized multimodal large language model (MLLM) that identifies human-perceivable visual artifacts in AI-generated videos
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论AI驱动视频生成技术的滥用已引发严重社会关切，凸显了对可靠AI生成视频检测器的迫切需求。然而，现有方法大多局限于二分类，缺乏人类可解读所需的必要解释。本文提出Skyra，一种专门的多模态大语言模型（MLLM），它能够识别AI生成视频中人类可感知的视觉伪影，并将其作为接地证据用于检测与解释。为支持这一目标，我们构建了ViF-CoT-4K用于监督微调（SFT），这是首个具有细粒度人工标注的大规模AI生成视频伪影数据集。随后，我们开发了一种两阶段训练策略，系统性地增强模型的时空伪影感知、解释能力与检测准确率。为全面评估Skyra，我们推出了ViF-Bench，一个包含由十余种最优视频生成器生成的3K高质量样本的基准。大量实验表明，Skyra在多个基准上超越现有方法，同时我们的评估为推进可解释的AI生成视频检测提供了宝贵见解。我们的代码、模型与数据集将公开。
英文原文摘要 1324 字符
The misuse of AI-driven video generation technologies has raised serious social concerns, highlighting the urgent need for reliable AI-generated video detectors. However, most existing methods are limited to binary classification and lack the necessary explanations for human interpretation. In this paper, we present Skyra, a specialized multimodal large language model (MLLM) that identifies human-perceivable visual artifacts in AI-generated videos and leverages them as grounded evidence for both detection and explanation. To support this objective, we construct ViF-CoT-4K for Supervised Fine-Tuning (SFT), which represents the first large-scale AI-generated video artifact dataset with fine-grained human annotations.We then develop a two-stage training strategy that systematically enhances our model's spatio-temporal artifact perception, explanation capability, and detection accuracy. To comprehensively evaluate Skyra, we introduce ViF-Bench, a benchmark comprising 3K high-quality samples generated by over ten state-of-the-art video generators. Extensive experiments demonstrate that Skyra surpasses existing methods across multiple benchmarks, while our evaluation yields valuable insights for advancing explainable AI-generated video detection. Our code, models, and datasets will be made publicly available.