TUE-Detector：一种基于使用工具的专家多模态大语言模型（MLLM）的AI生成视频检测器
TUE-Detector: A Tool-Using Expert MLLM-Based Detector for AI-Generated Videos
浏览论文内容
中文总结 AI 辅助
本研究针对AI生成视频检测中识别细微非自然伪影的挑战，提出TUE-Detector框架，将通用MLLM训练为使用工具的专家检测器，通过调用工具收集证据推理检测，经大量实验验证其有效性。
中文摘要 AI 辅助
AI生成视频检测旨在区分AI生成视频与真实视频，近年来受到越来越多的研究关注。要可靠完成该任务，关键挑战在于准确识别细微但可测量的非自然伪影。本研究从工具介导的证据发现这一新颖视角应对该挑战，提出基于使用工具的专家多模态大语言模型（MLLM）的AI生成视频检测器（TUE-Detector），这是一种用于AI生成视频检测的新颖框架。TUE-Detector将通用MLLM训练为任务定制的使用工具的专家检测器，使其学会调用合适工具、收集非自然性的具体证据并对证据进行推理以实现可靠检测。同时，TUE-Detector引入新颖设计，为专家检测器配备高质量且合适的工具。大量实验证明了该框架的有效性。
英文摘要
AI-generated video detection, which aims to distinguish AI-generated videos from real ones, has recently received increasing research attention. To perform this task reliably, a key challenge lies in accurately identifying subtle-yet-measurable unnatural artifacts. In this work, we address this challenge from a novel perspective of tool-mediated evidence discovery and propose Tool-Using Expert MLLM-based AI-generated Video Detector (TUE-Detector), a novel framework for AI-generated video detection. TUE-Detector trains a general MLLM into a task-tailored tool-using expert detector that learns to invoke suitable tools, collect concrete evidence of unnaturalness, and reason over the evidence for reliable detection. Meanwhile, TUE-Detector further introduces novel designs to equip the expert detector with high-quality and suitable tools. Extensive experiments demonstrate the effectiveness of our framework.
发表机构
- University of Nottingham（诺丁汉大学）
- Lancaster University（兰卡斯特大学）
- Peking University（北京大学）
机构由 AI 辅助整理，请以论文原文为准。
