用强化学习检测假视频，还能解释为啥是假的。
VidGuard-R1: AI-Generated Video Detection and Explanation via Reasoning MLLMs and RL
- 用强化学习探索多种推理路径，发现视频中的物理矛盾
- 在14万对视频上训练，零样本检测准确率领先
- 能给出可验证的判断理由，适合需要解释性的场景
AI生成视频的迅速扩散亟需高精度且可解释的检测工具。现有基于多模态大模型（MLLM）的检测方法依赖监督微调（SFT）或直接偏好优化（DPO），但受限于静态标注数据集，难以捕捉现代生成模型产生的多步物理不一致。为此，我们提出VidGuard-R1，首个采用组相对策略优化（GRPO）的视频真伪检测器。它通过强化学习框架主动探索并排序多种推理路径，引入时序稳定性与扩散感知复杂度奖励模型，激励模型发现“物理基准”异常。贡献包括：(1) 构建包含14万对难例的真实/伪造视频数据集；(2) 基于GRPO的训练范式实现当前最优零样本性能；(3) 采用推理优先架构，提供精确可验证的鉴伪依据。
原文摘要 · Abstract (English)
The rapid proliferation of AI-generated video necessitates robust detection tools that offer both high accuracy and human-interpretable explanations. While existing MLLM-based detectors rely on supervised fine-tuning (SFT) or direct preference optimization (DPO), these methods are often bottlenecked by static, pre-labeled datasets that fail to capture the evolving, multi-step physical inconsistencies of modern generative models. To bridge this gap, we introduce VidGuard-R1, the first video authenticity detector to utilize group relative policy optimization (GRPO). Moving beyond passive preference matching, VidGuard-R1 employs a reinforcement learning framework that encourages the model to explore and rank multiple reasoning paths. By introducing specialized reward models for temporal stability and diffusion-aware complexity, we incentivize the model to discover 'physics-grounded' artifacts. Our contributions include: (1) a curated dataset of 140,000 challenging real/fake video pairs; (2) a GRPO-based training paradigm that achieves state-of-the-art zero-shot performance; and (3) a reasoning-first architecture that provides precise, verifiable rationales for its forensic judgments. Project website: https://vidguard-r1.github.io/.
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。