Existing forgery detection methods are often limited to uni-modal or bi-modal settings, failing to handle the interleaved text, images, and videos prevalent in real-world misinformation. To bridge this gap, this paper targets to develop a unified framework for omnibus vision-language forgery detection and grounding. In this unified setting, the {interplay} between diverse modalities and the dual requirements of simultaneous detection and localization pose a critical ``difficulty bias`` problem: the simpler veracity classification task tends to dominate the gradients, leading to suboptimal performance in fine-grained grounding during multi-task optimization. To address this challenge, we propose \textbf{OmniVL-Guard}, a balanced reinforcement learning framework for omnibus vision-language forgery detection and grounding. Particularly, OmniVL-Guard comprises two core designs: Self-Evolving CoT Generatio and Adaptive Reward Scaling Policy Optimization (ARSPO). {Self-Evolving CoT Generation} synthesizes high-quality reasoning paths, effectively overcoming the cold-start challenge. Building upon this, {Adaptive Reward Scaling Policy Optimization (ARSPO)} dynamically modulates reward scales and task weights, ensuring a balanced joint optimization. Extensive experiments demonstrate that OmniVL-Guard significantly outperforms state-of-the-art methods and exhibits zero-shot robust generalization across out-of-domain scenarios.

翻译：现有的伪造检测方法通常局限于单模态或双模态设置，难以处理现实世界虚假信息中普遍存在的交错文本、图像和视频。为弥补这一差距，本文旨在开发一个统一的框架，用于全方位视觉语言伪造检测与定位。在此统一设置下，多种模态间的相互作用以及同时进行检测与定位的双重要求，引发了一个关键的“难度偏差”问题：较简单的真实性分类任务倾向于主导梯度，导致在多任务优化过程中细粒度定位的性能欠佳。为解决这一挑战，我们提出了 **OmniVL-Guard**，一个用于全方位视觉语言伪造检测与定位的平衡强化学习框架。具体而言，OmniVL-Guard 包含两个核心设计：自演进思维链生成与自适应奖励缩放策略优化（ARSPO）。自演进思维链生成能够合成高质量的推理路径，有效克服冷启动挑战。在此基础上，自适应奖励缩放策略优化（ARSPO）动态调整奖励尺度与任务权重，确保平衡的联合优化。大量实验表明，OmniVL-Guard 显著优于现有最先进方法，并在领域外场景中展现出零样本鲁棒泛化能力。