让AI自判是否需要推理，高效识别假图
Fake-HR1: Rethinking Reasoning of Vision Language Model for Synthetic Image Detection
- 根据图像生成特征动态决定是否启动推理
- 比现有模型检测准确率更高，响应速度提升显著
- 适合需要快速判断合成图像的场景
近期研究证明，在检测流程中引入链式思维（CoT）可提升模型识别合成图像的能力。然而，过长的推理过程带来大量资源开销，尤其在明显伪造图像上显得冗余。为此，我们提出 Fake-HR1，据我们所知首个能基于生成检测任务特性自适应判断是否需要推理的大规模混合推理模型。通过两阶段训练框架实现：先进行混合微调（HFT）冷启动初始化，再采用在线强化学习与混合推理分组策略优化（HGRPO）隐式学习何时选择合适推理模式。实验表明，Fake-HR1 能在不同查询类型下自适应执行推理，在推理能力与生成图像检测性能上均优于现有大语言模型，同时显著提升响应效率。
原文摘要 · Abstract (English)
Recent studies have demonstrated that incorporating Chain-of-Thought (CoT) reasoning into the detection process can enhance a model's ability to detect synthetic images. However, excessively lengthy reasoning incurs substantial resource overhead, including token consumption and latency, which is particularly redundant when handling obviously generated forgeries. To address this issue, we propose Fake-HR1, a large-scale hybrid-reasoning model that, to the best of our knowledge, is the first to adaptively determine whether reasoning is necessary based on the characteristics of the generative detection task. To achieve this, we design a two-stage training framework: we first perform Hybrid Fine-Tuning (HFT) for cold-start initialization, followed by online reinforcement learning with Hybrid-Reasoning Grouped Policy Optimization (HGRPO) to implicitly learn when to select an appropriate reasoning mode. Experimental results show that Fake-HR1 adaptively performs reasoning across different types of queries, surpassing existing LLMs in both reasoning ability and generative detection performance, while significantly improving response efficiency.
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。