Can Vision-Language Models Reason about AI Edits in Images?

• URL: http://arxiv.org/abs/2607.28464v1
• Date: Thu, 30 Jul 2026 16:23:40 GMT
• Title: Can Vision-Language Models Reason about AI Edits in Images?
• Abstract summary: Vision-Language Models (VLMs) offer a promising alternative due to their strong visual understanding and reasoning capabilities.<n>We propose a GRPO-based training framework that utilizes simple accuracy and format rewards.<n>Our approach achieves competitive detection and localization performance compared to state-of-the-art image forgery detectors.
• Score: 78.04125956307838
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Detection and localization of AI-tampered images are critical for trustworthy AI, yet modern generative models have made such manipulations increasingly difficult to identify. While traditional binary classifiers can detect image tampering, they lack interpretability and generalization. Vision-Language Models (VLMs) offer a promising alternative due to their strong visual understanding and reasoning capabilities; however, existing approaches typically rely on supervised finetuning with curated explanations rather than exploiting their inherent reasoning capabilities. In this work, we investigate whether VLMs can be trained to reason about AI-generated image edits using reinforcement learning (RL) rather than explicit reasoning supervision. Motivated by the success in Group Relative Policy Optimization (GRPO), an RL technique that incentivizes the model to reason by generating thinking traces prior to giving the final answer, we propose a GRPO-based training framework that utilizes simple accuracy and format rewards. Given an input image, the model produces a structured reasoning trace and predicts whether the image has been tampered with. A lightweight segmentation model is then guided by the reasoning output to generate pixel-level localization masks. Experiments across multiple image manipulation datasets demonstrate that our approach achieves competitive detection and localization performance compared to state-of-the-art image forgery detectors, despite requiring substantially weaker supervision. We introduce effective intersection over union (eff-IoU), a unified metric to jointly evaluate detection and localization. These results suggest that reinforcement learning provides an effective and scalable mechanism for teaching VLMs to reason about AI-generated content.

Related papers

• Boosting Robust AIGI Detection with LoRA-based Pairwise Training [55.076681464804636]
  Current AIGI detectors perform admirably on clean datasets, but their detection performance decreases when deployed "in the wild"<n>We propose a novel Lo-based Pairwise Training (RA) strategy designed specifically to achieve robust detection for AIGI under severe distortions.
  arXiv  Detail & Related papers  (2026-04-14T05:35:32Z)
• From Evidence to Verdict: An Agent-Based Forensic Framework for AI-Generated Image Detection [19.240335260177382]
  We introduce AIFo (Agent-based Image Forensics), a training-free framework that emulates human forensic investigation through multi-agent collaboration.<n>Unlike conventional methods, our framework employs a set of forensic tools, including reverse image search, metadata extraction, pre-trained classifiers, and VLM analysis.<n>Our comprehensive evaluation spans 6,000 images and challenges real-world scenarios, including images from modern generative platforms and diverse online sources.
  arXiv  Detail & Related papers  (2025-10-31T18:36:49Z)
• ThinkFake: Reasoning in Multimodal Large Language Models for AI-Generated Image Detection [51.93101033997245]
  Increasing realism of AI-generated images has raised serious concerns about misinformation and privacy violations.<n>We propose ThinkFake, a novel reasoning-based and generalizable framework for AI-generated image detection.<n>We show that ThinkFake outperforms state-of-the-art methods on the GenImage benchmark and demonstrates strong zero-shot generalization on the challenging LOKI benchmark.
  arXiv  Detail & Related papers  (2025-09-24T07:34:09Z)
• ForenX: Towards Explainable AI-Generated Image Detection with Multimodal Large Language Models [82.04858317800097]
  We present ForenX, a novel method that not only identifies the authenticity of images but also provides explanations that resonate with human thoughts.<n>ForenX employs the powerful multimodal large language models (MLLMs) to analyze and interpret forensic cues.<n>We introduce ForgReason, a dataset dedicated to descriptions of forgery evidences in AI-generated images.
  arXiv  Detail & Related papers  (2025-08-02T15:21:26Z)
• Foundations and Models in Modern Computer Vision: Key Building Blocks in Landmark Architectures [34.542592986038265]
  This report analyzes the evolution of key design patterns in computer vision by examining six influential papers.<n>We review ResNet, which introduced residual connections to overcome the vanishing gradient problem.<n>We examine the Vision Transformer (ViT), which established a new paradigm by applying the Transformer architecture to sequences of image patches.
  arXiv  Detail & Related papers  (2025-07-31T09:08:11Z)
• Interpretable and Reliable Detection of AI-Generated Images via Grounded Reasoning in MLLMs [43.08776932101172]
  We build a dataset of AI-generated images annotated with bounding boxes and descriptive captions.<n>We then finetune MLLMs through a multi-stage optimization strategy.<n>The resulting model achieves superior performance in both detecting AI-generated images and localizing visual flaws.
  arXiv  Detail & Related papers  (2025-06-08T08:47:44Z)
• RIGID: A Training-free and Model-Agnostic Framework for Robust AI-Generated Image Detection [60.960988614701414]
  RIGID is a training-free and model-agnostic method for robust AI-generated image detection. RIGID significantly outperforms existing trainingbased and training-free detectors.
  arXiv  Detail & Related papers  (2024-05-30T14:49:54Z)
• Enhancing Large Vision Language Models with Self-Training on Image Comprehension [131.14381425260706]
  We introduce Self-Training on Image (STIC), which emphasizes a self-training approach specifically for image comprehension. First, the model self-constructs a preference for image descriptions using unlabeled images. To further self-improve reasoning on the extracted visual information, we let the model reuse a small portion of existing instruction-tuning data.
  arXiv  Detail & Related papers  (2024-05-30T05:53:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.