UC-VLM: Consistency-Driven Learning for AI-Generated Image Detection with Vision-Language Large Models

[2608.15238] UC-VLM: Consistency-Driven Learning for AI-Generated Image Detection with Vision-Language Large Models Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Computer Vision and Pattern Recognition arXiv:2608.15238 (cs) [Submitted on 15 Aug 2026] Title: UC-VLM: Consistency-Driven Learning for AI-Generated Image Detection with Vision-Language Large Models Authors: Lei Tan , Shuwei Li , Mohan Kankanhalli , Robby T. Tan View a PDF of the paper titled UC-VLM: Consistency-Driven Learning for AI-Generated Image Detection with Vision-Language Large Models, by Lei Tan and 3 other authors View PDF HTML (experimental) Abstract: Vision-Language Large Models (VLLMs) are promising for AI-generated image (AIGI) detection because they can produce both a prediction and a natural-language output. However, most existing VLLM-based detectors primarily fine-tune the language side while giving limited attention to low-level visual forensic cues. They also often depend on manually crafted prompts or human-annotated rationales, which limits this http URL present UC-VLM, a unified multi-stage framework for AIGI detection that relies solely on binary supervision. UC-VLM first identifies effective instruction variants automatically. It then reuses the same binary label within a multi-stage training framework: (i) a visual discrimination objective that strengthens sensitivity to non-semantic forensic cues, and (ii) a label-conditioned generation objective that uses the binary label to supervise textual outputs. This design turns weak binary supervision into a shared supervision signal for both the visual pathway and the language output. Our key novelty is a unified multi-stage binary-supervised framework that consistently reuses the same authenticity labels for visual adaptation and label-conditioned text generation, while leveraging automatically optimized instructions to reduce prompt sensitivity without requiring human-written rationales or hand-crafted this http URL show that UC-VLM achieves 96.1% average accuracy on GenImage, exceeding the strongest prior result by 4.6%, and obtains 69.6% / 77.9% accuracy on Chameleon under ProGAN / SDV1.4 training, surpassing the best baseline by 11.2% / 15.3%, respectively. Comments: Accepted by ECCV 2026 Subjects: Computer Vision and Pattern Recognition (cs.CV) Cite as: arXiv:2608.15238 [cs.CV] (or arXiv:2608.15238v1 [cs.CV] for this version) https://doi.org/10.48550/arXiv.2608.15238 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Lei Tan [ view email ] [v1] Sat, 15 Aug 2026 13:53:59 UTC (1,225 KB) Full-text links: Access Paper: View a PDF of the paper titled UC-VLM: Consistency-Driven Learning for AI-Generated Image Detection with Vision-Language Large Models, by Lei Tan and 3 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CV < prev | next > new | recent | 2026-08 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• UC-VLM: Consistency-Driven Learning for AI-Generated Image Detection with Vision-Language Large Models#611180
• MOPDA: Mixed-Trajectory On-Policy Distillation for Language-Guided Industrial Anomaly Detection#1128625
• Reinforcing Consistency in Video MLLMs with Structured Rewards#629964
• Reinforcing Consistency in Video MLLMs with Structured Rewards#628102
• RAVEL: Asynchronous Rolling Inference for Flow-Based Vision-Language-Action Models#1119243