Paper
TranX-Adapter: Bridging Artifacts and Semantics within MLLMs for Robust AI-generated Image Detection
Authors
Wenbin Wang, Yuge Huang, Jianqing Xu, Yue Yu, Jiangtao Yan, Shouhong Ding, Pan Zhou, Yong Luo
Abstract
Rapid advances in AI-generated image (AIGI) technology enable highly realistic synthesis, threatening public information integrity and security. Recent studies have demonstrated that incorporating texture-level artifact features alongside semantic features into multimodal large language models (MLLMs) can enhance their AIGI detection capability. However, our preliminary analyses reveal that artifact features exhibit high intra-feature similarity, leading to an almost uniform attention map after the softmax operation. This phenomenon causes attention dilution, thereby hindering effective fusion between semantic and artifact features. To overcome this limitation, we propose a lightweight fusion adapter, TranX-Adapter, which integrates a Task-aware Optimal-Transport Fusion that leverages the Jensen-Shannon divergence between artifact and semantic prediction probabilities as a cost matrix to transfer artifact information into semantic features, and an X-Fusion that employs cross-attention to transfer semantic information into artifact features. Experiments on standard AIGI detection benchmarks upon several advanced MLLMs, show that our TranX-Adapter brings consistent and significant improvements (up to +6% accuracy).
Metadata
Related papers
Vibe Coding XR: Accelerating AI + XR Prototyping with XR Blocks and Gemini
Ruofei Du, Benjamin Hersh, David Li, Nels Numan, Xun Qian, Yanhe Chen, Zhongy... • 2026-03-25
Comparing Developer and LLM Biases in Code Evaluation
Aditya Mittal, Ryan Shar, Zichu Wu, Shyam Agarwal, Tongshuang Wu, Chris Donah... • 2026-03-25
The Stochastic Gap: A Markovian Framework for Pre-Deployment Reliability and Oversight-Cost Auditing in Agentic Artificial Intelligence
Biplab Pal, Santanu Bhattacharya • 2026-03-25
Retrieval Improvements Do Not Guarantee Better Answers: A Study of RAG for AI Policy QA
Saahil Mathur, Ryan David Rittner, Vedant Ajit Thakur, Daniel Stuart Schiff, ... • 2026-03-25
MARCH: Multi-Agent Reinforced Self-Check for LLM Hallucination
Zhuo Li, Yupeng Zhang, Pengyu Cheng, Jiajun Song, Mengyu Zhou, Hao Li, Shujie... • 2026-03-25
Raw Data (Debug)
{
"raw_xml": "<entry>\n <id>http://arxiv.org/abs/2602.21716v1</id>\n <title>TranX-Adapter: Bridging Artifacts and Semantics within MLLMs for Robust AI-generated Image Detection</title>\n <updated>2026-02-25T09:22:46Z</updated>\n <link href='https://arxiv.org/abs/2602.21716v1' rel='alternate' type='text/html'/>\n <link href='https://arxiv.org/pdf/2602.21716v1' rel='related' title='pdf' type='application/pdf'/>\n <summary>Rapid advances in AI-generated image (AIGI) technology enable highly realistic synthesis, threatening public information integrity and security. Recent studies have demonstrated that incorporating texture-level artifact features alongside semantic features into multimodal large language models (MLLMs) can enhance their AIGI detection capability. However, our preliminary analyses reveal that artifact features exhibit high intra-feature similarity, leading to an almost uniform attention map after the softmax operation. This phenomenon causes attention dilution, thereby hindering effective fusion between semantic and artifact features. To overcome this limitation, we propose a lightweight fusion adapter, TranX-Adapter, which integrates a Task-aware Optimal-Transport Fusion that leverages the Jensen-Shannon divergence between artifact and semantic prediction probabilities as a cost matrix to transfer artifact information into semantic features, and an X-Fusion that employs cross-attention to transfer semantic information into artifact features. Experiments on standard AIGI detection benchmarks upon several advanced MLLMs, show that our TranX-Adapter brings consistent and significant improvements (up to +6% accuracy).</summary>\n <category scheme='http://arxiv.org/schemas/atom' term='cs.CV'/>\n <published>2026-02-25T09:22:46Z</published>\n <arxiv:primary_category term='cs.CV'/>\n <author>\n <name>Wenbin Wang</name>\n </author>\n <author>\n <name>Yuge Huang</name>\n </author>\n <author>\n <name>Jianqing Xu</name>\n </author>\n <author>\n <name>Yue Yu</name>\n </author>\n <author>\n <name>Jiangtao Yan</name>\n </author>\n <author>\n <name>Shouhong Ding</name>\n </author>\n <author>\n <name>Pan Zhou</name>\n </author>\n <author>\n <name>Yong Luo</name>\n </author>\n </entry>"
}