AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

TranX-Adapter: Bridging Artifacts and Semantics within MLLMs for Robust AI-generated Image Detection

Wenbin Wang, Yuge Huang, Jianqing Xu, Yue Yu, Jiangtao Yan, Shouhong Ding, Pan Zhou, Yong Luo

ICML 2026 · Vision-language and multimodal › Cross-modal learning · approach: Multi-modality image fusion · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add artifact encoder (NPR) features to the MLLM (ablation)LLaVA-1.6-mistral 7B · GenImageaccuracy: +4.6%Improved
add X-Fusion individually (ablation)LLaVA-1.6-mistral 7B + artifact encoder · GenImageaccuracy: +2.3%Improved
add TOP-Fusion individually (ablation)LLaVA-1.6-mistral 7B + artifact encoder · GenImageaccuracy: +3.2%Improved
combine X-Fusion and TOP-Fusion (ablation)LLaVA-1.6-mistral 7B + artifact encoder · GenImageaccuracy: 91.9Improved
use TOP-Fusion in both transfer directions instead of the asymmetric design (ablation)TranX-Adapter · Chameleon (Qwen3-VL 2B)accuracy: 82.3 -> 78.9Hurt
use X-Fusion in both transfer directions instead of the asymmetric design (ablation)TranX-Adapter · Chameleon (Qwen3-VL 2B)accuracy: 82.3 -> 81.3Hurt
use cosine similarity cost matrix instead of JS divergence (ablation)TOP-Fusion · GenImage (Qwen3-VL 2B)accuracy: 88.0 -> 83.7Hurt
use KL divergence cost matrix instead of JS divergence (ablation)TOP-Fusion · GenImage (Qwen3-VL 2B)accuracy: 88.0 -> 86.8Hurt
use TranX-Adapter instead of direct feature concatenationQwen3-VL 4B · RRDatasetaccuracy: 85.6 -> 90.9Improved
use TranX-Adapter instead of direct feature concatenationLLaVA-1.6-mistral 7B · Chameleon (train all GenImage)accuracy: 81.9 -> 85.1Improved
use TranX-Adapter with a VAE-based artifact encoderLLaVA-1.6-mistral 7B + VAE · Chameleonaccuracy: 79.3 -> 83.8Improved
train TranX-Adapter (160M params) instead of LoRA or Adapter at the same sizeLLaVA-1.6-mistral 7B · Chameleonaccuracy: 74.4 -> 75.8Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy