AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

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

Lei Tan, Shuwei Li, Mohan Kankanhalli, Robby T. Tan

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: VLM capability analysis · 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 instruction optimization to frozen backbone (ablation)Qwen2.5-VL-7B · Chameleonaccuracy: 55.5 -> 68.3Improved
Add instruction optimization to frozen backbone (ablation)Qwen2.5-VL-7B · GenImageaccuracy: 51.9 -> 74.2Improved
Add visual adaptation (local crop + patch shuffle) to visual fine-tuning (ablation)Qwen2.5-VL-7B · GenImageaccuracy: 76.8 -> 91.7Improved
Add visual adaptation to visual fine-tuning (ablation)Qwen2.5-VL-7B · Chameleonaccuracy: 50.9 -> 55.4Improved
Add label-conditioned regeneration to LLM fine-tuning (ablation)Qwen2.5-VL-7B · GenImageaccuracy: 80.3 -> 82.4Improved
Add label-conditioned regeneration to LLM fine-tuning (ablation)Qwen2.5-VL-7B · Chameleonaccuracy: 71.0 -> 65.1Hurt
Naively fine-tune both vision and language (ablation)Qwen2.5-VL-7B · Chameleonaccuracy: 71.0 -> 52.0Hurt
Combine all three components (full UC-VLM) vs best single component (ablation)Qwen2.5-VL-7B · GenImageaccuracy: 91.7 -> 96.1Improved
Use structured prompt with explanation (P-3) vs plain QA (P-1) (ablation)Qwen2.5-VL-7B · Chameleonaccuracy: 55.5 -> 63.6Improved
Fine-tune vision encoder only (ablation)Qwen2.5-VL-7B · Chameleonaccuracy: 55.5 -> 50.9Hurt

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