AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

REVEAL: Reasoning-Enhanced Forensic Evidence Analysis for Explainable AI-Generated Image Detection

Huangsen Cao, Qin Mei, Zhiheng Li, Yuxi Li, Zhan Meng, Ying Zhang, Chen Li, Zhimeng Zhang, Xin Ding, Yongwei Wang, Jing LYU, Fei Wu

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Interleaved image-text generation with MLLMs · 10 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 R-GRPO reward-based RL on top of CoE tuning (instead of vanilla GRPO) (ablation)REVEAL · REVEAL-Benchaccuracy: 91.56 -> 95.31Improved
add vanilla GRPO after CoE tuning (ablation)REVEAL · REVEAL-Benchaccuracy: 85.73 -> 91.56Improved
add chain-of-evidence tuning instead of no reasoning supervision (ablation)REVEAL · REVEAL-Benchaccuracy: 61.21 -> 85.73Improved
use evidence-first CoE format instead of answer-first reasoning format (ablation)REVEAL · REVEAL-Benchaccuracy: 82.39 -> 85.73Improved
add R-GRPO to Phi-3.5 after CoE tuning (ablation)Phi-3.5 · REVEAL-Benchaccuracy: 83.75 -> 87.19Improved
add R-GRPO to Qwen2.5-VL-7B after CoE tuning (ablation)Qwen2.5-VL-7B · REVEAL-Benchaccuracy: 85.73 -> 92.19Improved
add R-GRPO to llava-v1.5-7b after CoE tuning (ablation)llava-v1.5-7b · REVEAL-Benchaccuracy: 91.56 -> 92.81Improved
scale backbone from LLaVA-7B to LLaVA-13B (with R-GRPO) (ablation)REVEAL · REVEAL-Benchaccuracy: 92.81 -> 95.31Improved
use REVEAL's LLM reasoning over expert outputs instead of majority voting of the eight experts (ablation)REVEAL · REVEAL-Benchaccuracy: 78.35 -> 95.31Improved
use REVEAL instead of decision tree over expert outputs (ablation)REVEAL · REVEAL-Benchaccuracy: 74.75 -> 95.31Improved
add expert guidance to CoE annotation instead of direct LLM annotation (ablation)REVEAL-Bench · annotation qualitylabel errors and explanation correctnessImproved
add the Pixel Noise expert to the annotation pipeline (ablation)REVEAL-Bench · REVEAL-BenchaccuracyImproved

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