AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

WikiAutoGen: Towards Multi-Modal Wikipedia-Style Article Generation

Zhongyu Yang, Jun Chen, Dannong Xu, Junjie Fei, Xiaoqian Shen, Liangbing Zhao, Chun-Mei Feng, Mohamed Elhoseiny

ICCV 2025 · Vision-language and multimodal › Multimodal LLMs · approach: Interleaved image-text generation with MLLMs · 11 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 multi-agent knowledge exploration (ablation)WikiAutoGen · WikiSeek text quality, Image as Topicaverage text score: 48.78 -> 66.56Improved
add outline proposal (ablation)WikiAutoGen · WikiSeek text quality, Image as Topicaverage text score: 48.78 -> 72.88Improved
add self-reflection (ablation)WikiAutoGen · WikiSeek text quality, Image as Topicaverage text score: 48.78 -> 71.60Improved
add multi-agent exploration on top of outline proposal + self-reflection (ablation)WikiAutoGen · WikiSeek text quality, Image as Topicaverage text score: 73.80 -> 77.49Improved
add self-reflection on top of outline proposal (ablation)WikiAutoGen · WikiSeek text quality, Image as Topicaverage text score: 72.88 -> 73.80Improved
add outline proposal on top of self-reflection (ablation)WikiAutoGen · WikiSeek text quality, Image as Topicaverage text score: 71.60 -> 73.80Improved
use WikiAutoGen instead of Co-StormWikiAutoGen · WikiSeek text quality, Text as Topicaverage text score: 69.96 -> 78.73Improved
use WikiAutoGen instead of oRAGWikiAutoGen · WikiSeek text quality, Image as Topicaverage text score: 48.38 -> 77.49Improved
use WikiAutoGen instead of Co-StormWikiAutoGen · WikiSeek text quality, Image-Text as Topicaverage text score: 63.77 -> 78.82Improved
use WikiAutoGen instead of oRAGWikiAutoGen · WikiSeek image content, Text as Topicaverage image score: 57.28 -> 68.99Improved
use WikiAutoGen instead of OmniThinkWikiAutoGen · WikiSeek image content, Image-Text as Topicaverage image score: 55.25 -> 70.98Improved
use WikiAutoGen instead of OpenAI deep researchWikiAutoGen · WikiSeek, Prometheus2 judge, averageaverage score: 93.06 -> 89.01Hurt

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