SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2503.19065 · ICCV · 2025

WikiAutoGen: Towards Multi-Modal Wikipedia-Style Article Generation

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

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. If it links a repository, it is listed below.

Abstract

Figure 1. Comparison of existing text-only article generation methods and our proposed WikiAutoGen. Existing approaches [14,28] rely exclusively on textual sources, often producing inconsistent or inaccurate results. For example, in (a), the target topic is 'Benzoxonium Chloride', yet the baseline incorrectly generates information about 'Benzalkonium Chloride'. In contrast, our WikiAutoGen framework integrates both visual and textual modalities to generate coherent multimodal content. Additionally, WikiAutoGen employs a multiperspective self-reflection mechanism, significantly improving content accuracy and reliability, as illustrated in (b).

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2503.19065")
get_code_for_paper("2503.19065")
have("2503.19065")

Connect an agent — have() is free.