{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T04:02:37Z","timestamp":1779249757367,"version":"3.51.4"},"reference-count":45,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01441","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"15532-15541","source":"Crossref","is-referenced-by-count":1,"title":["WikiAutoGen: Towards Multi-Modal Wikipedia-Style Article Generation"],"prefix":"10.1109","author":[{"given":"Zhongyu","family":"Yang","sequence":"first","affiliation":[{"name":"King Abdullah University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Chen","sequence":"additional","affiliation":[{"name":"Meta AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dannong","family":"Xu","sequence":"additional","affiliation":[{"name":"King Abdullah University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junjie","family":"Fei","sequence":"additional","affiliation":[{"name":"King Abdullah University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoqian","family":"Shen","sequence":"additional","affiliation":[{"name":"King Abdullah University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liangbing","family":"Zhao","sequence":"additional","affiliation":[{"name":"King Abdullah University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chun-Mei","family":"Feng","sequence":"additional","affiliation":[{"name":"IHPC, A*STAR"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohamed","family":"Elhoseiny","sequence":"additional","affiliation":[{"name":"King Abdullah University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Self-rag: Learning to retrieve, generate, and critique through self-reflection","volume":"abs\/2310.11511","author":"Asai","year":"2023","journal-title":"ArXiv"},{"key":"ref2","article-title":"Qwen technical report","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.729"},{"key":"ref4","first-page":"2","article-title":"Demystifying chains, trees, and graphs of thoughts","author":"Besta","year":"2024","journal-title":"ArXiv"},{"key":"ref5","article-title":"Deepseek llm: Scaling opensource language models with longtermism","author":"Bi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref6","first-page":"3","article-title":"Wikiweb2m: A page-level multimodal wikipedia dataset","author":"Burns","year":"2023","journal-title":"ArXiv"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-srw.10"},{"key":"ref8","year":"2023","journal-title":"Gemini: Multimodal language model"},{"key":"ref9","first-page":"4","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","volume":"abs\/1810.04805","author":"Devlin","year":"2018","journal-title":"CoRR"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.63317\/3knkq4fwny8w"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.321"},{"key":"ref12","first-page":"3","article-title":"Critic: Large language models can self-correct with tool-interactive critiquing","author":"Gou","year":"2023","journal-title":"ArXiv"},{"key":"ref13","article-title":"Gpt-4o system card","author":"Hurst","year":"2024","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.554"},{"key":"ref15","article-title":"DSPy: Compiling declarative language model calls into selfimproving pipelines","volume-title":"Proceedings of the Twelfth International Conference on Learning Representations (ICLR)","author":"Khattab"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.248"},{"key":"ref17","first-page":"2","article-title":"Longlamp: A benchmark for personalized long-form text generation","author":"Kumar","year":"2024","journal-title":"arXiv preprint"},{"key":"ref18","article-title":"Radev. Surfer100: Generating surveys from web resources, wikipedia-style","volume-title":"International Conference on Language Resources and Evaluation","author":"Li"},{"key":"ref19","first-page":"2","article-title":"Integrating planning into single-turn long-form text generation","author":"Liang","year":"2024","journal-title":"ArXiv"},{"key":"ref20","first-page":"3","article-title":"Self-refine: Iterative refinement with self-feedback","author":"Madaan","year":"2023","journal-title":"ArXiv"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.741"},{"key":"ref22","year":"2022","journal-title":"Chatgpt: Optimizing language models for dialogue"},{"key":"ref23","first-page":"6","year":"2025","journal-title":"Openai o3-mini"},{"key":"ref24","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2024.eacl-long.67","article-title":"Refiner: Reasoning feedback on intermediate representations","volume-title":"Conference of the European Chapter of the Association for Computational Linguistics","author":"Paul"},{"key":"ref25","first-page":"3","article-title":"Llms can learn self-restraint through iterative selfreflection","author":"Pich\u00e9","year":"2024","journal-title":"ArXiv"},{"key":"ref26","first-page":"2","article-title":"Hellobench: Evaluating long text generation capabilities of large language models","author":"Que","year":"2024","journal-title":"arXiv preprint"},{"key":"ref27","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the 38th International Conference on Machine Learning (ICML)","author":"Radford"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.347"},{"key":"ref29","first-page":"2","article-title":"Beyond summarization: Designing ai support for real-world expository writing tasks","author":"Shen","year":"2023","journal-title":"ArXiv"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0377"},{"key":"ref31","first-page":"3","article-title":"Principle-driven self-alignment of language models from scratch with minimal human supervision","author":"Sun","year":"2023","journal-title":"ArXiv"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.341"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.368"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.253"},{"key":"ref35","first-page":"2","article-title":"The llama 3 herd of models","author":"Touvron","year":"2024","journal-title":"arXiv preprint"},{"key":"ref36","first-page":"2","article-title":"Autopatent: A multiagent framework for automatic patent generation","author":"Wang","year":"2024","journal-title":"ArXiv"},{"key":"ref37","first-page":"2","article-title":"Autosurvey: Large language models can automatically write surveys","author":"Wang","year":"2024","journal-title":"ArXiv"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2854"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.333"},{"key":"ref40","first-page":"2","article-title":"Mindmap: Knowledge graph prompting sparks graph of thoughts in large language models","author":"Wen","year":"2023","journal-title":"Annual Meeting of the Association for Computational Linguistics"},{"key":"ref41","first-page":"2","article-title":"Spinning the golden thread: Benchmarking long-form generation in language models","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.50"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.382"},{"key":"ref44","first-page":"3","author":"Zhang","year":"2024","journal-title":"In-context principle learning from mistakes. ArXiv"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.nlp4science-1.10"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444125.pdf?arnumber=11444125","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:08:42Z","timestamp":1777612122000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444125\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01441","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}