{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T02:38:46Z","timestamp":1773801526662,"version":"3.50.1"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"10","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"<jats:p>Despite recent advances in text-to-image (T2I) generation, models still struggle to accurately render prompt-specified text with correct spatial layout\u2014especially in multi-span, structured settings. \nThis challenge is driven not only by the lack of datasets that align prompts with the exact text and layout expected in the image, but also by the absence of effective metrics for evaluating layout quality.\nTo address these issues,  we introduce TextGround4M, a large-scale dataset of over 4 million prompt-image pairs, each annotated with span-level text grounded in the prompt and corresponding bounding boxes.\nThis enables fine-grained supervision for layout-aware, prompt-grounded text rendering.\nBuilding on this, we propose a lightweight training strategy for autoregressive T2I models that appends layout-aware span tokens during training, without altering model architecture or inference behavior.\nWe further construct a benchmark with stratified layout complexity to evaluate both open-source and proprietary models in a zero-shot setting. \nIn addition, we introduce two layout-aware metrics to address the long-standing lack of spatial evaluation in text rendering.\nOur results show that models trained on TextGround4M outperform strong baselines in text fidelity, spatial accuracy, and prompt consistency, highlighting the importance of fine-grained layout supervision for grounded T2I generation.<\/jats:p>","DOI":"10.1609\/aaai.v40i10.37736","type":"journal-article","created":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T23:39:18Z","timestamp":1773790758000},"page":"7918-7926","source":"Crossref","is-referenced-by-count":0,"title":["TextGround4M: A Prompt-Aligned Dataset for Layout-Aware Text Rendering"],"prefix":"10.1609","volume":"40","author":[{"given":"Dongxing","family":"Mao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yilin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Linjie","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengyuan","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alex Jinpeng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"9382","published-online":{"date-parts":[[2026,3,14]]},"container-title":["Proceedings of the AAAI Conference on Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/37736\/41698","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/37736\/41698","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T23:39:18Z","timestamp":1773790758000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/37736"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,14]]},"references-count":0,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2026,3,17]]}},"URL":"https:\/\/doi.org\/10.1609\/aaai.v40i10.37736","relation":{},"ISSN":["2374-3468","2159-5399"],"issn-type":[{"value":"2374-3468","type":"electronic"},{"value":"2159-5399","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3,14]]}}}