{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T02:30:21Z","timestamp":1773801021486,"version":"3.50.1"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"4","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"<jats:p>Conventional document layout analysis (DLA) traditionally depends on empirical priors or a fixed set of learnable queries executed in a single forward pass. While sufficient for early-generation documents with a small, predetermined number of regions, this paradigm struggles with contemporary documents, which exhibit diverse element counts and increasingly complex layouts. To address challenges posed by modern documents, we present HybriDLA, a novel generative framework that unifies diffusion and autoregressive decoding within a single layer. The diffusion component iteratively refines bounding-box hypotheses, whereas the autoregressive component injects semantic and contextual awareness, enabling precise region prediction even in highly varied layouts. To further enhance detection quality, we design a multi-scale feature-fusion encoder that captures both fine-grained and high-level visual cues. This architecture elevates performance to 83.5% mean Average Precision (mAP). Extensive experiments on the DocLayNet and M6Doc benchmarks demonstrate that HybriDLA sets a state-of-the-art performance, outperforming previous approaches.<\/jats:p>","DOI":"10.1609\/aaai.v40i4.37308","type":"journal-article","created":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T22:59:27Z","timestamp":1773788367000},"page":"3147-3155","source":"Crossref","is-referenced-by-count":0,"title":["HybriDLA: Hybrid Generation for Document Layout Analysis"],"prefix":"10.1609","volume":"40","author":[{"given":"Yufan","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Omar","family":"Moured","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruiping","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junwei","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kunyu","family":"Peng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaming","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rainer","family":"Stiefelhagen","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\/37308\/41270","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/37308\/41270","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T22:59:28Z","timestamp":1773788368000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/37308"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,14]]},"references-count":0,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2026,3,17]]}},"URL":"https:\/\/doi.org\/10.1609\/aaai.v40i4.37308","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]]}}}