{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T02:49:43Z","timestamp":1773802183884,"version":"3.50.1"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"16","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"<jats:p>Rectification flow Transformers (RFTs) have shown promising performance in diffusion-based image synthesis but are typically confined to lower-resolution scenarios, limiting their ability to generate high-resolution images. \nExisting resolution extrapolation approaches often suffer from excessive computational overhead, resulting in prolonged inference times. \nWe propose LookFlow, a training-free high-resolution synthesis framework that accelerates inference while preserving visual quality.\nBuilding on pretrained text-to-image RFTs, LookFlow employs a dynamic lookahead guidance flow  mechanism to refine high-resolution velocity predictions by leveraging multi-timestep lookahead information extracted from a low-resolution flow. \nAdditionally, reusing temporally similar features across consecutive timesteps drastically reduces computation and significantly decreases inference time overhead.\nExtensive experiments on COCO demonstrate that LookFlow robustly scales resolutions from 4\u00d7 to 25\u00d7, achieving up to a maximum speedup of 2.01\u00d7 while maintaining competitive visual fidelity.<\/jats:p>","DOI":"10.1609\/aaai.v40i16.38388","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T00:23:24Z","timestamp":1773793404000},"page":"13800-13808","source":"Crossref","is-referenced-by-count":0,"title":["LookFlow: Training-Free and Efficient High-Resolution Image Synthesis via Dynamic Lookahead Guidance Flow"],"prefix":"10.1609","volume":"40","author":[{"given":"Yuan","family":"Zhou","sequence":"first","affiliation":[]},{"given":"Yan","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Jianlong","family":"Chang","sequence":"additional","affiliation":[]},{"given":"Xin","family":"Gu","sequence":"additional","affiliation":[]},{"given":"Ying","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Kun","family":"Ding","sequence":"additional","affiliation":[]},{"given":"Guangwen","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Shiming","family":"Xiang","sequence":"additional","affiliation":[]}],"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\/38388\/42350","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/38388\/42350","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T00:23:24Z","timestamp":1773793404000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/38388"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,14]]},"references-count":0,"journal-issue":{"issue":"16","published-online":{"date-parts":[[2026,3,17]]}},"URL":"https:\/\/doi.org\/10.1609\/aaai.v40i16.38388","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]]}}}