{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T02:36:27Z","timestamp":1773801387094,"version":"3.50.1"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"7","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"<jats:p>Aligning text-to-image (T2I) diffusion models with human preferences has emerged as a critical research challenge.\nWhile Direct Preference Optimization (DPO) has established a foundation for preference learning in large language models\n(LLMs), its extension to diffusion models remains limited in alignment performance. In this work, we propose an enhanced\nversion of Diffusion-DPO by introducing a stable reference model update strategy. This strategy facilitates the exploration\nof better alignment solutions while maintaining training stability. Moreover, we design a timestep-aware optimization\nstrategy that further boosts performance by addressing preference learning imbalance across timesteps. \nThrough the synergistic combination of our exploration and timestep-aware optimization, our method significantly improves the alignment\nperformance of Diffusion-DPO on human preference evaluation benchmarks, achieving state-of-the-art results.<\/jats:p>","DOI":"10.1609\/aaai.v40i7.37480","type":"journal-article","created":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T23:22:55Z","timestamp":1773789775000},"page":"5611-5619","source":"Crossref","is-referenced-by-count":0,"title":["Rethinking Direct Preference Optimization in Diffusion Models"],"prefix":"10.1609","volume":"40","author":[{"given":"Junyong","family":"Kang","sequence":"first","affiliation":[]},{"given":"Seohyun","family":"Lim","sequence":"additional","affiliation":[]},{"given":"Kyungjune","family":"Baek","sequence":"additional","affiliation":[]},{"given":"Hyunjung","family":"Shim","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\/37480\/41442","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/37480\/41442","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T23:22:56Z","timestamp":1773789776000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/37480"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,14]]},"references-count":0,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2026,3,17]]}},"URL":"https:\/\/doi.org\/10.1609\/aaai.v40i7.37480","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]]}}}