{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T02:42:13Z","timestamp":1773801733559,"version":"3.50.1"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"12","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"<jats:p>Flow Matching (FM) is an efficient generative modeling framework, but aligning it with human preferences remains underexplored.~Although applying Direct Preference Optimization (DPO) to diffusion models has yielded improvements, directly extending DPO-like methods to FM poses three challenges: 1) Incompatibility with ODE-based models, 2) Heavy computational cost from full model fine-tuning, and 3) Reliance on reference model quality. To address these limitations, we propose Preference Classifier for Flow Matching (PC-Flow), a novel reference-free preference alignment framework. Specifically, we  reinterpret FM\u2019s deterministic ODE as an equivalent SDE to enable DPO-style learning. Then, we introduce a lightweight classifier to model relative preferences exclusively. This approach decouples alignment from the generative model, eliminating the need for costly fine-tuning or a reference model. Theoretically, PC-Flow guarantees consistent preference-guided distribution evolution, achieves a DPO-equivalent objective without a reference model, and progressively steers generation toward preferred outputs. Experiments show that PC-Flow achieves DPO-level alignment with significantly lower training costs.<\/jats:p>","DOI":"10.1609\/aaai.v40i12.37971","type":"journal-article","created":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T23:53:57Z","timestamp":1773791637000},"page":"10047-10055","source":"Crossref","is-referenced-by-count":0,"title":["PC-Flow: Preference Alignment in Flow Matching via Classifier"],"prefix":"10.1609","volume":"40","author":[{"given":"Shaomeng","family":"Wang","sequence":"first","affiliation":[]},{"given":"He","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Longquan","family":"Dai","sequence":"additional","affiliation":[]},{"given":"Jinhui","family":"Tang","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\/37971\/41933","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/37971\/41933","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T23:53:58Z","timestamp":1773791638000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/37971"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,14]]},"references-count":0,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2026,3,17]]}},"URL":"https:\/\/doi.org\/10.1609\/aaai.v40i12.37971","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]]}}}