{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T02:37:06Z","timestamp":1773801426605,"version":"3.50.1"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"5","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"<jats:p>Video diffusion generation suffers from critical sampling efficiency bottlenecks, particularly for large-scale models and long contexts.\nExisting video acceleration methods, adapted from image-based techniques, lack a single-step distillation ability for large-scale video models and task generalization for conditional downstream tasks.\nTo bridge this gap, we propose the Video Phased Adversarial Equilibrium (V-PAE), a distillation framework that enables high-quality, single-step video generation from large-scale video models. Our approach employs a two-phase process.\n(i) Stability priming is a warm-up process to align the distributions of real and generated videos. It improves the stability of single-step adversarial distillation in the following process.\n(ii) Unified adversarial equilibrium is a flexible self-adversarial process that reuses generator parameters for the discriminator backbone. It achieves a co-evolutionary adversarial equilibrium in the Gaussian noise space.\nFor the conditional tasks, we primarily preserve video-image subject consistency, which is caused by semantic degradation and conditional frame collapse during the distillation training in image-to-video (I2V) generation.\nComprehensive experiments on VBench-I2V demonstrate that V-PAE outperforms existing acceleration methods by an average of 5.8% in the overall quality score, including semantic alignment, temporal coherence, and frame quality.\nIn addition, our approach reduces the diffusion latency of the large-scale video model (e.g., Wan2.1-I2V-14B) by 100 times, while preserving competitive performance.<\/jats:p>","DOI":"10.1609\/aaai.v40i5.37318","type":"journal-article","created":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T23:08:51Z","timestamp":1773788931000},"page":"3237-3245","source":"Crossref","is-referenced-by-count":0,"title":["Phased One-Step Adversarial Equilibrium for Video Diffusion Models"],"prefix":"10.1609","volume":"40","author":[{"given":"Jiaxiang","family":"Cheng","sequence":"first","affiliation":[]},{"given":"Bing","family":"Ma","sequence":"additional","affiliation":[]},{"given":"Xuhua","family":"Ren","sequence":"additional","affiliation":[]},{"given":"Hongyi Henry","family":"Jin","sequence":"additional","affiliation":[]},{"given":"Kai","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Peng","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Wenyue","family":"Li","sequence":"additional","affiliation":[]},{"given":"Yuan","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Tianxiang","family":"Zheng","sequence":"additional","affiliation":[]},{"given":"Qinglin","family":"Lu","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\/37318\/41280","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/37318\/41280","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T23:08:51Z","timestamp":1773788931000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/37318"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,14]]},"references-count":0,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,3,17]]}},"URL":"https:\/\/doi.org\/10.1609\/aaai.v40i5.37318","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]]}}}