{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T02:38:07Z","timestamp":1773801487602,"version":"3.50.1"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"9","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"<jats:p>Multi-subject video generation aims to synthesize videos from textual prompts and multiple reference images, ensuring that each subject preserves natural scale and visual fidelity. However, current methods face two challenges: scale inconsistency, where variations in subject size lead to unnatural generation, and permutation sensitivity, where the order of reference inputs causes subject distortion.\nIn this paper, we propose MoFu, a unified framework that tackles both challenges. For scale inconsistency, we introduce Scale-Aware Modulation (SMO), an LLM-guided module that extracts implicit scale cues from the prompt and modulates features to ensure consistent subject sizes. To address permutation sensitivity, we present a simple yet effective Fourier Fusion strategy that processes the frequency information of reference features via the Fast Fourier Transform to produce a unified representation. Besides, we design a Scale-Permutation Stability Loss to jointly encourage scale-consistent and permutation-invariant generation.\nTo further evaluate these challenges, we establish a dedicated benchmark with controlled variations in subject scale and reference permutation. Extensive experiments demonstrate that MoFu significantly outperforms existing methods in preserving natural scale, subject fidelity, and overall visual quality.<\/jats:p>","DOI":"10.1609\/aaai.v40i9.37638","type":"journal-article","created":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T23:33:14Z","timestamp":1773790394000},"page":"7033-7041","source":"Crossref","is-referenced-by-count":0,"title":["MoFu: Scale-Aware Modulation and Fourier Fusion for Multi-Subject Video Generation"],"prefix":"10.1609","volume":"40","author":[{"given":"Run","family":"Ling","sequence":"first","affiliation":[]},{"given":"Ke","family":"Cao","sequence":"additional","affiliation":[]},{"given":"Jian","family":"Lu","sequence":"additional","affiliation":[]},{"given":"Ao","family":"Ma","sequence":"additional","affiliation":[]},{"given":"Haowei","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Runze","family":"He","sequence":"additional","affiliation":[]},{"given":"Changwei","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Rongtao","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Yihua","family":"Shao","sequence":"additional","affiliation":[]},{"given":"Zhanjie","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Peng","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Guibing","family":"Guo","sequence":"additional","affiliation":[]},{"given":"Wei","family":"Feng","sequence":"additional","affiliation":[]},{"given":"Zheng","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Jingjing","family":"Lv","sequence":"additional","affiliation":[]},{"given":"Junjie","family":"Shen","sequence":"additional","affiliation":[]},{"given":"Ching","family":"Law","sequence":"additional","affiliation":[]},{"given":"Xingwei","family":"Wang","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\/37638\/41600","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/37638\/41600","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T23:33:14Z","timestamp":1773790394000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/37638"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,14]]},"references-count":0,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,3,17]]}},"URL":"https:\/\/doi.org\/10.1609\/aaai.v40i9.37638","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]]}}}