{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T02:56:51Z","timestamp":1773802611084,"version":"3.50.1"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"18","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"<jats:p>Data condensation techniques aim to synthesize a compact dataset from a larger one to enable efficient model training, yet while successful in unimodal settings, they often fail in multimodal scenarios where preserving intricate inter-modal dependencies is crucial. To address this, we introduce ImageBindDC, a novel data condensation framework operating within the unified feature space of ImageBind. Our approach moves beyond conventional distribution-matching by employing a powerful Characteristic Function (CF) loss, which operates in the Fourier domain to facilitate a more precise statistical alignment via exact infinite moment matching. We design our objective to enforce three critical levels of distributional consistency: (i) uni-modal alignment, which matches the statistical properties of synthetic and real data within each modality; (ii) cross-modal alignment, which preserves pairwise semantics by matching the distributions of hybrid real-synthetic data pairs; and (iii) joint-modal alignment, which captures the complete multivariate data structure by aligning the joint distribution of real data pairs with their synthetic counterparts. Extensive experiments highlight the effectiveness of ImageBindDC: on the NYU-v2 dataset, a model trained on just 5 condensed datapoints per class achieves lossless performance comparable to one trained on the full dataset, achieving a new state-of-the-art with an 8.2% absolute improvement over the previous best method and more than 4\u00d7 less condensation time.<\/jats:p>","DOI":"10.1609\/aaai.v40i18.38582","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T00:40:49Z","timestamp":1773794449000},"page":"15537-15545","source":"Crossref","is-referenced-by-count":0,"title":["ImageBindDC: Compressing Multi-modal Data with ImageBind-based Condensation"],"prefix":"10.1609","volume":"40","author":[{"given":"Yue","family":"Min","sequence":"first","affiliation":[]},{"given":"Shaobo","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Jiaze","family":"Li","sequence":"additional","affiliation":[]},{"given":"Tianle","family":"Niu","sequence":"additional","affiliation":[]},{"given":"Junxin","family":"Fan","sequence":"additional","affiliation":[]},{"given":"Yongliang","family":"Miao","sequence":"additional","affiliation":[]},{"given":"Lijin","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Linfeng","family":"Zhang","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\/38582\/42544","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/38582\/42544","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T00:40:49Z","timestamp":1773794449000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/38582"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,14]]},"references-count":0,"journal-issue":{"issue":"18","published-online":{"date-parts":[[2026,3,17]]}},"URL":"https:\/\/doi.org\/10.1609\/aaai.v40i18.38582","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]]}}}