{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T03:27:30Z","timestamp":1773804450971,"version":"3.50.1"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"33","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"<jats:p>With the emergence of large multimodal models, dual-encoder alignment via contrastive learning has seen a resurgence. However, the escalating model size demands effective Parameter-Efficient Fine-Tuning (PEFT). While LoRA is a promising inference-free alternative to adapters, we find that its naive application to multimodal tasks causes a severe rank imbalance, favoring the text modality and FFN layers. To address this, we propose HALoRA (Hierarchical Allocation LoRA), which introduces a component-wise budget allocator to ensure balanced fine-tuning across both modalities and their internal components. This is complemented by a gradient-approximated initialization to accelerate convergence. With only half the parameters of adapters, HALoRA achieves superior or competitive performance in retrieval and zero-shot classification. Our work presents a more principled approach to multimodal LoRA,  uncovering an intriguing asymmetry in vision-language alignment.<\/jats:p>","DOI":"10.1609\/aaai.v40i33.40056","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T02:23:20Z","timestamp":1773800600000},"page":"28283-28291","source":"Crossref","is-referenced-by-count":0,"title":["HALoRA: Low-Rank Adaptation with Hierarchical Budget Allocation for Efficient Vision-Language Alignment"],"prefix":"10.1609","volume":"40","author":[{"given":"Letian","family":"Zhang","sequence":"first","affiliation":[]},{"given":"GuangHao","family":"Meng","sequence":"additional","affiliation":[]},{"given":"XuDong","family":"Ren","sequence":"additional","affiliation":[]},{"given":"Jinpeng","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\/40056\/44017","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/40056\/44017","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T02:23:21Z","timestamp":1773800601000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/40056"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,14]]},"references-count":0,"journal-issue":{"issue":"33","published-online":{"date-parts":[[2026,3,17]]}},"URL":"https:\/\/doi.org\/10.1609\/aaai.v40i33.40056","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]]}}}