{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T02:39:11Z","timestamp":1773801551095,"version":"3.50.1"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"10","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"<jats:p>Developing a multi-modal language model capable of understanding 3D scenes remains challenging due to the limited availability of 3D training data, in contrast to the abundance of 2D datasets used for vision-language models (VLMs). As an alternative, we introduce LLaVA\u00b3 (pronounced LLaVA Cube), a novel method that improves the 3D scene understanding capabilities of VLMs using only multi-view 2D images, and without requiring any fine-tuning. Inspired by Cubist painters, who represented multiple viewpoints of a 3D object within a single 2D picture, we propose to describe the 3D scene for the VLM through omnidirectional visual representations of each object.\nThese representations are derived from an intermediate multi-view 3D reconstruction of the scene. Extensive experiments on 3D visual question answering and 3D language grounding show that our approach significantly outperforms previous 2D-based VLM solutions.<\/jats:p>","DOI":"10.1609\/aaai.v40i10.37791","type":"journal-article","created":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T23:41:37Z","timestamp":1773790897000},"page":"8412-8420","source":"Crossref","is-referenced-by-count":0,"title":["LLaVA\u00b3: Representing 3D Scenes Like a Cubist Painter to Boost 3D Scene Understanding of VLMs"],"prefix":"10.1609","volume":"40","author":[{"given":"Doriand","family":"Petit","sequence":"first","affiliation":[]},{"given":"Steve","family":"Bourgeois","sequence":"additional","affiliation":[]},{"given":"Vincent","family":"Gay-Bellile","sequence":"additional","affiliation":[]},{"given":"Florian","family":"Chabot","sequence":"additional","affiliation":[]},{"given":"Lo\u00efc","family":"Barthe","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\/37791\/41753","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/37791\/41753","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T23:41:37Z","timestamp":1773790897000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/37791"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,14]]},"references-count":0,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2026,3,17]]}},"URL":"https:\/\/doi.org\/10.1609\/aaai.v40i10.37791","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]]}}}