{"type":"ScholarlyArticle","title":"SpatialSV: Internalizing Interpretable 3D Spatial Awareness in MLLMs via Task-Oriented Visual Supervision","authors":[{"name":"Jiayu Tang","slug":"jiayu-tang","given":"Jiayu","family":"Tang","affiliation":""},{"name":"Yuchen Zhou","slug":"yuchen-zhou","given":"Yuchen","family":"Zhou","affiliation":""},{"name":"Chao Gou","slug":"chao-gou","given":"Chao","family":"Gou","affiliation":""}],"abstract":"Unlocking the spatial intelligence of multimodal large language models (MLLMs) is crucial for understanding and interacting with the 3D world. Prevailing approaches typically inject spatial priors via external tools, which impose significant inference overhead, or rely on latent feature distillation, which remains uninterpretable and lacks fine-grained geometric constraints. To address these issues, we propose SpatialSV, a framework designed to internalize robust 3D spatial awareness within MLLMs while simultaneously offering inherent interpretability. Deviating from passive feature imitation, SpatialSV employs task-oriented visual supervision, compelling the model to actively lift its 2D visual features into explicit 3D representations, including depth maps, camera poses, and point clouds. Crucially, this 2D-to-3D lifting process provides a transparent window into the model’s representations: the resulting 3D reconstructions serve as an intuitive proxy for visualizing and diagnosing the quality of the model’s intrinsic spatial knowledge. Extensive experiments across multiple benchmarks and models demonstrate the effectiveness of SpatialSV in enhancing and interpreting MLLMs’ spatial intelligence. Furthermore, the framework exhibits strong generalization in semi-supervised settings, validating its potential to leverage unlabeled visual data for scalable, interpretable spatial representation learning.","doi":"10.24963/ijcai.2026/188","url":"https://ijcai.org/proceedings/2026/188","pdf":"https://ijcai.org/proceedings/2026/0188.pdf","markdown":"https://ijcai.org/proceedings/2026/188.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/188","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"Computer Vision","track":"Main Track","number":188,"pages":{"first":1685,"last":1693},"keywords":["Computer Vision: 3D computer vision","Computer Vision: Multimodal learning","Computer Vision: Representation learning"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}