{"id":"5f5bb142-a08e-4f41-a576-8243ec4659bd","slug":"spatialvla","name":"SpatialVLA","description":"VLA with Ego3D position encoding and adaptive action grids, pretrained on 1.1M real robot episodes. Multi-institutional research effort demonstrating spatial reasoning for cross-embodiment manipulation.","brainType":"foundation-model","isOpen":true,"maturityStage":"research","architecture":"VLM + 3D spatial position encoding, adaptive action grids","reviewStatus":"reviewed","sources":[{"url":"https://spatialvla.github.io/","title":"SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Models","sourceName":"SpatialVLA authors"},{"url":"https://github.com/SpatialVLA/SpatialVLA","title":"SpatialVLA repository","sourceName":"SpatialVLA authors"},{"url":"https://arxiv.org/html/2501.15830v5","date":"2025-01-27","title":"SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model","sourceName":"arXiv"}],"keyFacts":[{"label":"SpatialVLA design (primary project page)","value":"The SpatialVLA project page describes a spatial-enhanced vision-language-action model trained on 1.1 million real robot episodes, with Ego3D Position Encoding and Adaptive Spatial Grids (also called Adaptive Action Grids). Authors are affiliated with Shanghai AI Laboratory, Fudan, Shanghai Jiao Tong, Zhejiang University, ShanghaiTech, and Northwestern Polytechnical University. Treat dataset size as author-stated (SpatialVLA)"},{"label":"Evaluation scope (primary project page)","value":"The page says SpatialVLA was evaluated across 7 robot learning scenarios, 16 real-robot tasks, and 48 simulation setups, focusing on zero-shot control, spatial understanding, and adaptation to new setups, and claims faster inference with fewer tokens per action. Treat SOTA and speed claims as author-reported (SpatialVLA)"},{"label":"Official code and model release","value":"The SpatialVLA repository provides the project code and links to model resources for the spatial vision language action system (SpatialVLA repository)"},{"label":"SpatialVLA research paper","value":"The SpatialVLA paper describes Ego3D position encoding and adaptive action grids as design components for spatially informed vision language action control (SpatialVLA paper)"},{"label":"Spatial action representation","value":"SpatialVLA combines Ego3D Position Encoding with Adaptive Spatial or Action Grids to represent spatial information for vision-language-action control (SpatialVLA)."},{"label":"Cross-embodiment resources","value":"The official SpatialVLA repository provides code and model resources for evaluating the spatial VLA across robot setups (SpatialVLA repository)."}],"aliases":[],"collisionRisk":"low","reviewNote":null,"builtOnBrainId":null,"createdAt":"2026-08-09T14:35:29.680Z","updatedAt":"2026-10-09T22:00:49.056Z","jsonLd":{"@context":"https://schema.org","@type":"SoftwareApplication","@id":"https://registry.deploy.report/brains/spatialvla","url":"https://registry.deploy.report/brains/spatialvla","name":"SpatialVLA","description":"VLA with Ego3D position encoding and adaptive action grids, pretrained on 1.1M real robot episodes. Multi-institutional research effort demonstrating spatial reasoning for cross-embodiment manipulation.","identifier":"5f5bb142-a08e-4f41-a576-8243ec4659bd","applicationCategory":"foundation-model","publisher":{"@id":"https://deploy.report/#organization"}},"framework_metadata":{"framework_schema_version":"0.1.0","verification_status":"verified","maturity_stage":"research","lifecycle_state":null,"architectural_position":{"cohort":null,"sub_cohorts":[]},"within_cohort_verified_vs_claimed_pair":null,"cap_flags":[],"verification_depth":{"sources_count":3,"primary_source_types":["code-repository","preprint"]}}}