Litcius/Paper detail

SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Models

Delin Qu, Haoming Song, Qizhi Chen, Yuanqi Yao, Xinyi Ye, Jiayuan Gu, Zhigang Wang, Yan Ding, Bin Zhao, Dong Wang, Xuelong Li

202515 citationsDOIOpen Access PDF

Abstract

and real-world setups, where the pre-learned action grids are re-discretized to capture robot-specific spatial action movements of new setups.The superior results from extensive evaluations demonstrate the exceptional in-distribution generalization and out-of-distribution adaptation capability, highlighting the crucial benefit of the proposed spatial-aware representations for generalist robot policy learning.All the details and codes are opensourced.

Topics & Concepts

Computer scienceArtificial intelligenceRepresentation (politics)Field (mathematics)Perspective (graphical)Feature (linguistics)Set (abstract data type)Focus (optics)Frame (networking)Identification (biology)Multimodal Machine Learning ApplicationsGeographic Information Systems StudiesHuman Pose and Action Recognition
SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Models | Litcius