AIIC AI Intelligence Centre

SOURCE-LINKED INTELLIGENCE

GaussVLA: Geometry-Aware Spatial Reasoning for Vision-Language-Action Model

arXiv · AI, language, vision and robotics · article · Aug 25, 2026 · UTC

Vision-Language-Action (VLA) models encode visual observations as flat 2D patch tokens that carry no intrinsic geometric structure, and augmenting them with dense monocular depth injects per-pixel scalar values that encode neither surface orientation nor geometric confidence. This leaves the policy with limited structured spatial reasoning for action prediction. We propose GaussVLA, a Mamba-based VLA that incorporates two custom modules: Gaussian Spatial Tokenizer (GST) to lift frozen semantic and depth features into compact 3D Gaussian tokens, pools geometrically salient regions with learned

Read original source ↗ Open in workspace

recordType
paper
region
Global

Evidence & attribution

First collected: 2026-09-21T10:22:00.206Z. This is not the publication date.