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

• URL: http://arxiv.org/abs/2608.24959v1
• Date: Tue, 25 Aug 2026 06:28:28 GMT
• Title: GaussVLA: Geometry-Aware Spatial Reasoning for Vision-Language-Action Model
• Abstract summary: GaussVLA encodes visual observations as flat 2D patch tokens that carry no intrinsic geometric structure.<n>It pools geometrically salient regions with learned queries, and emphDepth-Aware Chain-of-Thought (DA-CoT) that performs structured, non-autoregressive geometric reasoning.<n>On LIBERO, it achieves 93.5% average success and 100.0% success on the Spatial suite with only 200M parameters.
• Score: 8.618395711206896
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 queries, and \emph{Depth-Aware Chain-of-Thought (DA-CoT)} that performs structured, non-autoregressive geometric reasoning under language and flow-time conditioning. Across both simulation and real-world evaluations, GaussVLA demonstrates strong spatial-manipulation performance while remaining parameter-efficient. On LIBERO, it achieves 93.5% average success and 100.0% success on the Spatial suite with only 200M parameters, improving over SpatialVLA by 19.7% relative average success while remaining significantly more parameter-efficient.

Related papers

• GaussianDream++: Efficient 3D Gaussian World Modeling for Robotic Manipulation [55.47130289185285]
  Vision-Language-Action (VLA) policies have advanced language-conditioned robotic manipulation.<n>We present textbfMethodname, a compact, policy-native extension that inserts textbfWorld State Tokens and textbfWorld Prediction Tokens directly into the VLA backbone.
  arXiv  Detail & Related papers  (2026-08-26T11:41:55Z)
• GaussianWAM: Distilling Geometry and Semantics from 3D Gaussian Fields into World-Action Models [21.006803571591707]
  World-Action Models (WAMs) jointly learn future visual prediction and action generation, using video dynamics as a representation-learning signal for robotic manipulation.<n>We propose textbfGaussianWAM, a training-time representation-enhancement framework that organizes geometric and semantic supervision through a 3D Gaussian field.
  arXiv  Detail & Related papers  (2026-08-25T15:34:13Z)
• Gaussian-JEPA: Joint-Embedding Predictive Learning for 3D Gaussian Splats [91.55220894541151]
  3D Gaussian Splatting (3DGS) represents 3D content with anisotropic primitives that jointly encode geometry and appearance.<n>We introduce Gaussian-JEPA, which predicts representations of held-out Gaussian token blocks from visible context.
  arXiv  Detail & Related papers  (2026-08-16T09:43:50Z)
• Decoupling Semantics and Geometric Grounding: Spatial Visual Prompts for Language-Conditioned Imitation Learning [21.67233368353003]
  We propose SVP-IL, a decoupled architecture that explicitly extracts spatial visual grounding from the action generation loop.<n>In experiments, SVP-IL significantly outperforms state-of-the-art VLAs and pure visuomotor baselines.
  arXiv  Detail & Related papers  (2026-06-24T03:45:06Z)
• GA-VLN: Geometry-Aware BEV Representation for Efficient Vision-Language Navigation [75.85672467847631]
  We introduce the Geometry-Aware BEV (GA-BEV) - a compact, 3D-grounded feature representation.<n>We construct BEV spatial maps from RGB-D inputs by projecting visual features into 3D space.<n>We incorporate features from a pretrained 3D foundation model into the BEV space, injecting structural priors learned from large-scale 3D reconstruction tasks.
  arXiv  Detail & Related papers  (2026-05-21T06:20:17Z)
• VGGT-Occ: Geometry-Grounded and Density-Aware Gated Fusion for 3D Occupancy Prediction [37.542568613707296]
  VGGT-Occ is a framework that embeds geometric tokens throughout the entire pipeline.<n>We introduce Projection-Aware Deformable Attention (PA-DA) to inject geometry into all attention stages.<n>Features are then integrated through a view-quality semantic gate for cross-view consistency.
  arXiv  Detail & Related papers  (2026-05-16T09:51:04Z)
• GST-VLA: Structured Gaussian Spatial Tokens for 3D Depth-Aware Vision-Language-Action Models [6.2676602262188625]
  VLA models encode visual observations as 2D patch tokens with no intrinsic geometric structure.<n>We introduce GST-VLA with two contributions.<n>First, the Gaussian Spatial Tokenizer ( GST) converts frozen dense depth and frozen semantic patch features into 3D primitives.<n>Second, 3D Depth-Aware Chain-of-Thought (DA-CoT) reasoning supervises four structured intermediate spatial thoughts.
  arXiv  Detail & Related papers  (2026-03-10T01:39:38Z)
• GLaD: Geometric Latent Distillation for Vision-Language-Action Models [106.53332923530245]
  We introduce GLaD, a geometry-aware Vision-Language-Action (VLA) framework that incorporates 3D geometric priors during pretraining through knowledge distillation.<n>GLaD achieves 94.1% average success rate across four LIBERO task suites, outperforming UniVLA (92.5%) which uses identical pretraining data.
  arXiv  Detail & Related papers  (2025-12-10T13:07:27Z)
• GauSSmart: Enhanced 3D Reconstruction through 2D Foundation Models and Geometric Filtering [50.675710727721786]
  We propose GauSSmart, a hybrid method that bridges 2D foundational models and 3D Gaussian Splatting reconstruction.<n>Our approach integrates established 2D computer vision techniques, including convex filtering and semantic feature supervision.<n>We validate our approach across three datasets, where GauSSmart consistently outperforms existing Gaussian Splatting.
  arXiv  Detail & Related papers  (2025-10-16T03:38:26Z)
• MonoGSDF: Exploring Monocular Geometric Cues for Gaussian Splatting-Guided Implicit Surface Reconstruction [86.87464903285208]
  We introduce MonoGSDF, a novel method that couples primitives with a neural Signed Distance Field (SDF) for high-quality reconstruction.<n>To handle arbitrary-scale scenes, we propose a scaling strategy for robust generalization.<n>Experiments on real-world datasets outperforms prior methods while maintaining efficiency.
  arXiv  Detail & Related papers  (2024-11-25T20:07:07Z)
• Why Approximate Matrix Square Root Outperforms Accurate SVD in Global Covariance Pooling? [59.820507600960745]
  We propose a new GCP meta-layer that uses SVD in the forward pass, and Pad'e Approximants in the backward propagation to compute the gradients. The proposed meta-layer has been integrated into different CNN models and achieves state-of-the-art performances on both large-scale and fine-grained datasets.
  arXiv  Detail & Related papers  (2021-05-06T08:03:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.