# From Spatial to Actions: Grounding Vision-Language-Action Model in Spatial Foundation Priors

arXiv: https://arxiv.org/abs/2510.17439 · HTML: https://mlsanity.com/paper/2510.17439/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 44 of its 51 references that are in the map.
- First posted on arXiv 20 Oct 2025.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)
- Vision-language-action models / [3D and spatial-aware VLA](https://mlsanity.com/vla/3d-and-spatial-aware-vla/)

## Builds on (most cited first, 30 of 44)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022)
- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [Octo: An Open-Source Generalist Robot Policy](https://mlsanity.com/paper/2405.12213/) (2024)
- [Kosmos-2: Grounding Multimodal Large Language Models to the World](https://mlsanity.com/paper/2306.14824/) (2023)
- [Grounding Image Matching in 3D with MASt3R](https://mlsanity.com/paper/2406.09756/) (2024)
- [Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success](https://mlsanity.com/paper/2502.19645/) (2025)
- [ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth](https://mlsanity.com/paper/2302.12288/) (2023)
- [BridgeData V2: A Dataset for Robot Learning at Scale](https://mlsanity.com/paper/2308.12952/) (2023)
- [CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks](https://mlsanity.com/paper/2112.03227/) (2021)
- [Continuous 3D Perception Model with Persistent State](https://mlsanity.com/paper/2501.12387/) (2025)
- [SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model](https://mlsanity.com/paper/2501.15830/) (2025)
- [Evaluating Real-World Robot Manipulation Policies in Simulation](https://mlsanity.com/paper/2405.05941/) (2024)
- [Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation](https://mlsanity.com/paper/2312.13139/) (2023)
- [Vision-Language Foundation Models as Effective Robot Imitators](https://mlsanity.com/paper/2311.01378/) (2023)
- [3D-VLA: A 3D Vision-Language-Action Generative World Model](https://mlsanity.com/paper/2403.09631/) (2024)
- [TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies](https://mlsanity.com/paper/2412.10345/) (2024)
- [GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulation](https://mlsanity.com/paper/2410.06158/) (2024)
- [3D Diffuser Actor: Policy Diffusion with 3D Scene Representations](https://mlsanity.com/paper/2402.10885/) (2024)
- [Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence](https://mlsanity.com/paper/2505.23747/) (2025)
- [Language Conditioned Imitation Learning over Unstructured Data](https://mlsanity.com/paper/2005.07648/) (2020)

## Built on by (most cited first, 28 of 28)

- [Unified 4D World Action Modeling from Video Priors with Asynchronous Denoising](https://mlsanity.com/paper/2604.26694/) (2026)
- [World Guidance: World Modeling in Condition Space for Action Generation](https://mlsanity.com/paper/2602.22010/) (2026)
- [ACoT-VLA: Action Chain-of-Thought for Vision-Language-Action Models](https://mlsanity.com/paper/2601.11404/) (2026)
- [Mixture of Horizons in Action Chunking](https://mlsanity.com/paper/2511.19433/) (2025)
- [FD-VLA: Force-Distilled Vision-Language-Action Model for Contact-Rich Manipulation](https://mlsanity.com/paper/2602.02142/) (2026)
- [SimVLA: A Simple VLA Baseline for Robotic Manipulation](https://mlsanity.com/paper/2602.18224/) (2026)
- [AnyCamVLA: Zero-Shot Camera Adaptation for Viewpoint Robust Vision-Language-Action Models](https://mlsanity.com/paper/2603.05868/) (2026)
- [Holi-Spatial: Evolving Video Streams into Holistic 3D Spatial Intelligence](https://mlsanity.com/paper/2603.07660/) (2026)
- [FocusVLA: Focused Visual Utilization for Vision-Language-Action Models](https://mlsanity.com/paper/2603.28740/) (2026)
- [Understanding the Impact of Geometric Foundation Models on Vision-Language-Action Models](https://mlsanity.com/paper/2605.24642/) (2026)
- [SG-WAM: Self-Guided World Modeling in Geometry-Aware Policy Space](https://mlsanity.com/paper/2608.01397/) (2026)
- [MultihopSpatial: Multi-hop Compositional Spatial Reasoning Benchmark for Vision-Language Model](https://mlsanity.com/paper/2603.18892/) (2026)
- [VeriSpace: Spatially Grounded Action Verification for Vision-Language-Action Models](https://mlsanity.com/paper/2606.10568/) (2026)
- [From Fixed to Free Cameras: Calibration-Free View-Robust Vision-Language-Action Model](https://mlsanity.com/paper/2607.05396/) (2026)
- [NTR: Neural Token Reconstruction for Scene Token Bottleneck in End-to-End Driving](https://mlsanity.com/paper/2605.31116/) (2026)
- [Direct Action-Head Injection of A Grounded 3D Point Unlocks Spatial and Task Generalization](https://mlsanity.com/paper/2606.27663/) (2026)
- [PVI: Plug-in Visual Injection for Vision-Language-Action Models](https://mlsanity.com/paper/2603.12772/) (2026)
- [3DThinkVLA: Endowing Vision-Language-Action Models with Latent 3D Priors via 3D-Thinking-Guided Co-training](https://mlsanity.com/paper/2606.04436/) (2026)
- [World-to-Wrist: Task-Conditioned Future Wrist Modeling for Fine-Grained Robot Manipulation](https://mlsanity.com/paper/2608.05369/) (2026)
- [OmniVLA-RL: A Vision-Language-Action Model with Spatial Understanding and Online RL](https://mlsanity.com/paper/2604.17706/) (2026)
- [X-Imitator: Spatial-Aware Imitation Learning via Bidirectional Action-Pose Interaction](https://mlsanity.com/paper/2605.12162/) (2026)
- [SpatialBench: Is Your Spatial Foundation Model an All-Round Player?](https://mlsanity.com/paper/2605.27367/) (2026)
- [Breaking Structural Isolation: Scalable Graph Clustering via Community-Aware Sampling and Structural Entropy](https://mlsanity.com/paper/2607.05469/) (2026)
- [VistaVLA: Geometry- and Semantic-Aware 3D Gaussian-Grounded VLA for Robotic Manipulation](https://mlsanity.com/paper/2607.12356/) (2026)
- [GRAFT: Grounded and Efficient Online Reinforcement Adaptation for Fine-Grained Robot Manipulation](https://mlsanity.com/paper/2608.27079/) (2026)
- [StrataVLA: Hierarchical and Efficient 3D Geometric Grounding for Vision-Language-Action Models](https://mlsanity.com/paper/2609.26071/) (2026)
- [GeoBridge-VLA: Geometry-Aware Residual Adaptation for Vision-Language-Action Models](https://mlsanity.com/paper/2610.05026/) (2026)
- [Axiom-0: Hierarchical Self-Refinement for Vision-Language-Action Policies](https://mlsanity.com/paper/2610.14155/) (2026)

## Abstract (arXiv)

Existing vision-language-action (VLA) models act in 3D real-world but are typically built on 2D encoders, leaving a spatial reasoning gap that limits generalization and adaptability. Recent 3D integration techniques for VLAs either require specialized sensors and transfer poorly across modalities, or inject weak cues that lack geometry and degrade vision-language alignment. In this work, we introduce FALCON (From Spatial to Action), a novel paradigm that injects rich 3D spatial tokens into the action head. FALCON leverages spatial foundation models to deliver strong geometric priors from RGB alone, and includes an Embodied Spatial Model that can optionally fuse depth, or pose for higher fidelity when available, without retraining or architectural changes. To preserve language reasoning, spatial tokens are consumed by a Spatial-Enhanced Action Head rather than being concatenated into the vision-language backbone. These designs enable FALCON to address limitations in spatial representation, modality transferability, and alignment. In comprehensive evaluations across three simulation benchmarks and eleven real-world tasks, our proposed FALCON achieves state-of-the-art performance, consistently surpasses competitive baselines, and remains robust under clutter, spatial-prompt conditioning, and variations in object scale and height.