# Evo-0: Vision-Language-Action Model with Implicit Spatial Understanding

arXiv: https://arxiv.org/abs/2507.00416 · HTML: https://mlsanity.com/paper/2507.00416/

## Key facts

- Cited by 58 papers in the map (data through 14 Oct 2026).
- Placed in 3D and spatial-aware VLA, one of 13 directions in Vision-language-action models.
- Builds on 31 of its 34 references that are in the map.
- First posted on arXiv 1 Jul 2025.

## Placed in

- 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 31)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (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)
- [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)
- [Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data](https://mlsanity.com/paper/2401.10891/) (2024)
- [GR00T N1: An Open Foundation Model for Generalist Humanoid Robots](https://mlsanity.com/paper/2503.14734/) (2025)
- [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)
- [PaliGemma: A versatile 3B VLM for transfer](https://mlsanity.com/paper/2407.07726/) (2024)
- [RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation](https://mlsanity.com/paper/2410.07864/) (2024)
- [ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth](https://mlsanity.com/paper/2302.12288/) (2023)
- [SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model](https://mlsanity.com/paper/2501.15830/) (2025)
- [3D-VLA: A 3D Vision-Language-Action Generative World Model](https://mlsanity.com/paper/2403.09631/) (2024)
- [Rectified Flow: A Marginal Preserving Approach to Optimal Transport](https://mlsanity.com/paper/2209.14577/) (2022)
- [MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic Videos](https://mlsanity.com/paper/2412.04463/) (2024)
- [Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence](https://mlsanity.com/paper/2505.23747/) (2025)
- [HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Model](https://mlsanity.com/paper/2503.10631/) (2025)
- [SpatialBot: Precise Spatial Understanding with Vision Language Models](https://mlsanity.com/paper/2406.13642/) (2024)
- [RVT-2: Learning Precise Manipulation from Few Demonstrations](https://mlsanity.com/paper/2406.08545/) (2024)
- [VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) Manifold](https://mlsanity.com/paper/2505.12549/) (2025)
- [PointVLA: Injecting the 3D World into Vision-Language-Action Models](https://mlsanity.com/paper/2503.07511/) (2025)
- [BridgeVLA: Input-Output Alignment for Efficient 3D Manipulation Learning with Vision-Language Models](https://mlsanity.com/paper/2506.07961/) (2025)
- [MM-Spatial: Exploring 3D Spatial Understanding in Multimodal LLMs](https://mlsanity.com/paper/2503.13111/) (2025)
- [Lift3D Foundation Policy: Lifting 2D Large-Scale Pretrained Models for Robust 3D Robotic Manipulation](https://mlsanity.com/paper/2411.18623/) (2024)

## Built on by (most cited first, 30 of 58)

- [Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model](https://mlsanity.com/paper/2510.12276/) (2025)
- [Vision-Language-Action Models for Robotics: A Review Towards Real-World Applications](https://mlsanity.com/paper/2510.07077/) (2025)
- [Unified 4D World Action Modeling from Video Priors with Asynchronous Denoising](https://mlsanity.com/paper/2604.26694/) (2026)
- [Pure Vision Language Action (VLA) Models: A Comprehensive Survey](https://mlsanity.com/paper/2509.19012/) (2025)
- [Evo-1: Lightweight Vision-Language-Action Model with Preserved Semantic Alignment](https://mlsanity.com/paper/2511.04555/) (2025)
- [VLSA: Vision-Language-Action Models with Plug-and-Play Safety Constraint Layer](https://mlsanity.com/paper/2512.11891/) (2025)
- [ACoT-VLA: Action Chain-of-Thought for Vision-Language-Action Models](https://mlsanity.com/paper/2601.11404/) (2026)
- [Why Do MLLMs Struggle with Spatial Understanding? A Systematic Analysis from Data to Architecture](https://mlsanity.com/paper/2509.02359/) (2025)
- [From Spatial to Actions: Grounding Vision-Language-Action Model in Spatial Foundation Priors](https://mlsanity.com/paper/2510.17439/) (2025)
- [GeoAware-VLA: Implicit Geometry Aware Vision-Language-Action Model](https://mlsanity.com/paper/2509.14117/) (2025)
- [SwiftVLA: Unlocking Spatiotemporal Dynamics for Lightweight VLA Models at Minimal Overhead](https://mlsanity.com/paper/2512.00903/) (2025)
- [JEPA-VLA: Video Predictive Embedding is Needed for VLA Models](https://mlsanity.com/paper/2602.11832/) (2026)
- [Mixture of Horizons in Action Chunking](https://mlsanity.com/paper/2511.19433/) (2025)
- [PALM: Progress-Aware Policy Learning via Affordance Reasoning for Long-Horizon Robotic Manipulation](https://mlsanity.com/paper/2601.07060/) (2026)
- [VGGDrive: Empowering Vision-Language Models with Cross-View Geometric Grounding for Autonomous Driving](https://mlsanity.com/paper/2602.20794/) (2026)
- [StereoVLA: Enhancing Vision-Language-Action Models with Stereo Vision](https://mlsanity.com/paper/2512.21970/) (2025)
- [Learning to Feel the Future: DreamTacVLA for Contact-Rich Manipulation](https://mlsanity.com/paper/2512.23864/) (2025)
- [Evo-Depth: A Lightweight Depth-Enhanced Vision-Language-Action Model](https://mlsanity.com/paper/2605.14950/) (2026)
- [Any3D-VLA: Enhancing VLA Robustness via Diverse Point Clouds](https://mlsanity.com/paper/2602.00807/) (2026)
- [DTP: A Simple yet Effective Distracting Token Pruning Framework for Vision-Language Action Models](https://mlsanity.com/paper/2601.16065/) (2026)
- [Gaze2Act: Gaze-Conditioned Vision-Language-Action Policies for Interactive Robot Manipulation](https://mlsanity.com/paper/2605.30282/) (2026)
- [IntentVLA: Short-Horizon Intent Modeling for Aliased Robot Manipulation](https://mlsanity.com/paper/2605.14712/) (2026)
- [3D-Mix for VLA: A Plug-and-Play Module for Integrating VGGT-based 3D Information into Vision-Language-Action Models](https://mlsanity.com/paper/2603.24393/) (2026)
- [ConsisVLA-4D: Advancing Spatiotemporal Consistency in Efficient 3D-Perception and 4D-Reasoning for Robotic Manipulation](https://mlsanity.com/paper/2605.05126/) (2026)
- [LA4VLA: Learning to Act without Seeing via Language-Action Pretraining](https://mlsanity.com/paper/2606.27295/) (2026)
- [UAOR: Uncertainty-aware Observation Reinjection for Vision-Language-Action Models](https://mlsanity.com/paper/2602.18020/) (2026)
- [An Anatomy of Vision-Language-Action Models: From Modules to Milestones and Challenges](https://mlsanity.com/paper/2512.11362/) (2025)
- [Real2Edit2Real: Generating Robotic Demonstrations via a 3D Control Interface](https://mlsanity.com/paper/2512.19402/) (2025)
- [Understanding the Impact of Geometric Foundation Models on Vision-Language-Action Models](https://mlsanity.com/paper/2605.24642/) (2026)
- [Embodied3DBench: Benchmarking Low-Level Embodied Spatial Intelligence of Vision Language Models](https://mlsanity.com/paper/2605.29074/) (2026)

## Abstract (arXiv)

Vision-Language-Action (VLA) models have emerged as a promising framework for enabling generalist robots capable of perceiving, reasoning, and acting in the real world. These models usually build upon pretrained Vision-Language Models (VLMs), which excel at semantic understanding due to large-scale image and text pretraining. However, existing VLMs typically lack precise spatial understanding capabilities, as they are primarily tuned on 2D image-text pairs without 3D supervision. To address this limitation, recent approaches have incorporated explicit 3D inputs such as point clouds or depth maps, but this necessitates additional depth sensors or pre-trained depth estimation models, which may yield defective results. In contrast, our work introduces a plug-and-play module that implicitly incorporates 3D geometry features into VLA models by leveraging an off-the-shelf visual geometry foundation model. This integration provides the model with depth-aware visual representations, improving its ability to understand the geometric structure of the scene and the spatial relationships among objects from RGB images alone. We evaluate our method on a set of spatially challenging tasks in both simulation and the real world. Extensive evaluations show that our method significantly improves the performance of state-of-the-art VLA models across diverse scenarios.