# DepthVLA: Enhancing Vision-Language-Action Models with Depth-Aware Spatial Reasoning

arXiv: https://arxiv.org/abs/2510.13375 · HTML: https://mlsanity.com/paper/2510.13375/

## Key facts

- Cited by 46 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 47 of its 49 references that are in the map.
- First posted on arXiv 15 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 47)

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [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)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [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)
- [Octo: An Open-Source Generalist Robot Policy](https://mlsanity.com/paper/2405.12213/) (2024)
- [Depth Anything V2](https://mlsanity.com/paper/2406.09414/) (2024)
- [LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning](https://mlsanity.com/paper/2306.03310/) (2023)
- [Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data](https://mlsanity.com/paper/2401.10891/) (2024)
- [Depth Map Prediction from a Single Image using a Multi-Scale Deep Network](https://mlsanity.com/paper/1406.2283/) (2014)
- [Grounding Image Matching in 3D with MASt3R](https://mlsanity.com/paper/2406.09756/) (2024)
- [DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset](https://mlsanity.com/paper/2403.12945/) (2024)
- [ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes](https://mlsanity.com/paper/2308.11417/) (2023)
- [Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs](https://mlsanity.com/paper/2401.06209/) (2024)
- [PaliGemma: A versatile 3B VLM for transfer](https://mlsanity.com/paper/2407.07726/) (2024)
- [BridgeData V2: A Dataset for Robot Learning at Scale](https://mlsanity.com/paper/2308.12952/) (2023)
- [Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding](https://mlsanity.com/paper/2011.02523/) (2020)
- [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)
- [CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models](https://mlsanity.com/paper/2503.22020/) (2025)
- [MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion](https://mlsanity.com/paper/2410.03825/) (2024)
- [CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation](https://mlsanity.com/paper/2411.19650/) (2024)
- [Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models](https://mlsanity.com/paper/2402.07865/) (2024)
- [3D-VLA: A 3D Vision-Language-Action Generative World Model](https://mlsanity.com/paper/2403.09631/) (2024)
- [3D Reconstruction with Spatial Memory](https://mlsanity.com/paper/2408.16061/) (2024)
- [Unified World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets](https://mlsanity.com/paper/2504.02792/) (2025)
- [DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge](https://mlsanity.com/paper/2507.04447/) (2025)

## Built on by (most cited first, 30 of 46)

- [World Action Models: The Next Frontier in Embodied AI](https://mlsanity.com/paper/2605.12090/) (2026)
- [ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?](https://mlsanity.com/paper/2606.19531/) (2026)
- [ACoT-VLA: Action Chain-of-Thought for Vision-Language-Action Models](https://mlsanity.com/paper/2601.11404/) (2026)
- [Adaptive Action Chunking at Inference-time for Vision-Language-Action Models](https://mlsanity.com/paper/2604.04161/) (2026)
- [JEPA-VLA: Video Predictive Embedding is Needed for VLA Models](https://mlsanity.com/paper/2602.11832/) (2026)
- [Generation Enhances Understanding in Unified Multimodal Models via Multi-Representation Generation](https://mlsanity.com/paper/2601.21406/) (2026)
- [UniDriveVLA: Unifying Understanding, Perception, and Action Planning for Autonomous Driving](https://mlsanity.com/paper/2604.02190/) (2026)
- [StereoVLA: Enhancing Vision-Language-Action Models with Stereo Vision](https://mlsanity.com/paper/2512.21970/) (2025)
- [S-VAM: Shortcut Video-Action Model by Self-Distilling Geometric and Semantic Foresight](https://mlsanity.com/paper/2603.16195/) (2026)
- [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)
- [SimVLA: A Simple VLA Baseline for Robotic Manipulation](https://mlsanity.com/paper/2602.18224/) (2026)
- [GuidedVLA: Specifying Task-Relevant Factors via Plug-and-Play Action Attention Specialization](https://mlsanity.com/paper/2605.12369/) (2026)
- [PointACT: Vision-Language-Action Models with Multi-Scale Point-Action Interaction](https://mlsanity.com/paper/2605.21414/) (2026)
- [DreamWAM: Beyond RGB Future Prediction for World Action Models](https://mlsanity.com/paper/2608.04996/) (2026)
- [FocusVLA: Focused Visual Utilization for Vision-Language-Action Models](https://mlsanity.com/paper/2603.28740/) (2026)
- [GEM: Generative Supervision Helps Embodied Intelligence](https://mlsanity.com/paper/2605.28548/) (2026)
- [UniLACT: Depth-Aware RGB Latent Action Learning for Vision-Language-Action Models](https://mlsanity.com/paper/2602.20231/) (2026)
- [Look Before Acting: Enhancing Vision Foundation Representations for Vision-Language-Action Models](https://mlsanity.com/paper/2603.15618/) (2026)
- [Spatial Memory for Out-of-Vision Manipulation in Vision-Language-Action](https://mlsanity.com/paper/2605.22283/) (2026)
- [Afford-VLA: Action-Aligned Visual Planning via Internalized Affordance](https://mlsanity.com/paper/2605.24203/) (2026)
- [Learning Panorama-Aware VLA for Mobile Manipulation with Whole-Body Teleoperation](https://mlsanity.com/paper/2608.02257/) (2026)
- [Learning Action Manifold with Multi-view Latent Priors for Robotic Manipulation](https://mlsanity.com/paper/2605.11832/) (2026)
- [GesVLA: Gesture-Aware Vision-Language-Action Model Embedded Representations](https://mlsanity.com/paper/2605.22812/) (2026)
- [MotionVLA: Injecting Geometric Motion into Vision-Language-Action Model](https://mlsanity.com/paper/2606.08288/) (2026)
- [GEAR-VLA: Learning Geometry-Aware Action Representations for Generalizable Robotic Manipulation](https://mlsanity.com/paper/2606.08530/) (2026)
- [Z-1: Efficient Reinforcement Learning for Vision-Language-Action Models](https://mlsanity.com/paper/2606.31846/) (2026)
- [DepthCache: Depth-Guided Training-Free Visual Token Merging for Vision-Language-Action Model Inference](https://mlsanity.com/paper/2603.10469/) (2026)
- [PVI: Plug-in Visual Injection for Vision-Language-Action Models](https://mlsanity.com/paper/2603.12772/) (2026)
- [R3D: Revisiting 3D Policy Learning](https://mlsanity.com/paper/2604.15281/) (2026)

## Abstract (arXiv)

Vision-Language-Action (VLA) models have recently shown impressive generalization and language-guided manipulation capabilities. However, their performance degrades on tasks requiring precise spatial reasoning due to limited spatial reasoning inherited from Vision-Language Models (VLMs). Existing VLAs rely on extensive action-data pretraining to ground VLMs in 3D space, which reduces training efficiency and is still insufficient for accurate spatial understanding. In this work, we present DepthVLA, a simple yet effective VLA architecture that explicitly incorporates spatial awareness through a pretrained depth prediction module. DepthVLA adopts a mixture-of-transformers design that unifies a VLM, a depth transformer, and an action expert with fully shared attentions, forming an end-to-end model with enhanced spatial reasoning. Extensive evaluations in both real-world and simulated environments show that DepthVLA outperforms state-of-the-art approaches, achieving 78.5% vs. 65.0% progress in real-world tasks, 94.9% vs. 93.6% in the LIBERO simulator, and 74.8% vs. 58.8% in the Simpler simulator. Our code will be made publicly available.