# GeoAware-VLA: Implicit Geometry Aware Vision-Language-Action Model

arXiv: https://arxiv.org/abs/2509.14117 · HTML: https://mlsanity.com/paper/2509.14117/

## Key facts

- Cited by 26 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 35 of its 46 references that are in the map.
- First posted on arXiv 17 Sep 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 35)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [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)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [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)
- [LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning](https://mlsanity.com/paper/2306.03310/) (2023)
- [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features](https://mlsanity.com/paper/2502.14786/) (2025)
- [Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success](https://mlsanity.com/paper/2502.19645/) (2025)
- [A Generalist Agent](https://mlsanity.com/paper/2205.06175/) (2022)
- [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)
- [Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation](https://mlsanity.com/paper/2209.05451/) (2022)
- [Evaluating Real-World Robot Manipulation Policies in Simulation](https://mlsanity.com/paper/2405.05941/) (2024)
- [Implicit Behavioral Cloning](https://mlsanity.com/paper/2109.00137/) (2021)
- [3D Diffuser Actor: Policy Diffusion with 3D Scene Representations](https://mlsanity.com/paper/2402.10885/) (2024)
- [Behavior Generation with Latent Actions](https://mlsanity.com/paper/2403.03181/) (2024)
- [MUSt3R: Multi-view Network for Stereo 3D Reconstruction](https://mlsanity.com/paper/2503.01661/) (2025)
- [Act3D: 3D Feature Field Transformers for Multi-Task Robotic Manipulation](https://mlsanity.com/paper/2306.17817/) (2023)
- [Decomposing the Generalization Gap in Imitation Learning for Visual Robotic Manipulation](https://mlsanity.com/paper/2307.03659/) (2023)
- [Multi-View Masked World Models for Visual Robotic Manipulation](https://mlsanity.com/paper/2302.02408/) (2023)
- [BAKU: An Efficient Transformer for Multi-Task Policy Learning](https://mlsanity.com/paper/2406.07539/) (2024)
- [Learning Generalizable Manipulation Policies with Object-Centric 3D Representations](https://mlsanity.com/paper/2310.14386/) (2023)

## Built on by (most cited first, 26 of 26)

- [VGGT-Omega](https://mlsanity.com/paper/2605.15195/) (2026)
- [VGGDrive: Empowering Vision-Language Models with Cross-View Geometric Grounding for Autonomous Driving](https://mlsanity.com/paper/2602.20794/) (2026)
- [Evo-Depth: A Lightweight Depth-Enhanced Vision-Language-Action Model](https://mlsanity.com/paper/2605.14950/) (2026)
- [VLA Models Are More Generalizable Than You Think: Revisiting Physical and Spatial Modeling](https://mlsanity.com/paper/2512.02902/) (2025)
- [Geometric Action Model for Robot Policy Learning](https://mlsanity.com/paper/2606.17046/) (2026)
- [AnyCamVLA: Zero-Shot Camera Adaptation for Viewpoint Robust Vision-Language-Action Models](https://mlsanity.com/paper/2603.05868/) (2026)
- [ConsisVLA-4D: Advancing Spatiotemporal Consistency in Efficient 3D-Perception and 4D-Reasoning for Robotic Manipulation](https://mlsanity.com/paper/2605.05126/) (2026)
- [Understanding the Impact of Geometric Foundation Models on Vision-Language-Action Models](https://mlsanity.com/paper/2605.24642/) (2026)
- [Learning Action Manifold with Multi-view Latent Priors for Robotic Manipulation](https://mlsanity.com/paper/2605.11832/) (2026)
- [GaussianDream: A Feed-Forward 3D Gaussian World Model for Robotic Manipulation](https://mlsanity.com/paper/2605.20752/) (2026)
- [From Fixed to Free Cameras: Calibration-Free View-Robust Vision-Language-Action Model](https://mlsanity.com/paper/2607.05396/) (2026)
- [R3DP: Real-Time 3D-Aware Policy for Embodied Manipulation](https://mlsanity.com/paper/2603.14498/) (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)
- [Cross-View Action Consistency for Camera-Robust Vision-Language-Action Policies](https://mlsanity.com/paper/2608.06965/) (2026)
- [Domain Arithmetic: One-Shot VLA Adaptation under Environmental Shifts](https://mlsanity.com/paper/2607.00666/) (2026)
- [The Moving Eye: Enhancing VLA Spatial Generalization via Hybrid Dynamic Data Collection](https://mlsanity.com/paper/2607.02322/) (2026)
- [RayViT: Ray-Conditioned Visual Representations for Viewpoint-Robust Imitation Learning](https://mlsanity.com/paper/2607.29622/) (2026)
- [Decoupling Intention from Trajectory: A Representational Deduction Framework for World Action Models](https://mlsanity.com/paper/2608.06994/) (2026)
- [GaussianDream++: Efficient 3D Gaussian World Modeling for Robotic Manipulation](https://mlsanity.com/paper/2608.25659/) (2026)
- [InfiNoVA: Infinite Novel View Augmentation for Viewpoint Invariant Robot Policies](https://mlsanity.com/paper/2609.27734/) (2026)
- [MVG-WAM: Multiple View Geometry-Aware World-Action Modeling for Robotic Manipulation](https://mlsanity.com/paper/2609.37793/) (2026)
- [Less Decoder is More Encoder: Geometric Representation Learning from Novel View Synthesis](https://mlsanity.com/paper/2610.03717/) (2026)
- [VLA-ZO: Fast Zeroth-Order Adaptation for Vision-Language-Action Models](https://mlsanity.com/paper/2610.06271/) (2026)
- [WARP-VLA: Wrist-Camera Adaptation for View-Robust Policy Execution in Vision-Language-Action Models](https://mlsanity.com/paper/2610.11508/) (2026)
- [VersaCamVLA: Camera-Configurable VLA Policies for Robotic Manipulation](https://mlsanity.com/paper/2610.12451/) (2026)

## Abstract (arXiv)

Vision-Language-Action (VLA) models often fail to generalize to unseen camera viewpoints, a limitation stemming from their difficulty in inferring robust 3D geometry from 2D images. We introduce GeoAware-VLA, a simple yet effective approach that enhances viewpoint invariance by integrating strong geometric priors into the vision backbone. Instead of training a visual encoder or relying on explicit 3D data, we leverage a frozen, pretrained geometric vision model as a feature extractor. A lightweight, trainable projection layer then adapts these geometrically-rich features for the policy decoder, relieving it of the burden of learning 3D consistency from scratch. Through extensive evaluations on the LIBERO and CALVIN benchmarks, we show that GeoAware-VLA preserves and even improves in-distribution performance while achieving substantial gains in zero-shot generalization to unseen camera poses, improving unseen-view success rates by an average of 35 percentage points on LIBERO and over 11 percentage points on CALVIN compared to their respective baselines. Crucially, these gains transfer to the physical world, where our model shows significant improvement on a real robotic platform. Our approach proves effective across both continuous and discrete action spaces, highlighting that robust geometric grounding is a key ingredient for building more generalizable robotic agents.