# Any3D-VLA: Enhancing VLA Robustness via Diverse Point Clouds

arXiv: https://arxiv.org/abs/2602.00807 · HTML: https://mlsanity.com/paper/2602.00807/

## Key facts

- Cited by 13 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 48 of its 60 references that are in the map.
- First posted on arXiv 31 Jan 2026.

## 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 48)

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (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)
- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware](https://mlsanity.com/paper/2304.13705/) (2023)
- [Objaverse: A Universe of Annotated 3D Objects](https://mlsanity.com/paper/2212.08051/) (2022)
- [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)
- [Kosmos-2: Grounding Multimodal Large Language Models to the World](https://mlsanity.com/paper/2306.14824/) (2023)
- [Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success](https://mlsanity.com/paper/2502.19645/) (2025)
- [Depth Anything 3: Recovering the Visual Space from Any Views](https://mlsanity.com/paper/2511.10647/) (2025)
- [CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks](https://mlsanity.com/paper/2112.03227/) (2021)
- [SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model](https://mlsanity.com/paper/2501.15830/) (2025)
- [CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models](https://mlsanity.com/paper/2503.22020/) (2025)
- [AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems](https://mlsanity.com/paper/2503.06669/) (2025)
- [InternLM2 Technical Report](https://mlsanity.com/paper/2403.17297/) (2024)
- [Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models](https://mlsanity.com/paper/2402.07865/) (2024)
- [MapAnything: Universal Feed-Forward Metric 3D Reconstruction](https://mlsanity.com/paper/2509.13414/) (2025)
- [Orbit: A Unified Simulation Framework for Interactive Robot Learning Environments](https://mlsanity.com/paper/2301.04195/) (2023)
- [3D Diffuser Actor: Policy Diffusion with 3D Scene Representations](https://mlsanity.com/paper/2402.10885/) (2024)
- [UniDepthV2: Universal Monocular Metric Depth Estimation Made Simpler](https://mlsanity.com/paper/2502.20110/) (2025)
- [Act3D: 3D Feature Field Transformers for Multi-Task Robotic Manipulation](https://mlsanity.com/paper/2306.17817/) (2023)
- [Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model](https://mlsanity.com/paper/2510.12276/) (2025)
- [GraspVLA: a Grasping Foundation Model Pre-trained on Billion-scale Synthetic Action Data](https://mlsanity.com/paper/2505.03233/) (2025)
- [Sonata: Self-Supervised Learning of Reliable Point Representations](https://mlsanity.com/paper/2503.16429/) (2025)
- [PointVLA: Injecting the 3D World into Vision-Language-Action Models](https://mlsanity.com/paper/2503.07511/) (2025)
- [Bidirectional Projection Network for Cross Dimension Scene Understanding](https://mlsanity.com/paper/2103.14326/) (2021)

## Built on by (most cited first, 13 of 13)

- [Utonia: Toward One Encoder for All Point Clouds](https://mlsanity.com/paper/2603.03283/) (2026)
- [FASTER: Rethinking Real-Time Flow VLAs](https://mlsanity.com/paper/2603.19199/) (2026)
- [Evo-Depth: A Lightweight Depth-Enhanced Vision-Language-Action Model](https://mlsanity.com/paper/2605.14950/) (2026)
- [Learning 4D Geometric Priors for Inference-Efficient World Action Models](https://mlsanity.com/paper/2607.05468/) (2026)
- [GaussianDream: A Feed-Forward 3D Gaussian World Model for Robotic Manipulation](https://mlsanity.com/paper/2605.20752/) (2026)
- [ELAN4D: Embodiment-Centric 4D Supervision for Vision-Language-Action Models via Plug-and-Play Adaptation](https://mlsanity.com/paper/2605.30484/) (2026)
- [See like a Robot: Robot-Centric Pointmaps for VLA Models](https://mlsanity.com/paper/2607.11498/) (2026)
- [2D or 3D: Who Governs Salience in VLA Models? -- Tri-Stage Token Pruning Framework with Modality Salience Awareness](https://mlsanity.com/paper/2604.09244/) (2026)
- [Mind-VLA: Instruction-Aware Spatial Representation Alignment for Vision-Language-Action Models](https://mlsanity.com/paper/2608.04633/) (2026)
- [Toward Unified Robot Learning: Bridging Representation, Vision-Language-Action, and World Models](https://mlsanity.com/paper/2609.03927/) (2026)
- [GeomVLA: Unifying Scene, Motion, and Action in 3D](https://mlsanity.com/paper/2609.13812/) (2026)
- [Adaptive Code Generation for Controlling Robots](https://mlsanity.com/paper/2610.09588/) (2026)
- [WARP-VLA: Wrist-Camera Adaptation for View-Robust Policy Execution in Vision-Language-Action Models](https://mlsanity.com/paper/2610.11508/) (2026)

## Abstract (arXiv)

Existing Vision-Language-Action (VLA) models typically take 2D images as visual input, which limits their spatial understanding in complex scenes. How can we incorporate 3D information to enhance VLA capabilities? We conduct a pilot study across different observation spaces and visual representations. The results show that explicitly lifting visual input into point clouds yields representations that better complement their corresponding 2D representations. To address the challenges of (1) scarce 3D data and (2) the domain gap induced by cross-environment differences and depth-scale biases, we propose Any3D-VLA. It unifies the simulator, sensor, and model-estimated point clouds within a training pipeline, constructs diverse inputs, and learns domain-agnostic 3D representations that are fused with the corresponding 2D representations. Simulation and real-world experiments demonstrate Any3D-VLA's advantages in improving performance and mitigating the domain gap. Our project homepage is available at https://xianzhefan.github.io/Any3D-VLA.github.io.