mlsanityData to 7 Oct 2026

Any3D-VLA: Enhancing VLA Robustness via Diverse Point Clouds

arXiv 2602.00807 ↗First posted 31 Jan 2026cs.CV cs.ROcited by 13

On the map: Vision-language-action models → 3D and spatial-aware VLA

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.

Key facts. Cited by 13 papers in the map (data through 7 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.

Builds on

48 of 60 references.

Closest ancestors · 9

Same direction, newest first

  1. 2025QDepth-VLA: Quantized Depth Prediction as Auxiliary Supervision for Vision-Language-Action Models16 Oct
  2. 2025DepthVLA: Enhancing Vision-Language-Action Models with Depth-Aware Spatial Reasoning15 Oct
  3. 2025Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model14 Oct
  4. 2025GeoVLA: Empowering 3D Representations in Vision-Language-Action Models12 Aug
  5. 2025Evo-0: Vision-Language-Action Model with Implicit Spatial Understanding1 Jul
  6. 2025BridgeVLA: Input-Output Alignment for Efficient 3D Manipulation Learning with Vision-Language Models9 Jun
  7. 20253D CAVLA: Leveraging Depth and 3D Context to Generalize Vision Language Action Models for Unseen Tasks9 May
  8. 2025PointVLA: Injecting the 3D World into Vision-Language-Action Models10 Mar
  9. 2025SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model27 Jan

Other references · 39

  1. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  2. 2022Flow Matching for Generative Modelingcited by 5,426
  3. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,048
  4. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,777
  5. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,297
  6. 2025π0.5: a Vision-Language-Action Model with Open-World Generalizationcited by 1,653
  7. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,522
  8. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,490
  9. 2025VGGT: Visual Geometry Grounded Transformercited by 1,475
  10. 2024Octo: An Open-Source Generalist Robot Policycited by 1,427
  11. 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learningcited by 1,338
  12. 2023Kosmos-2: Grounding Multimodal Large Language Models to the Worldcited by 1,075
27 more
  1. 2025Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Successcited by 844
  2. 2025Depth Anything 3: Recovering the Visual Space from Any Viewscited by 626
  3. 2021CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Taskscited by 564
  4. 2025CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Modelscited by 440
  5. 2024InternLM2 Technical Reportcited by 391
  6. 2025AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systemscited by 390
  7. 2024Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Modelscited by 336
  8. 2025MapAnything: Universal Feed-Forward Metric 3D Reconstructioncited by 295
  9. 20243D Diffuser Actor: Policy Diffusion with 3D Scene Representationscited by 278
  10. 2023Orbit: A Unified Simulation Framework for Interactive Robot Learning Environmentscited by 239
  11. 2025UniDepthV2: Universal Monocular Metric Depth Estimation Made Simplercited by 170
  12. 2023Act3D: 3D Feature Field Transformers for Multi-Task Robotic Manipulationcited by 135
  13. 2025GraspVLA: a Grasping Foundation Model Pre-trained on Billion-scale Synthetic Action Datacited by 120
  14. 2025Sonata: Self-Supervised Learning of Reliable Point Representationscited by 108
  15. 2021Bidirectional Projection Network for Cross Dimension Scene Understandingcited by 95
  16. 2025Dita: Scaling Diffusion Transformer for Generalist Vision-Language-Action Policycited by 73
  17. 2025Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representationscited by 42
  18. 2024WorDepth: Variational Language Prior for Monocular Depth Estimationcited by 34
  19. 2025GraspGen: A Diffusion-based Framework for 6-DOF Grasping with On-Generator Trainingcited by 32
  20. 2024ODIN: A Single Model for 2D and 3D Segmentationcited by 25
  21. 2024RSA: Resolving Scale Ambiguities in Monocular Depth Estimators through Language Descriptionscited by 20
  22. 2025Is Diversity All You Need for Scalable Robotic Manipulation?cited by 19
  23. 2024BODex: Scalable and Efficient Robotic Dexterous Grasp Synthesis Using Bilevel Optimizationcited by 18
  24. 2025Vision-Language Embodiment for Monocular Depth Estimationcited by 16
  25. 20243D-MVP: 3D Multiview Pretraining for Robotic Manipulationcited by 10
  26. 2025SpatialActor: Exploring Disentangled Spatial Representations for Robust Robotic Manipulationcited by 5
  27. 2025TR2M: Transferring Monocular Relative Depth to Metric Depth with Language Descriptions and Dual-Level Scale-Oriented Contrastcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 13.

13 papers.

Sort:

By area:

  1. 2026FASTER: Rethinking Real-Time Flow VLAscited by 20
  2. 2026Utonia: Toward One Encoder for All Point Cloudscited by 18
  3. 2026Learning 4D Geometric Priors for Inference-Efficient World Action Modelscited by 14
  4. 2026Evo-Depth: A Lightweight Depth-Enhanced Vision-Language-Action Modelcited by 13
  5. 2026GaussianDream: A Feed-Forward 3D Gaussian World Model for Robotic Manipulationcited by 3
  6. 2026ELAN4D: Embodiment-Centric 4D Supervision for Vision-Language-Action Models via Plug-and-Play Adaptationcited by 1
  7. 2026See like a Robot: Robot-Centric Pointmaps for VLA Modelscited by 1
  8. 20262D or 3D: Who Governs Salience in VLA Models? -- Tri-Stage Token Pruning Framework with Modality Salience Awarenesscited by 0
  9. 2026Mind-VLA: Instruction-Aware Spatial Representation Alignment for Vision-Language-Action Modelscited by 0
  10. 2026Toward Unified Robot Learning: Bridging Representation, Vision-Language-Action, and World Modelscited by 0
  11. 2026GeomVLA: Unifying Scene, Motion, and Action in 3Dcited by 0
  12. 2026Adaptive Code Generation for Controlling Robotscited by 0
1 more
  1. 2026WARP-VLA: Wrist-Camera Adaptation for View-Robust Policy Execution in Vision-Language-Action Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025GeoAware-VLA: Implicit Geometry Aware Vision-Language-Action Model
  2. 2024VLA-3D: A Dataset for 3D Semantic Scene Understanding and Navigation
  3. 2025SwiftVLA: Unlocking Spatiotemporal Dynamics for Lightweight VLA Models at Minimal Overhead
  4. 2026PointACT: Vision-Language-Action Models with Multi-Scale Point-Action Interaction
  5. 2026VLM3: Vision Language Models Are Native 3D Learners
  6. 2025Learning from Videos for 3D World: Enhancing MLLMs with 3D Vision Geometry Priors
  7. 2025LEO-VL: Efficient Scene Representation for Scalable 3D Vision-Language Learning
  8. 2026VLGA: Vision-Language-Geometry-Action Models for Autonomous Driving