mlsanityData to 7 Oct 2026

3D and spatial-aware VLA

129 papers0 this weekHigh confidence in this grouping: the papers form one clear topicHigh confidence in this grouping: the papers form one clear topic · About

Keywords: spatial, manipulation, vla, action, vision-language-action

Key facts. 3D and spatial-aware VLA: 129 papers on arXiv since 2023 (data through 7 Oct 2026). 71 of its 129 mapped papers (55%) cite “SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model” (2025, arXiv 2501.15830). 42 of its 129 mapped papers (33%) cite “3D-VLA: A 3D Vision-Language-Action Generative World Model” (2024, arXiv 2403.09631). 13 new papers 17 Sep–7 Oct.

What’s new

17 Sep – 7 Oct 2026

13 new papers, 17 Sep – 7 Oct; 0 this week.

  1. Earlier · 13
  2. GeoBridge-VLA: Geometry-Aware Residual Adaptation for Vision-Language-Action Models
  3. ExStereo: Lifting 2D Vision-Language-Action Models to 3D with Explicit Stereo Representations
  4. ChunkVLA-AM: Parallel Action Chunking for Vision-Language-Action Robot Control in Additive Manufacturing also fits: Efficient VLA inference and adaptation
  5. Correcting WHERE, Preserving HOW: Compositional Generalization for Vision-Language-Action Models via Referential Guidance also fits: Generalist VLA models and benchmarks
  6. Beyond Token Importance: Preserving Spatial Scaffolds for Efficient Vision-Language-Action Inference also fits: Efficient VLA inference and adaptation
  7. Spatial Grafting: Grounding 3D Features for Flow-Matching Robot Policies
  8. InfiNoVA: Infinite Novel View Augmentation for Viewpoint Invariant Robot Policies also fits: Human-video and latent-action pretraining
  9. HABILIS Brain 0: Geometry-Change Supervision for Vision-Language-Action and Residual Flow Recovery
  10. PanoFuse: Panorama-Enhanced Vision-Language-Action Learning with Decoupled Semantic-Geometric Routing
  11. Bridge3D: Enabling Vision-Language-Action Models to See and Act in 3D
All 13
  1. Topology-Informed Visual Prompting For Vision Language Action Policies
  2. Grounded Action Model: 3D Grounding as a Foundation for Robotics also fits: World model-based VLA
  3. FOCAL-VLA: Subtask-Guided Geometry Distillation and Implicit World Modeling for Vision-Language-Action Models

Foundations

Most cited by papers here

  1. SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model2025cited by 71 here
  2. 3D-VLA: A 3D Vision-Language-Action Generative World Model2024cited by 42 here
  3. PointVLA: Injecting the 3D World into Vision-Language-Action Models2025cited by 36 here
  4. TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies2024cited by 32 here
  5. GeoVLA: Empowering 3D Representations in Vision-Language-Action Models2025cited by 27 here

Lineage

The papers this direction builds on, oldest first.

Each paper on the line cites the one before.

  1. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 93 here
  2. 2024Octo: An Open-Source Generalist Robot Policycited by 69 here
  3. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 114 here
  4. 2024TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulationcited by 17 here
  5. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 91 here
  6. 2025FAST: Efficient Action Tokenization for Vision-Language-Action Modelscited by 36 here
  7. 2025SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Modelcited by 71 here
  8. 2025PointVLA: Injecting the 3D World into Vision-Language-Action Modelscited by 36 here
  9. 2025BridgeVLA: Input-Output Alignment for Efficient 3D Manipulation Learning with Vision-Language Modelscited by 24 here
  10. 2025Evo-0: Vision-Language-Action Model with Implicit Spatial Understandingcited by 18 here
  11. 2025Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Modelcited by 26 here
13 more it builds on, not in this chain
  1. 20243D-VLA: A 3D Vision-Language-Action Generative World Modelcited by 42 here
  2. 2024Robotic Control via Embodied Chain-of-Thought Reasoningcited by 19 here
  3. 2024CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulationcited by 31 here
  4. 2024TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policiescited by 32 here
  5. 2025Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Successcited by 48 here
  6. 2025CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Modelscited by 38 here
  7. 2025π0.5: a Vision-Language-Action Model with Open-World Generalizationcited by 72 here
  8. 2025UniVLA: Learning to Act Anywhere with Task-centric Latent Actionscited by 21 here
  9. 2025SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Roboticscited by 19 here
  10. 20254D-VLA: Spatiotemporal Vision-Language-Action Pretraining with Cross-Scene Calibrationcited by 18 here
  11. 2025DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledgecited by 18 here
  12. 2025GeoVLA: Empowering 3D Representations in Vision-Language-Action Modelscited by 27 here
  13. 2025LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Modelscited by 22 here

The 24 most cited of 298.

Browse

30 of 129, ranked 6–35

  1. 6Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model202526
  2. 7BridgeVLA: Input-Output Alignment for Efficient 3D Manipulation Learning with Vision-Language Models202524
  3. 84D-VLA: Spatiotemporal Vision-Language-Action Pretraining with Cross-Scene Calibration202518
  4. 9Evo-0: Vision-Language-Action Model with Implicit Spatial Understanding202518
  5. 103D CAVLA: Leveraging Depth and 3D Context to Generalize Vision Language Action Models for Unseen Tasks202516
  6. 11DepthVLA: Enhancing Vision-Language-Action Models with Depth-Aware Spatial Reasoning202513
  7. 12QDepth-VLA: Quantized Depth Prediction as Auxiliary Supervision for Vision-Language-Action Models202511
  8. 13GeoAware-VLA: Implicit Geometry Aware Vision-Language-Action Model202510
  9. 14From Spatial to Actions: Grounding Vision-Language-Action Model in Spatial Foundation Priors20259
  10. 15OG-VLA: Orthographic Image Generation for 3D-Aware Vision-Language Action Model20257
All 30
  1. 16InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy20257
  2. 17GraphCoT-VLA: A 3D Spatial-Aware Reasoning Vision-Language-Action Model for Robotic Manipulation with Ambiguous Instructions20256
  3. 18Any3D-VLA: Enhancing VLA Robustness via Diverse Point Clouds20265
  4. 19StereoVLA: Enhancing Vision-Language-Action Models with Stereo Vision20255
  5. 20ROCKET: Residual-Oriented Multi-Layer Alignment for Spatially-Aware Vision-Language-Action Models20264
  6. 21GeoPredict: Leveraging Predictive Kinematics and 3D Gaussian Geometry for Precise VLA Manipulation20254
  7. 22AnyCamVLA: Zero-Shot Camera Adaptation for Viewpoint Robust Vision-Language-Action Models20263
  8. 23Evo-Depth: A Lightweight Depth-Enhanced Vision-Language-Action Model20263
  9. 24Spatial Traces: Enhancing VLA Models with Spatial-Temporal Understanding20253
  10. 25Grounding Actions in Camera Space: Observation-Centric Vision-Language-Action Policy20253
  11. 26VLA-4D: Embedding 4D Awareness into Vision-Language-Action Models for SpatioTemporally Coherent Robotic Manipulation20253
  12. 27GLaD: Geometric Latent Distillation for Vision-Language-Action Models20253
  13. 28AugVLA-3D: Depth-Driven Feature Augmentation for Vision-Language-Action Models20262
  14. 29PoseVLA: Universal Pose Pretraining for Generalizable Vision-Language-Action Policies20262
  15. 303D-Mix for VLA: A Plug-and-Play Module for Integrating VGGT-based 3D Information into Vision-Language-Action Models20262
  16. 31LaMP: Learning Vision-Language-Action Policy with 3D Scene Flow as Latent Motion Prior20262
  17. 32Spatial-Aware VLA Pretraining through Visual-Physical Alignment from Human Videos20252
  18. 33DynamicVLA: A Vision-Language-Action Model for Dynamic Object Manipulation20261
  19. 34GeneralVLA: Generalizable Vision-Language-Action Models with Knowledge-Guided Trajectory Planning20261
  20. 35ST4VLA: Spatially Guided Training for Vision-Language-Action Models20261