mlsanityData to 14 Oct 2026

Mind-VLA: Instruction-Aware Spatial Representation Alignment for Vision-Language-Action Models

arXiv 2608.04633 ↗First posted 5 Aug 2026cs.ROcited by 0

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

Abstract (arXiv)

Recent Vision-Language-Action (VLA) methods improve generalization by aligning their representations with 3D scene geometry. However, these methods are fundamentally instruction-agnostic: the representations align the entire scene uniformly, neglecting the 3D geometry of the specific target object designated by the language instruction. This causes failures on fine-grained manipulation and target occlusion tasks, where success depends on accurate 3D understanding of the target object rather than the entire scene. To address this, we present Mind-VLA, an instruction-aware spatial representation alignment method for VLA models. Specifically, Mind-VLA first obtains the target object specified by the language instruction, then prepares its canonical target views and extracts the corresponding VAE and VGGT features. Finally, the latent representation of the VLA model is aligned with these features to enable instruction-aware 3D understanding. Mind-VLA reaches 94.4% on LIBERO and 4.47 on CALVIN with a compact 345M-parameter backbone. On real-robot tasks with target occlusion, Mind-VLA reaches 54% average success, outperforming the matched scene-VGGT control by 26 percentage points.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in 3D and spatial-aware VLA, one of 13 directions in Vision-language-action models. Builds on 51 of its 51 references that are in the map. First posted on arXiv 5 Aug 2026.

Builds on

51 of 51 references.

Closest ancestors · 10

Same direction, newest first

  1. 2026Any3D-VLA: Enhancing VLA Robustness via Diverse Point Clouds31 Jan
  2. 2025StereoVLA: Enhancing Vision-Language-Action Models with Stereo Vision26 Dec
  3. 2025GLaD: Geometric Latent Distillation for Vision-Language-Action Models10 Dec
  4. 2025QDepth-VLA: Quantized Depth Prediction as Auxiliary Supervision for Vision-Language-Action Models16 Oct
  5. 2025Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model14 Oct
  6. 2025GeoVLA: Empowering 3D Representations in Vision-Language-Action Models12 Aug
  7. 2025OG-VLA: Orthographic Image Generation for 3D-Aware Vision-Language Action Model1 Jun
  8. 2025PointVLA: Injecting the 3D World into Vision-Language-Action Models10 Mar
  9. 2025SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model27 Jan
  10. 2024TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies13 Dec

Other references · 41

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2020Denoising Diffusion Implicit Modelscited by 9,781
  4. 2023Segment Anythingcited by 8,234
  5. 2022Scalable Diffusion Models with Transformerscited by 6,054
  6. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 3,080
  7. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,887
  8. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,838
  9. 2025Qwen3-VL Technical Reportcited by 2,793
  10. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,407
  11. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,061
  12. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,568
29 more
  1. 2025VGGT: Visual Geometry Grounded Transformercited by 1,539
  2. 2024Octo: An Open-Source Generalist Robot Policycited by 1,484
  3. 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learningcited by 1,410
  4. 2025SAM 3: Segment Anything with Conceptscited by 906
  5. 2023Open X-Embodiment: Robotic Learning Datasets and RT-X Modelscited by 862
  6. 2024DROID: A Large-Scale In-The-Wild Robot Manipulation Datasetcited by 852
  7. 2021CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Taskscited by 584
  8. 2022Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulationcited by 551
  9. 2025SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Roboticscited by 530
  10. 2022BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learningcited by 523
  11. 2023CoTracker: It is Better to Track Togethercited by 522
  12. 2025CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Modelscited by 451
  13. 2024CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulationcited by 422
  14. 2023Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulationcited by 364
  15. 2024Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representationscited by 289
  16. 20243D Diffuser Actor: Policy Diffusion with 3D Scene Representationscited by 282
  17. 2025SAM 3D: 3Dfy Anything in Imagescited by 247
  18. 2023RVT: Robotic View Transformer for 3D Object Manipulationcited by 225
  19. 2025DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledgecited by 213
  20. 2025HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Modelcited by 181
  21. 2024Predictive Inverse Dynamics Models are Scalable Learners for Robotic Manipulationcited by 161
  22. 2022What Matters in Language Conditioned Robotic Imitation Learning over Unstructured Datacited by 138
  23. 2023Act3D: 3D Feature Field Transformers for Multi-Task Robotic Manipulationcited by 138
  24. 2024RVT-2: Learning Precise Manipulation from Few Demonstrationscited by 137
  25. 2024Multimodal Diffusion Transformer: Learning Versatile Behavior from Multimodal Goalscited by 134
  26. 2025Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modelingcited by 96
  27. 2024Towards Synergistic, Generalized, and Efficient Dual-System for Robotic Manipulationcited by 73
  28. 2024Closed-Loop Visuomotor Control with Generative Expectation for Robotic Manipulationcited by 53
  29. 2026PALM: Progress-Aware Policy Learning via Affordance Reasoning for Long-Horizon Robotic Manipulationcited by 21

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Spatial-Aware VLA Pretraining through Visual-Physical Alignment from Human Videos
  2. 2026ROCKET: Residual-Oriented Multi-Layer Alignment for Spatially-Aware Vision-Language-Action Models
  3. 2026VEGA: Visual Encoder Grounding Alignment for Spatially-Aware Vision-Language-Action Models
  4. 20263DVLA: Enhancing Vision-Language-Action Models via 3D Spatial and Instance Understanding
  5. 2026G3VLA: Geometric inductive bias for Vision-Language-Action Models
  6. 2026Direct Action-Head Injection of A Grounded 3D Point Unlocks Spatial and Task Generalization
  7. 2026SAM3D-Guided Object-Centric Representation Alignment for Vision-Language-Action Models
  8. 2025DepthVLA: Enhancing Vision-Language-Action Models with Depth-Aware Spatial Reasoning