mlsanityData to 7 Oct 2026

QDepth-VLA: Quantized Depth Prediction as Auxiliary Supervision for Vision-Language-Action Models

arXiv 2510.14836 ↗First posted 16 Oct 2025cs.CV cs.ROcited by 19

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

Abstract (arXiv)

Spatial perception and reasoning are crucial for Vision-Language-Action (VLA) models to accomplish fine-grained manipulation tasks. However, existing approaches often lack the ability to understand and reason over the essential 3D structures necessary for precise control. To address this limitation, we propose QDepth-VLA, a general framework that augments VLA models with an auxiliary depth prediction task. A dedicated depth expert is designed to predict quantized latent tokens of depth maps obtained from a VQ-VAE encoder, enabling the model to learn depth-aware representations that capture critical geometric cues. Experimental results on the simulation benchmarks and real-world tasks demonstrate that QDepth-VLA yields strong spatial reasoning and competitive performance on manipulation tasks.

Key facts. Cited by 19 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 37 of its 50 references that are in the map. First posted on arXiv 16 Oct 2025.

Builds on

37 of 50 references.

Closest ancestors · 6

Same direction, newest first

  1. 2025GeoVLA: Empowering 3D Representations in Vision-Language-Action Models12 Aug
  2. 20254D-VLA: Spatiotemporal Vision-Language-Action Pretraining with Cross-Scene Calibration27 Jun
  3. 20253D CAVLA: Leveraging Depth and 3D Context to Generalize Vision Language Action Models for Unseen Tasks9 May
  4. 2025PointVLA: Injecting the 3D World into Vision-Language-Action Models10 Mar
  5. 2025SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model27 Jan
  6. 20243D-VLA: A 3D Vision-Language-Action Generative World Model14 Mar

Other references · 31

  1. 2017Neural Discrete Representation Learningcited by 4,650
  2. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,151
  3. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,048
  4. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 2,993
  5. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,730
  6. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,297
  7. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,007
  8. 2025π0.5: a Vision-Language-Action Model with Open-World Generalizationcited by 1,653
  9. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,490
  10. 2024Octo: An Open-Source Generalist Robot Policycited by 1,427
  11. 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learningcited by 1,338
  12. 2024Gemma: Open Models Based on Gemini Research and Technologycited by 889
19 more
  1. 2024PaliGemma: A versatile 3B VLM for transfercited by 679
  2. 2023BridgeData V2: A Dataset for Robot Learning at Scalecited by 634
  3. 2024Evaluating Real-World Robot Manipulation Policies in Simulationcited by 484
  4. 2025CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Modelscited by 440
  5. 2025AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systemscited by 390
  6. 2025UniVLA: Learning to Act Anywhere with Task-centric Latent Actionscited by 386
  7. 2024GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulationcited by 290
  8. 2023RVT: Robotic View Transformer for 3D Object Manipulationcited by 224
  9. 2024PaliGemma 2: A Family of Versatile VLMs for Transfercited by 204
  10. 2025DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledgecited by 203
  11. 2025Video Depth Anything: Consistent Depth Estimation for Super-Long Videoscited by 202
  12. 2025ConRFT: A Reinforced Fine-tuning Method for VLA Models via Consistency Policycited by 139
  13. 2023Act3D: 3D Feature Field Transformers for Multi-Task Robotic Manipulationcited by 135
  14. 2024RVT-2: Learning Precise Manipulation from Few Demonstrationscited by 135
  15. 2025ReconVLA: Reconstructive Vision-Language-Action Model as Effective Robot Perceivercited by 80
  16. 2025Long-VLA: Unleashing Long-Horizon Capability of Vision Language Action Model for Robot Manipulationcited by 48
  17. 2025FP3: A 3D Foundation Policy for Robotic Manipulationcited by 31
  18. 2025RoboEnvision: A Long-Horizon Video Generation Model for Multi-Task Robot Manipulationcited by 16
  19. 2025Bridging VLM and KMP: Enabling Fine-grained robotic manipulation via Semantic Keypoints Representationcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 18.

19 papers.

Sort:

By area:

  1. 2025SwiftVLA: Unlocking Spatiotemporal Dynamics for Lightweight VLA Models at Minimal Overheadcited by 23
  2. 2026Any3D-VLA: Enhancing VLA Robustness via Diverse Point Cloudscited by 13
  3. 2026Evo-Depth: A Lightweight Depth-Enhanced Vision-Language-Action Modelcited by 13
  4. 2026LaMP: Learning Vision-Language-Action Policy with 3D Scene Flow as Latent Motion Priorcited by 11
  5. 2026FocusVLA: Focused Visual Utilization for Vision-Language-Action Modelscited by 5
  6. 2026UniLACT: Depth-Aware RGB Latent Action Learning for Vision-Language-Action Modelscited by 3
  7. 2026Look Before Acting: Enhancing Vision Foundation Representations for Vision-Language-Action Modelscited by 3
  8. 2026GaussianDream: A Feed-Forward 3D Gaussian World Model for Robotic Manipulationcited by 3
  9. 2026OASIS: Observation-Action Space Alignment via SE(3) Trajectory Prediction for Robotic Manipulationcited by 3
  10. 2026EvoScene-VLA: Evolving Scene Beliefs Inside the Action Decoder for Chunked Robot Controlcited by 2
  11. 2026GeoAlign: Beyond Semantics with State-Guided Spatial Alignment in VLA Modelscited by 1
  12. 20263DThinkVLA: Endowing Vision-Language-Action Models with Latent 3D Priors via 3D-Thinking-Guided Co-trainingcited by 1
7 more
  1. 2026AnchorVLA4D: an Anchor-Based Spatial-Temporal Vision-Language-Action Model for Robotic Manipulationcited by 0
  2. 2026VistaVLA: Geometry- and Semantic-Aware 3D Gaussian-Grounded VLA for Robotic Manipulationcited by 0
  3. 2026CoTinyVLA: Chain-of-Thought Distillation for a Sub-Billion-Parameter Vision-Language-Action Modelcited by 0
  4. 2026Mind-VLA: Instruction-Aware Spatial Representation Alignment for Vision-Language-Action Modelscited by 0
  5. 2026GaussianDream++: Efficient 3D Gaussian World Modeling for Robotic Manipulationcited by 0
  6. 2026Temporal Forcing: 4D Representation Alignment for Vision-Language-Action Modelscited by 0
  7. 2026GeomVLA: Unifying Scene, Motion, and Action in 3Dcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025DepthVLA: Enhancing Vision-Language-Action Models with Depth-Aware Spatial Reasoning
  2. 2026AugVLA-3D: Depth-Driven Feature Augmentation for Vision-Language-Action Models
  3. 2026Recurrent-Depth VLA: Implicit Test-Time Compute Scaling of Vision-Language-Action Models via Latent Iterative Reasoning
  4. 2026H-VLA: Hierarchical Vision-Language-Action Model with Key-Action Reasoning and Motion Planning in a Unified Action Space
  5. 2026SG-VLA: Learning Spatially-Grounded Vision-Language-Action Models for Mobile Manipulation
  6. 2026FOCAL-VLA: Subtask-Guided Geometry Distillation and Implicit World Modeling for Vision-Language-Action Models
  7. 2026G3VLA: Geometric inductive bias for Vision-Language-Action Models
  8. 2026V-Link: Recovering Lost Visual Representations in Action DiT for Vision-Language-Action Models