mlsanityData to 14 Oct 2026

Vision-Language-Action Models for Robotics: A Review Towards Real-World Applications

arXiv 2510.07077 ↗First posted 8 Oct 2025cs.RO cs.AI cs.CVcited by 84

On the map: Multimodal LLMs / vision-language models → Embodied and 3D vision-language models

also in 1 more
Abstract (arXiv)

Amid growing efforts to leverage advances in large language models (LLMs) and vision-language models (VLMs) for robotics, Vision-Language-Action (VLA) models have recently gained significant attention. By unifying vision, language, and action data at scale, which have traditionally been studied separately, VLA models aim to learn policies that generalise across diverse tasks, objects, embodiments, and environments. This generalisation capability is expected to enable robots to solve novel downstream tasks with minimal or no additional task-specific data, facilitating more flexible and scalable real-world deployment. Unlike previous surveys that focus narrowly on action representations or high-level model architectures, this work offers a comprehensive, full-stack review, integrating both software and hardware components of VLA systems. In particular, this paper provides a systematic review of VLAs, covering their strategy and architectural transition, architectures and building blocks, modality-specific processing techniques, and learning paradigms. In addition, to support the deployment of VLAs in real-world robotic applications, we also review commonly used robot platforms, data collection strategies, publicly available datasets, data augmentation methods, and evaluation benchmarks. Throughout this comprehensive survey, this paper aims to offer practical guidance for the robotics community in applying VLAs to real-world robotic systems. All references categorized by training approach, evaluation method, modality, and dataset are available in the table on our project website: https://vla-survey.github.io .

Key facts. Cited by 84 papers in the map (data through 14 Oct 2026). Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 372 of its 427 references that are in the map. First posted on arXiv 8 Oct 2025.

Builds on

372 of 427 references.

Closest ancestors · 28

Same direction, newest first

  1. 2025CronusVLA: Towards Efficient and Robust Manipulation via Multi-Frame Vision-Language-Action Modeling24 Jun
  2. 2025BridgeVLA: Input-Output Alignment for Efficient 3D Manipulation Learning with Vision-Language Models9 Jun
  3. 2025SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics2 Jun
  4. 2025Knowledge Insulating Vision-Language-Action Models: Train Fast, Run Fast, Generalize Better29 May
  5. 2025VTLA: Vision-Tactile-Language-Action Model with Preference Learning for Insertion Manipulation14 May
  6. 2025Vision-Language-Action (VLA) Models: Concepts, Progress, Applications and Challenges7 May
  7. 2025CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models27 Mar
  8. 2025MoLe-VLA: Dynamic Layer-skipping Vision Language Action Model via Mixture-of-Layers for Efficient Robot Manipulation26 Mar
  9. 2025TLA: Tactile-Language-Action Model for Contact-Rich Manipulation11 Mar
  10. 2025PointVLA: Injecting the 3D World into Vision-Language-Action Models10 Mar
  11. 2025RoboBrain: A Unified Brain Model for Robotic Manipulation from Abstract to Concrete28 Feb
  12. 2025Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success27 Feb
16 more
  1. 2025DexVLA: Vision-Language Model with Plug-In Diffusion Expert for General Robot Control9 Feb
  2. 2025UP-VLA: A Unified Understanding and Prediction Model for Embodied Agent31 Jan
  3. 2025Integrating LMM Planners and 3D Skill Policies for Generalizable Manipulation30 Jan
  4. 2025Improving Vision-Language-Action Model with Online Reinforcement Learning28 Jan
  5. 2024DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot Execution4 Nov
  6. 2024Robotic Control via Embodied Chain-of-Thought Reasoning11 Jul
  7. 2024LLaRA: Supercharging Robot Learning Data for Vision-Language Policy28 Jun
  8. 2024RoboUniView: Visual-Language Model with Unified View Representation for Robotic Manipulation27 Jun
  9. 2024RoboPoint: A Vision-Language Model for Spatial Affordance Prediction for Robotics15 Jun
  10. 2024Yell At Your Robot: Improving On-the-Fly from Language Corrections19 Mar
  11. 2024Real-World Robot Applications of Foundation Models: A Review8 Feb
  12. 2023Vision-Language Foundation Models as Effective Robot Imitators2 Nov
  13. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control28 Jul
  14. 2023PaLM-E: An Embodied Multimodal Language Model6 Mar
  15. 2023Open-World Object Manipulation using Pre-trained Vision-Language Models2 Mar
  16. 2022Robotic Skill Acquisition via Instruction Augmentation with Vision-Language Models21 Nov

Other references · 344

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  5. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  6. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  7. 2023GPT-4 Technical Reportcited by 18,396
  8. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  9. 2017Proximal Policy Optimization Algorithmscited by 15,215
  10. 2024The Llama 3 Herd of Modelscited by 14,715
  11. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  12. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
38 more
  1. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  2. 2020Denoising Diffusion Implicit Modelscited by 9,781
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  4. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  5. 2023Segment Anythingcited by 8,234
  6. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  7. 2023Visual Instruction Tuningcited by 7,869
  8. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  9. 2017Mask R-CNNcited by 7,277
  10. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  11. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  12. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  13. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,137
  14. 2022Scalable Diffusion Models with Transformerscited by 6,054
  15. 2022Flow Matching for Generative Modelingcited by 5,702
  16. 2025Qwen2.5-VL Technical Reportcited by 5,587
  17. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  18. 2024Qwen2.5 Technical Reportcited by 4,942
  19. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  20. 2017Neural Discrete Representation Learningcited by 4,712
  21. 2024GPT-4o System Cardcited by 4,588
  22. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  23. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,386
  24. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,307
  25. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,152
  26. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 4,057
  27. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,332
  28. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,253
  29. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,109
  30. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,887
  31. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,838
  32. 2022InstructPix2Pix: Learning to Follow Image Editing Instructionscited by 2,611
  33. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,581
  34. 2015VQA: Visual Question Answeringcited by 2,506
  35. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,415
  36. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,407
  37. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,348
  38. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,333

50 most cited of 344 All 344 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 13; 2026: 71.

84 papers.

Sort:

By area:

  1. 2025VLSA: Vision-Language-Action Models with Plug-and-Play Safety Constraint Layercited by 34
  2. 2026QuantVLA: Scale-Calibrated Post-Training Quantization for Vision-Language-Action Modelscited by 30
  3. 2026Observing and Controlling Features in Vision-Language-Action Modelscited by 16
  4. 2025Latent Chain-of-Thought World Modeling for End-to-End Drivingcited by 15
  5. 2026TaF-VLA: Tactile-Force Alignment in Vision-Language-Action Models for Force-aware Manipulationcited by 13
  6. 2025Learning Interactive World Model for Object-Centric Reinforcement Learningcited by 11
  7. 2026CoPE-VideoLM: Leveraging Codec Primitives For Efficient Video Language Modelingcited by 11
  8. 2026Goal2Skill: Long-Horizon Manipulation with Adaptive Planning and Reflectioncited by 11
  9. 2026FRoM-W1: Towards General Humanoid Whole-Body Control with Language Instructionscited by 10
  10. 2025Multistep Quasimetric Learning for Scalable Goal-conditioned Reinforcement Learningcited by 8
  11. 2026VLA Knows Its Limits: Adaptive Execution Horizons for Robot Policiescited by 8
  12. 2026Vision-Language-Action in Robotics: A Survey of Datasets, Benchmarks, and Data Enginescited by 8
38 more
  1. 2025Token Expand-Merge: Training-Free Token Compression for Vision-Language-Action Modelscited by 7
  2. 2026Mean-Flow based One-Step Vision-Language-Actioncited by 7
  3. 2025Bring My Cup! Personalizing Vision-Language-Action Models with Visual Attentive Promptingcited by 6
  4. 2026Gated Relational Alignment via Confidence-based Distillation for Efficient VLMscited by 6
  5. 2026AR-VLA: True Autoregressive Action Expert for Vision-Language-Action Modelscited by 6
  6. 2026NeuroVLA: A Brain-inspired Embodied Intelligence for Fluid and Fast Reflexive Robotics Controlcited by 5
  7. 2026TIDAL: Temporally Interleaved Diffusion and Action Loop for High-Frequency VLA Controlcited by 5
  8. 2026ReconVLA: An Uncertainty-Guided and Failure-Aware Vision-Language-Action Framework for Robotic Controlcited by 5
  9. 2026Using large language models for embodied planning introduces systematic safety riskscited by 5
  10. 2026FLARE: A Failure-Aware Framework for Autonomous Correction and Recovery in Visual-Language Robotic Manipulationcited by 5
  11. 2025An Anatomy of Vision-Language-Action Models: From Modules to Milestones and Challengescited by 4
  12. 2026CF-VLA: Efficient Coarse-to-Fine Action Generation for Vision-Language-Action Policiescited by 4
  13. 20263D Scene Graphs: Open Challenges and Future Directionscited by 4
  14. 2025Language-Conditioned Safe Trajectory Generation for Spacecraft Rendezvouscited by 3
  15. 2026SA-VLA: Spatially-Aware Flow-Matching for Vision-Language-Action Reinforcement Learningcited by 3
  16. 2026Self-Supervised Bootstrapping of Action-Predictive Embodied Reasoningcited by 3
  17. 2026MOTIF: Learning Action Motifs for Few-shot Cross-Embodiment Transfercited by 3
  18. 2026SELF-VLA: A Skill Enhanced Agentic Vision-Language-Action Framework for Contact-Rich Disassemblycited by 3
  19. 2026RoboHarness: A Memory-Augmented Policy Harness for Vision-Language-Action Model Robustness via In-Context Adaptationcited by 3
  20. 2026FSD-VLN: Fast-Slow Dual-System Modeling for Aerial Long-Horizon Vision-Language Navigationcited by 3
  21. 2026From Inference Efficiency to Embodied Efficiency: Revisiting Efficiency Metrics for Vision-Language-Action Modelscited by 2
  22. 2026DyGRO-VLA: Cross-Task Scaling of Vision-Language-Action Models via Dynamic Grouped Residual Optimizationcited by 2
  23. 2026PointAction: 3D Points as Universal Action Representations for Robot Controlcited by 2
  24. 2026Revisiting Parameter Redundancy in Vision-Language-Action Models: Insights from VLM-to-VLA Adaptationcited by 2
  25. 2026LIME: Learning Intent-aware Camera Motion from Egocentric Videocited by 2
  26. 2026Learning Robust Execution in Robotic Manipulation with Agentic Reinforcement Learningcited by 2
  27. 2025ROSBag MCP Server: Analyzing Robot Data with LLMs for Agentic Embodied AI Applicationscited by 1
  28. 2025Sigma: The Key for Vision-Language-Action Models toward Telepathic Alignmentcited by 1
  29. 2025Vision-Language-Action Models for Selective Robotic Disassembly: A Case Study on Critical Component Extraction from Desktopscited by 1
  30. 2026Habilis-β: A Fast-Motion and Long-Lasting On-Device Vision-Language-Action Modelcited by 1
  31. 2026Online Self-Training for Co-Adaptation in Hierarchical Diffusion Policiescited by 1
  32. 2026FlowHijack: A Dynamics-Aware Backdoor Attack on Flow-Matching Vision-Language-Action Modelscited by 1
  33. 2026Intent-aligned Autonomous Spacecraft Guidance via Reasoning Modelscited by 1
  34. 2026NeuroAI and Beyond: Bridging Between Advances in Neuroscience and Artificial Intelligencecited by 1
  35. 2026Position: Embodied AI Requires a Privacy-Utility Trade-offcited by 1
  36. 2026LoopVLA: Learning Sufficiency in Recurrent Refinement for Vision-Language-Action Modelscited by 1
  37. 2026When Absolute State Fails: Evaluating Proprioceptive Encodings for Robust Manipulationcited by 1
  38. 2026Comprehensive AI governance requires addressing non-model gainscited by 1

50 most cited of 84 All 84 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Vision Language Action Models in Robotic Manipulation: A Systematic Review
  2. 2025VLA-0: Building State-of-the-Art VLAs with Zero Modification
  3. 2024What Matters in Building Vision-Language-Action Models for Generalist Robots
  4. 2025A Survey on Efficient Vision-Language-Action Models
  5. 2025Pure Vision Language Action (VLA) Models: A Comprehensive Survey
  6. 2025VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model
  7. 2024Benchmarking Vision, Language, & Action Models on Robotic Learning Tasks
  8. 2025From Intention to Execution: Probing the Generalization Boundaries of Vision-Language-Action Models