mlsanityData to 7 Oct 2026

Vision-Language-Action (VLA) Models: Concepts, Progress, Applications and Challenges

arXiv 2505.04769 ↗First posted 7 May 2025cs.CVcited by 72

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

also in 1 more
Abstract (arXiv)

Vision-Language-Action (VLA) models mark a transformative advancement in artificial intelligence, aiming to unify perception, natural language understanding, and embodied action within a single computational framework. This foundational review presents a comprehensive synthesis of recent advancements in Vision-Language-Action models, systematically organized across five thematic pillars that structure the landscape of this rapidly evolving field. We begin by establishing the conceptual foundations of VLA systems, tracing their evolution from cross-modal learning architectures to generalist agents that tightly integrate vision-language models (VLMs), action planners, and hierarchical controllers. Our methodology adopts a rigorous literature review framework, covering over 80 VLA models published in the past three years. Key progress areas include architectural innovations, efficient training strategies, and real-time inference accelerations. We explore diverse application domains such as autonomous vehicles, medical and industrial robotics, precision agriculture, humanoid robotics, and augmented reality. We analyzed challenges and propose solutions including agentic adaptation and cross-embodiment planning. Furthermore, we outline a forward-looking roadmap where VLA models, VLMs, and agentic AI converge to strengthen socially aligned, adaptive, and general-purpose embodied agents. This work, is expected to serve as a foundational reference for advancing intelligent, real-world robotics and artificial general intelligence. The project repository is available on GitHub as https://github.com/Applied-AI-Research-Lab/Vision-Language-Action-Models-Concepts-Progress-Applications-and-Challenges. [Index Terms: Vision Language Action, VLA, Vision Language Models, VLMs, Action Tokenization, NLP]

Key facts. Cited by 72 papers in the map (data through 7 Oct 2026). Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 135 of its 291 references that are in the map. First posted on arXiv 7 May 2025.

Builds on

135 of 291 references.

Closest ancestors · 16

Same direction, newest first

  1. 2025CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models27 Mar
  2. 2025RoboFlamingo-Plus: Fusion of Depth and RGB Perception with Vision-Language Models for Enhanced Robotic Manipulation25 Mar
  3. 2025JARVIS-VLA: Post-Training Large-Scale Vision Language Models to Play Visual Games with Keyboards and Mouse20 Mar
  4. 2025TLA: Tactile-Language-Action Model for Contact-Rich Manipulation11 Mar
  5. 2025PointVLA: Injecting the 3D World into Vision-Language-Action Models10 Mar
  6. 2025Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success27 Feb
  7. 2025DexVLA: Vision-Language Model with Plug-In Diffusion Expert for General Robot Control9 Feb
  8. 2025RLS3: RL-Based Synthetic Sample Selection to Enhance Spatial Reasoning in Vision-Language Models for Indoor Autonomous Perception31 Jan
  9. 2025UP-VLA: A Unified Understanding and Prediction Model for Embodied Agent31 Jan
  10. 2025Improving Vision-Language-Action Model with Online Reinforcement Learning28 Jan
  11. 2025ECBench: Can Multi-modal Foundation Models Understand the Egocentric World? A Holistic Embodied Cognition Benchmark9 Jan
  12. 2024VLA-3D: A Dataset for 3D Semantic Scene Understanding and Navigation5 Nov
4 more
  1. 2024Robotic Control via Embodied Chain-of-Thought Reasoning11 Jul
  2. 2024SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities22 Jan
  3. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control28 Jul
  4. 2023PaLM-E: An Embodied Multimodal Language Model6 Mar

Other references · 119

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  4. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  5. 2016Densely Connected Convolutional Networkscited by 6,691
  6. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
  7. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,048
  8. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,534
  9. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,297
  10. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,007
  11. 2025π0.5: a Vision-Language-Action Model with Open-World Generalizationcited by 1,653
  12. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,490
38 more
  1. 2024Octo: An Open-Source Generalist Robot Policycited by 1,427
  2. 2024Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Predictioncited by 1,005
  3. 2023VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Modelscited by 733
  4. 2023ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoderscited by 703
  5. 2019Deep Hough Voting for 3D Object Detection in Point Cloudscited by 648
  6. 2025FAST: Efficient Action Tokenization for Vision-Language-Action Modelscited by 643
  7. 2021CLIPort: What and Where Pathways for Robotic Manipulationcited by 617
  8. 2023Language Is Not All You Need: Aligning Perception with Language Modelscited by 543
  9. 2025SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Modelcited by 502
  10. 2014Long-term Recurrent Convolutional Networks for Visual Recognition and Descriptioncited by 483
  11. 2019Res2Net: A New Multi-scale Backbone Architecturecited by 468
  12. 2024CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulationcited by 411
  13. 2015Recent Advances in Convolutional Neural Networkscited by 360
  14. 2021An End-to-End Transformer Model for 3D Object Detectioncited by 329
  15. 20243D-VLA: A 3D Vision-Language-Action Generative World Modelcited by 320
  16. 2023Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Actioncited by 301
  17. 2023UniSim: A Neural Closed-Loop Sensor Simulatorcited by 294
  18. 2024A Survey on Vision-Language-Action Models for Embodied AIcited by 274
  19. 2019RoboNet: Large-Scale Multi-Robot Learningcited by 268
  20. 2021Bridge Data: Boosting Generalization of Robotic Skills with Cross-Domain Datasetscited by 248
  21. 2025Hi Robot: Open-Ended Instruction Following with Hierarchical Vision-Language-Action Modelscited by 216
  22. 2016Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learningcited by 209
  23. 2024RT-H: Action Hierarchies Using Languagecited by 204
  24. 2024NaVILA: Legged Robot Vision-Language-Action Model for Navigationcited by 201
  25. 2025ORION: A Holistic End-to-End Autonomous Driving Framework by Vision-Language Instructed Action Generationcited by 177
  26. 2025Multimodal Chain-of-Thought Reasoning: A Comprehensive Surveycited by 176
  27. 2024An Introduction to Vision-Language Modelingcited by 175
  28. 2025OpenDriveVLA: Towards End-to-end Autonomous Driving with Large Vision Language Action Modelcited by 172
  29. 2024Understanding World or Predicting Future? A Comprehensive Survey of World Modelscited by 161
  30. 2024Precise and Dexterous Robotic Manipulation via Human-in-the-Loop Reinforcement Learningcited by 153
  31. 2025ConRFT: A Reinforced Fine-tuning Method for VLA Models via Consistency Policycited by 139
  32. 2024VisionLLM v2: An End-to-End Generalist Multimodal Large Language Model for Hundreds of Vision-Language Taskscited by 136
  33. 2025HAMSTER: Hierarchical Action Models For Open-World Robot Manipulationcited by 125
  34. 2025GraspVLA: a Grasping Foundation Model Pre-trained on Billion-scale Synthetic Action Datacited by 120
  35. 2025NORA: A Small Open-Sourced Generalist Vision Language Action Model for Embodied Taskscited by 119
  36. 2024AHA: A Vision-Language-Model for Detecting and Reasoning Over Failures in Robotic Manipulationcited by 118
  37. 2025ChatVLA: Unified Multimodal Understanding and Robot Control with Vision-Language-Action Modelcited by 112
  38. 2025Reactive Diffusion Policy: Slow-Fast Visual-Tactile Policy Learning for Contact-Rich Manipulationcited by 103

50 most cited of 119 All 119 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 33; 2026: 39.

72 papers.

Sort:

By area:

  1. 2025A Survey of Reinforcement Learning for Large Reasoning Modelscited by 175
  2. 2025AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challengescited by 167
  3. 2025LIBERO-PRO: Towards Robust and Fair Evaluation of Vision-Language-Action Models Beyond Memorizationcited by 166
  4. 2025SimpleVLA-RL: Scaling VLA Training via Reinforcement Learningcited by 141
  5. 2025Vision-Language-Action Models for Robotics: A Review Towards Real-World Applicationscited by 82
  6. 2025A Survey on Vision-Language-Action Models for Autonomous Drivingcited by 72
  7. 2025A Survey: Learning Embodied Intelligence from Physical Simulators and World Modelscited by 50
  8. 2025How Far are VLMs from Visual Spatial Intelligence? A Benchmark-Driven Perspectivecited by 41
  9. 2025Vision-Language-Action Models for Autonomous Driving: Past, Present, and Futurecited by 32
  10. 2026JEPA-VLA: Video Predictive Embedding is Needed for VLA Modelscited by 22
  11. 2026FASTER: Rethinking Real-Time Flow VLAscited by 20
  12. 2025FreezeVLA: Action-Freezing Attacks against Vision-Language-Action Modelscited by 19
38 more
  1. 2025VLA-RAIL: A Real-Time Asynchronous Inference Linker for VLA Models and Robotscited by 18
  2. 2025Parallels Between VLA Model Post-Training and Human Motor Learning: Progress, Challenges, and Trendscited by 17
  3. 2025DeepThinkVLA: Enhancing Reasoning Capability of Vision-Language-Action Modelscited by 17
  4. 2025AsyncVLA: Asynchronous Flow Matching for Vision-Language-Action Modelscited by 16
  5. 2025Embodied Agents Meet Personalization: Investigating Challenges and Solutions Through the Lens of Memory Utilizationcited by 15
  6. 2025REALM: A Real-to-Sim Validated Benchmark for Generalization in Robotic Manipulationcited by 12
  7. 2026Make Each Token Count: Towards Improving Long-Context Performance with KV Cache Evictioncited by 10
  8. 2025Compose Your Policies! Improving Diffusion-based or Flow-based Robot Policies via Test-time Distribution-level Compositioncited by 8
  9. 2026ProgressVLA: Progress-Guided Diffusion Policy for Vision-Language Robotic Manipulationcited by 8
  10. 2025Generative AI for Autonomous Driving: Frontiers and Opportunitiescited by 7
  11. 2025XRoboToolkit: A Cross-Platform Framework for Robot Teleoperationcited by 7
  12. 2025Survey of Vision-Language-Action Models for Embodied Manipulationcited by 7
  13. 2026Inject Once Survive Later: Backdooring Vision-Language-Action Models to Persist Through Downstream Fine-tuningcited by 7
  14. 2025NEBULA: Do We Evaluate Vision-Language-Action Agents Correctly?cited by 6
  15. 2026ImagineUAV: Aerial Vision-Language Navigation via World-Action Modeling and Kinodynamic Planningcited by 6
  16. 2026Hardware Co-Design Scaling Laws via Roofline Modelling for On-Device LLMscited by 5
  17. 2026VLA-Thinker: Boosting Vision-Language-Action Models through Thinking-with-Image Reasoningcited by 5
  18. 2026Vesta: A Generalist Embodied Reasoning Modelcited by 5
  19. 2025Beyond Human Demonstrations: Diffusion-Based Reinforcement Learning to Generate Data for VLA Trainingcited by 4
  20. 2025SurveyBench: Can LLM(-Agents) Write Academic Surveys that Align with Reader Needs?cited by 4
  21. 2025Robotic Manipulation via Imitation Learning: Taxonomy, Evolution, Benchmark, and Challengescited by 3
  22. 2025Transferring Vision-Language-Action Models to Industry Applications: Architectures, Performance, and Challengescited by 3
  23. 2026Improving Robustness of Vision-Language-Action Models by Restoring Corrupted Visual Inputscited by 3
  24. 2026Towards Human-Like Manipulation through RL-Augmented Teleoperation and Mixture-of-Dexterous-Experts VLAcited by 3
  25. 2026LABSHIELD: A Multimodal Benchmark for Safety-Critical Reasoning and Planning in Scientific Laboratoriescited by 3
  26. 2026Judge, Then Drive: A Critic-Centric Vision Language Action Framework for Autonomous Drivingcited by 3
  27. 2025Language-Conditioned Representations and Mixture-of-Experts Policy for Robust Multi-Task Robotic Manipulationcited by 2
  28. 2025IPR-1: Interactive Physical Reasonercited by 2
  29. 2025E3AD: An Emotion-Aware Vision-Language-Action Model for Human-Centric End-to-End Autonomous Drivingcited by 2
  30. 2026Information-Theoretic Constraints for Continual Vision-Language-Action Alignmentcited by 2
  31. 2026SafeAlign-VLA: A Negative-Enhanced Safe Alignment Framework for Risk-Aware Autonomous Drivingcited by 2
  32. 2026Revisiting Parameter Redundancy in Vision-Language-Action Models: Insights from VLM-to-VLA Adaptationcited by 2
  33. 2025Progressive Bird's Eye View Perception for Safety-Critical Autonomous Driving: A Comprehensive Surveycited by 1
  34. 2025Sigma: The Key for Vision-Language-Action Models toward Telepathic Alignmentcited by 1
  35. 2026Lingua-SafetyBench: A Benchmark for Safety Evaluation of Multilingual Vision-Language Modelscited by 1
  36. 2026Selective Perception for Robot: Task-Aware Attention in Multimodal VLAcited by 1
  37. 2026MALLVI: A Multi-Agent Framework for Integrated Generalized Robotics Manipulationcited by 1
  38. 2026PhysiFlow: Physics-Aware Humanoid Whole-Body VLA via Multi-Brain Latent Flow Matching and Robust Trackingcited by 1

50 most cited of 72 All 72 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Pure Vision Language Action (VLA) Models: A Comprehensive Survey
  2. 2025An Anatomy of Vision-Language-Action Models: From Modules to Milestones and Challenges
  3. 202510 Open Challenges Steering the Future of Vision-Language-Action Models
  4. 2025Vision Language Action Models in Robotic Manipulation: A Systematic Review
  5. 2025VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model
  6. 2025Efficient Vision-Language-Action Models for Embodied Manipulation: A Systematic Survey
  7. 2025A Survey on Vision-Language-Action Models: An Action Tokenization Perspective
  8. 2026Rethinking the Practicality of Vision-language-action Model: A Comprehensive Benchmark and An Improved Baseline