mlsanityData to 14 Oct 2026

Efficient Vision-Language-Action Models for Embodied Manipulation: A Systematic Survey

arXiv 2510.17111 ↗First posted 20 Oct 2025cs.RO cs.LGcited by 26

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 extend vision-language models to embodied control by mapping natural-language instructions and visual observations to robot actions. Despite their capabilities, VLA systems face significant challenges due to their massive computational and memory demands, which conflict with the constraints of edge platforms such as on-board mobile manipulators that require real-time performance. Addressing this tension has become a central focus of recent research. In light of the growing efforts toward more efficient and scalable VLA systems, this survey provides a systematic review of approaches for improving VLA efficiency, with an emphasis on reducing latency, memory footprint, and training and inference costs. We categorize existing solutions into four dimensions: model architecture, perception feature, action generation, and training/inference strategies, summarizing representative techniques within each category. Finally, we discuss future trends and open challenges, highlighting directions for advancing efficient embodied intelligence.

Key facts. Cited by 26 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 83 of its 98 references that are in the map. First posted on arXiv 20 Oct 2025.

Builds on

83 of 98 references.

Closest ancestors · 9

Same direction, newest first

  1. 2025VITA-VLA: Efficiently Teaching Vision-Language Models to Act via Action Expert Distillation10 Oct
  2. 2025SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics2 Jun
  3. 2025CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models27 Mar
  4. 2025MoLe-VLA: Dynamic Layer-skipping Vision Language Action Model via Mixture-of-Layers for Efficient Robot Manipulation26 Mar
  5. 2025Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success27 Feb
  6. 2024DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot Execution4 Nov
  7. 2024HiRT: Enhancing Robotic Control with Hierarchical Robot Transformers12 Sep
  8. 2024Robotic Control via Embodied Chain-of-Thought Reasoning11 Jul
  9. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control28 Jul

Other references · 74

  1. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  3. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  4. 2023Visual Instruction Tuningcited by 7,869
  5. 2020Scaling Laws for Neural Language Modelscited by 6,586
  6. 2022Scalable Diffusion Models with Transformerscited by 6,054
  7. 2022Flow Matching for Generative Modelingcited by 5,702
  8. 2018GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understandingcited by 4,899
  9. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,718
  10. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,386
  11. 2017Deep reinforcement learning from human preferencescited by 3,912
  12. 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenesscited by 3,673
38 more
  1. 2023Qwen Technical Reportcited by 3,344
  2. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,887
  3. 2023InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuningcited by 2,876
  4. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,838
  5. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,407
  6. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,061
  7. 2023Pythia: A Suite for Analyzing Large Language Models Across Training and Scalingcited by 1,786
  8. 2022Fast Inference from Transformers via Speculative Decodingcited by 1,653
  9. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,568
  10. 2024Octo: An Open-Source Generalist Robot Policycited by 1,484
  11. 2025SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Featurescited by 1,188
  12. 2024DROID: A Large-Scale In-The-Wild Robot Manipulation Datasetcited by 852
  13. 2025FAST: Efficient Action Tokenization for Vision-Language-Action Modelscited by 665
  14. 2024An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Modelscited by 642
  15. 2023Learning Universal Policies via Text-Guided Video Generationcited by 522
  16. 2025SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Modelcited by 519
  17. 2019Be Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self Distillationcited by 497
  18. 2023Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulationcited by 364
  19. 2024TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulationcited by 339
  20. 2024GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulationcited by 296
  21. 2024Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representationscited by 289
  22. 20243D Diffuser Actor: Policy Diffusion with 3D Scene Representationscited by 282
  23. 2024A Survey on Vision-Language-Action Models for Embodied AIcited by 279
  24. 2023A Survey on Model Compression for Large Language Modelscited by 269
  25. 2025SmolVLM: Redefining small and efficient multimodal modelscited by 237
  26. 2025Real-Time Execution of Action Chunking Flow Policiescited by 216
  27. 2025DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledgecited by 213
  28. 2025VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interactioncited by 197
  29. 2023BitNet: Scaling 1-bit Transformers for Large Language Modelscited by 189
  30. 2024Behavior Generation with Latent Actionscited by 160
  31. 2025ConRFT: A Reinforced Fine-tuning Method for VLA Models via Consistency Policycited by 154
  32. 2025Unified Vision-Language-Action Modelcited by 134
  33. 2025NORA: A Small Open-Sourced Generalist Vision Language Action Model for Embodied Taskscited by 127
  34. 2023Accelerating Transformer Inference for Translation via Parallel Decodingcited by 124
  35. 2025GR-3 Technical Reportcited by 111
  36. 2025A Survey on Vision-Language-Action Models: An Action Tokenization Perspectivecited by 96
  37. 2025EfficientVLA: Training-Free Acceleration and Compression for Vision-Language-Action Modelscited by 93
  38. 2025PD-VLA: Accelerating Vision-Language-Action Model Integrated with Action Chunking via Parallel Decodingcited by 88

50 most cited of 74 All 74 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 6; 2026: 20.

26 papers.

Sort:

By area:

  1. 2025VLASH: Real-Time VLAs via Future-State-Aware Asynchronous Inferencecited by 58
  2. 2025VLSA: Vision-Language-Action Models with Plug-and-Play Safety Constraint Layercited by 34
  3. 2026Fast-ThinkAct: Efficient Vision-Language-Action Reasoning via Verbalizable Latent Planningcited by 24
  4. 2026FASTER: Rethinking Real-Time Flow VLAscited by 21
  5. 2026Efficient-WAM: A 1B-Parameter World-Action Model with Low-Cost Future Imaginationcited by 18
  6. 2025TS-DP: Reinforcement Speculative Decoding For Temporal Adaptive Diffusion Policy Accelerationcited by 6
  7. 2026VLA-Thinker: Boosting Vision-Language-Action Models through Thinking-with-Image Reasoningcited by 6
  8. 2026StreamingVLA: Streaming Vision-Language-Action Model with Action Flow Matching and Adaptive Early Observationcited by 6
  9. 2025ActDistill: General Action-Guided Self-Derived Distillation for Efficient Vision-Language-Action Modelscited by 5
  10. 2026TIDAL: Temporally Interleaved Diffusion and Action Loop for High-Frequency VLA Controlcited by 5
  11. 2025An Anatomy of Vision-Language-Action Models: From Modules to Milestones and Challengescited by 4
  12. 2025RoboNeuron: A Middle-Layer Infrastructure for Agent-Driven Orchestration in Embodied AIcited by 3
14 more
  1. 2026Jetson-PI: Towards Onboard Real-Time Robot Control via Foresight-Aligned Asynchronous Inferencecited by 3
  2. 2026From Inference Efficiency to Embodied Efficiency: Revisiting Efficiency Metrics for Vision-Language-Action Modelscited by 2
  3. 2026ElegantVLA: Learning When to Think for Efficient Vision-Language-Action Modelscited by 2
  4. 2026Revisiting Parameter Redundancy in Vision-Language-Action Models: Insights from VLM-to-VLA Adaptationcited by 2
  5. 2026PhysReflect-VLA: Physical Feasibility and Self-Reflective Regulation for Reliable Vision-Language-Action Policiescited by 1
  6. 2026Position: Introspective Experience from Conversational Environments as a Path to Better Learningcited by 0
  7. 2026VLAMotor: Test-Guided Enhancement of Vision-Language-Action Models via Agent-BasedData Synthesiscited by 0
  8. 2026Devil in the Lens: Analyzing and Defending Physical Prompt Injection Against Vision-Language Models on Wearable Devicescited by 0
  9. 2026Toward Unified Robot Learning: Bridging Representation, Vision-Language-Action, and World Modelscited by 0
  10. 2026rMuscle: Robotic Muscle Memory for Efficient Vision-Language-Action Model Inferencecited by 0
  11. 2026Catch Me If You Can: Real-Time Feedback Denoising for Responsive VLAscited by 0
  12. 2026Faster and Better? Benchmark Bugs and Design Limitations Distort the Evaluation of Vision-Language-Action Accelerationcited by 0
  13. 2026Beyond LLM Serving: Characterizing Vision-Language-Action Workloads for Embodied AI System Designcited by 0
  14. 2026REACT: Rolling Denoising and Dual Decoupling for Reactive Robot Control with VLA Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Vision Language Action Models in Robotic Manipulation: A Systematic Review
  2. 2025Survey of Vision-Language-Action Models for Embodied Manipulation
  3. 2025A Survey on Efficient Vision-Language-Action Models
  4. 2025Large VLM-based Vision-Language-Action Models for Robotic Manipulation: A Survey
  5. 2026Vision-Language-Action in Robotics: A Survey of Datasets, Benchmarks, and Data Engines
  6. 2025Vision-Language-Action Models for Robotics: A Review Towards Real-World Applications
  7. 2026AC^2-VLA: Action-Context-Aware Adaptive Computation in Vision-Language-Action Models for Efficient Robotic Manipulation
  8. 2025Pure Vision Language Action (VLA) Models: A Comprehensive Survey