mlsanityData to 14 Oct 2026

SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics

arXiv 2506.01844 ↗First posted 2 Jun 2025cs.LG cs.ROcited by 530

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

also in 1 more
Abstract (arXiv)

Vision-language models (VLMs) pretrained on large-scale multimodal datasets encode rich visual and linguistic knowledge, making them a strong foundation for robotics. Rather than training robotic policies from scratch, recent approaches adapt VLMs into vision-language-action (VLA) models that enable natural language-driven perception and control. However, existing VLAs are typically massive--often with billions of parameters--leading to high training costs and limited real-world deployability. Moreover, they rely on academic and industrial datasets, overlooking the growing availability of community-collected data from affordable robotic platforms. In this work, we present SmolVLA, a small, efficient, and community-driven VLA that drastically reduces both training and inference costs, while retaining competitive performance. SmolVLA is designed to be trained on a single GPU and deployed on consumer-grade GPUs or even CPUs. To further improve responsiveness, we introduce an asynchronous inference stack decoupling perception and action prediction from action execution, allowing higher control rates with chunked action generation. Despite its compact size, SmolVLA achieves performance comparable to VLAs that are 10x larger. We evaluate SmolVLA on a range of both simulated as well as real-world robotic benchmarks and release all code, pretrained models, and training data.

Key facts. Cited by 530 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 75 of its 85 references that are in the map. First posted on arXiv 2 Jun 2025.

Builds on

75 of 85 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025DexVLA: Vision-Language Model with Plug-In Diffusion Expert for General Robot Control9 Feb
  2. 2023Vision-Language Foundation Models as Effective Robot Imitators2 Nov
  3. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control28 Jul

Other references · 72

  1. 2017Attention Is All You Needcited by 60,361
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2020Language Models are Few-Shot Learnerscited by 32,419
  4. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  5. 2023GPT-4 Technical Reportcited by 18,396
  6. 2024The Llama 3 Herd of Modelscited by 14,715
  7. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,137
  8. 2022Flow Matching for Generative Modelingcited by 5,702
  9. 2023Improved Baselines with Visual Instruction Tuningcited by 4,418
  10. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,386
  11. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,234
  12. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,181
38 more
  1. 2023Mistral 7Bcited by 3,164
  2. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,109
  3. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,887
  4. 2023InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuningcited by 2,876
  5. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,838
  6. 2023MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Modelscited by 2,711
  7. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,407
  8. 2024Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scalingcited by 1,599
  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. 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learningcited by 1,410
  12. 2025GR00T N1: An Open Foundation Model for Generalist Humanoid Robotscited by 1,225
  13. 2019Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learningcited by 1,204
  14. 2024MiniCPM-V: A GPT-4V Level MLLM on Your Phonecited by 1,079
  15. 2024Chameleon: Mixed-Modal Early-Fusion Foundation Modelscited by 927
  16. 2024DROID: A Large-Scale In-The-Wild Robot Manipulation Datasetcited by 852
  17. 2024Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMscited by 838
  18. 2022PaLI: A Jointly-Scaled Multilingual Language-Image Modelcited by 766
  19. 2022OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Frameworkcited by 745
  20. 2024PaliGemma: A versatile 3B VLM for transfercited by 696
  21. 2023VILA: On Pre-training for Visual Language Modelscited by 692
  22. 2025FAST: Efficient Action Tokenization for Vision-Language-Action Modelscited by 665
  23. 2021Multimodal Few-Shot Learning with Frozen Language Modelscited by 661
  24. 2022AudioLM: a Language Modeling Approach to Audio Generationcited by 616
  25. 2024Moshi: a speech-text foundation model for real-time dialoguecited by 568
  26. 2023Language Is Not All You Need: Aligning Perception with Language Modelscited by 543
  27. 2025VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understandingcited by 518
  28. 2022Temporal Difference Learning for Model Predictive Controlcited by 397
  29. 2023An Embodied Generalist Agent in 3D Worldcited by 365
  30. 2024TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulationcited by 339
  31. 2025SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Modelcited by 335
  32. 2024What matters when building vision-language models?cited by 326
  33. 2025Perception Encoder: The best visual embeddings are not at the output of the networkcited by 326
  34. 2023OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documentscited by 316
  35. 2023SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Modelscited by 286
  36. 2022Rectified Flow: A Marginal Preserving Approach to Optimal Transportcited by 283
  37. 2021Bridge Data: Boosting Generalization of Robotic Skills with Cross-Domain Datasetscited by 250
  38. 2025SmolVLM: Redefining small and efficient multimodal modelscited by 237

50 most cited of 72 All 72 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 108; 2026: 422.

530 papers.

Sort:

By area:

  1. 2026Fast-WAM: Do World Action Models Need Test-time Future Imagination?cited by 349
  2. 2026Causal World Modeling for Robot Controlcited by 321
  3. 2025X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Modelcited by 303
  4. 2025DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledgecited by 213
  5. 2025LIBERO-PRO: Towards Robust and Fair Evaluation of Vision-Language-Action Models Beyond Memorizationcited by 179
  6. 2025VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Modelcited by 145
  7. 2025GR-3 Technical Reportcited by 111
  8. 2025Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policiescited by 90
  9. 2025Vision-Language-Action Models for Robotics: A Review Towards Real-World Applicationscited by 84
  10. 2025InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policycited by 84
  11. 2026RoboCasa365: A Large-Scale Simulation Framework for Training and Benchmarking Generalist Robotscited by 79
  12. 2025RynnVLA-002: A Unified Vision-Language-Action and World Modelcited by 74
38 more
  1. 2025Large VLM-based Vision-Language-Action Models for Robotic Manipulation: A Surveycited by 69
  2. 2025VL-JEPA: Joint Embedding Predictive Architecture for Vision-languagecited by 68
  3. 2026Being-H0.5: Scaling Human-Centric Robot Learning for Cross-Embodiment Generalizationcited by 66
  4. 2025Training-Time Action Conditioning for Efficient Real-Time Chunkingcited by 64
  5. 2025Embodied AI Agents: Modeling the Worldcited by 61
  6. 2025VLASH: Real-Time VLAs via Future-State-Aware Asynchronous Inferencecited by 58
  7. 2026MolmoAct2: Action Reasoning Models for Real-world Deploymentcited by 50
  8. 2025TGRPO :Fine-tuning Vision-Language-Action Model via Trajectory-wise Group Relative Policy Optimizationcited by 49
  9. 2025Pure Vision Language Action (VLA) Models: A Comprehensive Surveycited by 49
  10. 2025VLA-0: Building State-of-the-Art VLAs with Zero Modificationcited by 49
  11. 2025Leave No Observation Behind: Real-time Correction for VLA Action Chunkscited by 46
  12. 2025GR-RL: Going Dexterous and Precise for Long-Horizon Robotic Manipulationcited by 45
  13. 2025BitVLA: 1-bit Vision-Language-Action Models for Robotics Manipulationcited by 43
  14. 2025Evo-1: Lightweight Vision-Language-Action Model with Preserved Semantic Alignmentcited by 41
  15. 2026RoboDojo: A Unified Sim-and-Real Benchmark for Comprehensive Evaluation of Generalist Robot Manipulation Policiescited by 40
  16. 2025Vision Language Action Models in Robotic Manipulation: A Systematic Reviewcited by 38
  17. 2025OmniVTLA: Vision-Tactile-Language-Action Models with Semantic-Aligned Tactile Sensingcited by 38
  18. 2025OmniVLA: An Omni-Modal Vision-Language-Action Model for Robot Navigationcited by 38
  19. 2025The Better You Learn, The Smarter You Prune: Towards Efficient Vision-language-action Models via Differentiable Token Pruningcited by 36
  20. 2025Dual-Stream Diffusion for World-Model Augmented Vision-Language-Action Modelcited by 36
  21. 2025ContextVLA: Vision-Language-Action Model with Amortized Multi-Frame Contextcited by 35
  22. 2025Action-aware Dynamic Pruning for Efficient Vision-Language-Action Manipulationcited by 34
  23. 2025A Survey on Efficient Vision-Language-Action Modelscited by 34
  24. 2025VLSA: Vision-Language-Action Models with Plug-and-Play Safety Constraint Layercited by 34
  25. 2026DynamicVLA: A Vision-Language-Action Model for Dynamic Object Manipulationcited by 34
  26. 2026ACoT-VLA: Action Chain-of-Thought for Vision-Language-Action Modelscited by 33
  27. 2025EO-1: An Open Unified Embodied Foundation Model for General Robot Controlcited by 31
  28. 2025VLA-Arena: An Open-Source Framework for Benchmarking Vision-Language-Action Modelscited by 31
  29. 2026CLAP: Contrastive Latent Action Pretraining for Learning Vision-Language-Action Models from Human Videoscited by 31
  30. 2026Interactive World Simulator for Robot Policy Training and Evaluationcited by 31
  31. 2025Real-to-Sim Robot Policy Evaluation with Gaussian Splatting Simulation of Soft-Body Interactionscited by 30
  32. 2026QuantVLA: Scale-Calibrated Post-Training Quantization for Vision-Language-Action Modelscited by 30
  33. 2026QVLA: Not All Channels Are Equal in Vision-Language-Action Model's Quantizationcited by 28
  34. 2026Adaptive Action Chunking at Inference-time for Vision-Language-Action Modelscited by 28
  35. 2026OA-WAM: Object-Addressable World Action Model for Robust Robot Manipulationcited by 28
  36. 2025SRPO: Self-Referential Policy Optimization for Vision-Language-Action Modelscited by 27
  37. 2025Efficient Vision-Language-Action Models for Embodied Manipulation: A Systematic Surveycited by 26
  38. 2025SwiftVLA: Unlocking Spatiotemporal Dynamics for Lightweight VLA Models at Minimal Overheadcited by 26

50 most cited of 530 All 530 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025GigaBrain-0: A World Model-Powered Vision-Language-Action Model
  2. 2026CoRE-VLA: Towards Scalable and Robust Vision-Language-Action Modeling via Conditional Routing of Experts
  3. 2026ElegantVLA: Learning When to Think for Efficient Vision-Language-Action Models
  4. 2026StarVLA-α: Reducing Complexity in Vision-Language-Action Systems
  5. 2026StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing
  6. 2025EdgeVLA: Efficient Vision-Language-Action Models
  7. 2025Vision-Language-Action (VLA) Models: Concepts, Progress, Applications and Challenges
  8. 2025VITA-VLA: Efficiently Teaching Vision-Language Models to Act via Action Expert Distillation