mlsanityData to 7 Oct 2026

TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulation

arXiv 2409.12514 ↗First posted 19 Sep 2024cs.RO cs.CVcited by 331

On the map: Vision-language-action models → Generalist VLA models and benchmarks

Abstract (arXiv)

Vision-Language-Action (VLA) models have shown remarkable potential in visuomotor control and instruction comprehension through end-to-end learning processes. However, current VLA models face significant challenges: they are slow during inference and require extensive pre-training on large amounts of robotic data, making real-world deployment difficult. In this paper, we introduce a new family of compact vision-language-action models, called TinyVLA, which offers two key advantages over existing VLA models: (1) faster inference speeds, and (2) improved data efficiency, eliminating the need for pre-training stage. Our framework incorporates two essential components to build TinyVLA: (1) initializing the policy backbone with robust, high-speed multimodal models, and (2) integrating a diffusion policy decoder during fine-tuning to enable precise robot actions. We conducted extensive evaluations of TinyVLA in both simulation and on real robots, demonstrating that our approach significantly outperforms the state-of-the-art VLA model, OpenVLA, in terms of speed and data efficiency, while delivering comparable or superior performance. Additionally, TinyVLA exhibits strong generalization capabilities across various dimensions, including language instructions, novel objects, unseen positions, changes in object appearance, background variations, and environmental shifts, often matching or exceeding the performance of OpenVLA. We believe that methodname offers an interesting perspective on utilizing pre-trained multimodal models for policy learning. Our project is at https://tiny-vla.github.io.

Key facts. Cited by 331 papers in the map (data through 7 Oct 2026). Placed in Generalist VLA models and benchmarks, one of 13 directions in Vision-language-action models. Builds on 72 of its 88 references that are in the map. First posted on arXiv 19 Sep 2024.

Builds on

72 of 88 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024LLaRA: Supercharging Robot Learning Data for Vision-Language Policy28 Jun
  2. 2024OpenVLA: An Open-Source Vision-Language-Action Model13 Jun
  3. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control28 Jul

Other references · 69

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  4. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  5. 2023Visual Instruction Tuningcited by 7,792
  6. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,069
  7. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,464
  8. 2023Mistral 7Bcited by 3,065
  9. 2023InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuningcited by 2,855
  10. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,730
  11. 2023MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Modelscited by 2,689
  12. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,302
38 more
  1. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,286
  2. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,007
  3. 2023Pythia: A Suite for Analyzing Large Language Models Across Training and Scalingcited by 1,734
  4. 2024Octo: An Open-Source Generalist Robot Policycited by 1,427
  5. 2019Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learningcited by 1,168
  6. 2021GLM: General Language Model Pretraining with Autoregressive Blank Infillingcited by 1,026
  7. 2023Training Diffusion Models with Reinforcement Learningcited by 939
  8. 2023Open X-Embodiment: Robotic Learning Datasets and RT-X Modelscited by 849
  9. 2023VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Modelscited by 733
  10. 2024PaliGemma: A versatile 3B VLM for transfercited by 679
  11. 2023MiniGPT-v2: large language model as a unified interface for vision-language multi-task learningcited by 617
  12. 2020Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixelscited by 573
  13. 2023Textbooks Are All You Needcited by 561
  14. 2023Otter: A Multi-Modal Model with In-Context Instruction Tuningcited by 548
  15. 2022BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learningcited by 517
  16. 2022Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Taskscited by 420
  17. 2024Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperationcited by 377
  18. 2021Pix2seq: A Language Modeling Framework for Object Detectioncited by 345
  19. 2024Robotic Control via Embodied Chain-of-Thought Reasoningcited by 340
  20. 2024MoE-LLaVA: Mixture of Experts for Large Vision-Language Modelscited by 298
  21. 2023SayPlan: Grounding Large Language Models using 3D Scene Graphs for Scalable Robot Task Planningcited by 289
  22. 2023SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Modelscited by 283
  23. 2023Zero-Shot Robotic Manipulation with Pretrained Image-Editing Diffusion Modelscited by 264
  24. 2023MM-SafetyBench: A Benchmark for Safety Evaluation of Multimodal Large Language Modelscited by 255
  25. 2021Bridge Data: Boosting Generalization of Robotic Skills with Cross-Domain Datasetscited by 248
  26. 2023Affordances from Human Videos as a Versatile Representation for Roboticscited by 221
  27. 2024MobileVLM V2: Faster and Stronger Baseline for Vision Language Modelcited by 172
  28. 2022Masked World Models for Visual Controlcited by 169
  29. 2023RoboAgent: Generalization and Efficiency in Robot Manipulation via Semantic Augmentations and Action Chunkingcited by 167
  30. 2022A Unified Sequence Interface for Vision Taskscited by 152
  31. 2024Multimodal Diffusion Transformer: Learning Versatile Behavior from Multimodal Goalscited by 131
  32. 2024LLaVA-Phi: Efficient Multi-Modal Assistant with Small Language Modelcited by 128
  33. 2024Yell At Your Robot: Improving On-the-Fly from Language Correctionscited by 123
  34. 2024Efficient Multimodal Learning from Data-centric Perspectivecited by 120
  35. 2022A Generalist Framework for Panoptic Segmentation of Images and Videoscited by 99
  36. 2021Reset-Free Reinforcement Learning via Multi-Task Learning: Learning Dexterous Manipulation Behaviors without Human Interventioncited by 90
  37. 2023GOAT: GO to Any Thingcited by 89
  38. 2024LLARVA: Vision-Action Instruction Tuning Enhances Robot Learningcited by 87

50 most cited of 69 All 69 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 13; 2025: 152; 2026: 166.

331 papers.

Sort:

By area:

  1. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,297
  2. 2025π0.5: a Vision-Language-Action Model with Open-World Generalizationcited by 1,653
  3. 2025GR00T N1: An Open Foundation Model for Generalist Humanoid Robotscited by 1,167
  4. 2025Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Successcited by 844
  5. 2025FAST: Efficient Action Tokenization for Vision-Language-Action Modelscited by 643
  6. 2025SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Roboticscited by 507
  7. 2025RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulationcited by 477
  8. 2025CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Modelscited by 440
  9. 2024CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulationcited by 411
  10. 2025WorldVLA: Towards Autoregressive Action World Modelcited by 351
  11. 2025LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Modelscited by 278
  12. 2025Hi Robot: Open-Ended Instruction Following with Hierarchical Vision-Language-Action Modelscited by 216
38 more
  1. 2025DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledgecited by 203
  2. 2025DexVLA: Vision-Language Model with Plug-In Diffusion Expert for General Robot Controlcited by 191
  3. 2025MolmoAct: Action Reasoning Models that can Reason in Spacecited by 189
  4. 2025HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Modelcited by 176
  5. 2024VLABench: A Large-Scale Benchmark for Language-Conditioned Robotics Manipulation with Long-Horizon Reasoning Taskscited by 171
  6. 2024RoboMIND: Benchmark on Multi-embodiment Intelligence Normative Data for Robot Manipulationcited by 166
  7. 2025Knowledge Insulating Vision-Language-Action Models: Train Fast, Run Fast, Generalize Bettercited by 142
  8. 2026π0.7: a Steerable Generalist Robotic Foundation Model with Emergent Capabilitiescited by 127
  9. 2025Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Modelcited by 125
  10. 2025EgoVLA: Learning Vision-Language-Action Models from Egocentric Human Videoscited by 116
  11. 2025ChatVLA: Unified Multimodal Understanding and Robot Control with Vision-Language-Action Modelcited by 112
  12. 2025FLARE: Robot Learning with Implicit World Modelingcited by 105
  13. 2025PointVLA: Injecting the 3D World into Vision-Language-Action Modelscited by 101
  14. 2025Galaxea Open-World Dataset and G0 Dual-System VLA Modelcited by 90
  15. 2025EfficientVLA: Training-Free Acceleration and Compression for Vision-Language-Action Modelscited by 89
  16. 2025PD-VLA: Accelerating Vision-Language-Action Model Integrated with Action Chunking via Parallel Decodingcited by 88
  17. 2025VLA-Cache: Efficient Vision-Language-Action Manipulation via Adaptive Token Cachingcited by 83
  18. 2025Vision-Language-Action Models for Robotics: A Review Towards Real-World Applicationscited by 82
  19. 2025SAFE: Multitask Failure Detection for Vision-Language-Action Modelscited by 74
  20. 2025CogVLA: Cognition-Aligned Vision-Language-Action Model via Instruction-Driven Routing & Sparsificationcited by 70
  21. 2025RynnVLA-002: A Unified Vision-Language-Action and World Modelcited by 70
  22. 2024Exploring the Adversarial Vulnerabilities of Vision-Language-Action Models in Roboticscited by 68
  23. 2025VQ-VLA: Improving Vision-Language-Action Models via Scaling Vector-Quantized Action Tokenizerscited by 67
  24. 2025Large VLM-based Vision-Language-Action Models for Robotic Manipulation: A Surveycited by 66
  25. 2025WorldEval: World Model as Real-World Robot Policies Evaluatorcited by 64
  26. 2025RoboArena: Distributed Real-World Evaluation of Generalist Robot Policiescited by 63
  27. 2025Scalable Vision-Language-Action Model Pretraining for Robotic Manipulation with Real-Life Human Activity Videoscited by 63
  28. 2024Diffusion-VLA: Generalizable and Interpretable Robot Foundation Model via Self-Generated Reasoningcited by 57
  29. 2025FLOWER: Democratizing Generalist Robot Policies with Efficient Vision-Language-Action Flow Policiescited by 56
  30. 2026MEM: Multi-Scale Embodied Memory for Vision Language Action Modelscited by 55
  31. 2025Training Strategies for Efficient Embodied Reasoningcited by 53
  32. 2025Interleave-VLA: Enhancing Robot Manipulation with Interleaved Image-Text Instructionscited by 50
  33. 2025A Survey: Learning Embodied Intelligence from Physical Simulators and World Modelscited by 50
  34. 2025ChatVLA-2: Vision-Language-Action Model with Open-World Embodied Reasoning from Pretrained Knowledgecited by 49
  35. 2025Long-VLA: Unleashing Long-Horizon Capability of Vision Language Action Model for Robot Manipulationcited by 48
  36. 2025TLA: Tactile-Language-Action Model for Contact-Rich Manipulationcited by 46
  37. 2025Pure Vision Language Action (VLA) Models: A Comprehensive Surveycited by 46
  38. 2025BitVLA: 1-bit Vision-Language-Action Models for Robotics Manipulationcited by 42

50 most cited of 331 All 331 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model
  2. 2025Vision Language Action Models in Robotic Manipulation: A Systematic Review
  3. 2026SimVLA: A Simple VLA Baseline for Robotic Manipulation
  4. 2025EdgeVLA: Efficient Vision-Language-Action Models
  5. 2024Benchmarking Vision, Language, & Action Models on Robotic Learning Tasks
  6. 2025VLA-0: Building State-of-the-Art VLAs with Zero Modification
  7. 2026A Pragmatic VLA Foundation Model
  8. 2025dVLA: Diffusion Vision-Language-Action Model with Multimodal Chain-of-Thought