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

By Junjie Wen, Yichen Zhu, Jinming Li, Minjie Zhu, Zhibin Tang, Kun Wu, Zhiyuan Xu, Ning Liu, Ran Cheng, Chaomin Shen and 3 more. IEEE Robotics and Automation Letters, 2024

387 citations recorded by the source corpus.

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 letter, 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 TinyVLA offers an interesting perspective on utilizing pre-trained multimodal models for policy learning.

Subfields: Computer Vision and Pattern Recognition, Control and Systems Engineering

View Paper: https://www.semanticscholar.org/paper/dc62bc6536e9e3ad80242f10f44c046e4c7bd3d1

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Control and Systems Engineering

Citations in the corpus

CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation (2024, neutral): “In recent years, there has been a surge of interest in robotic control models equipped with visual capabilities [7, 8, 15, 30, 34, 45, 48, 58, 60, 62, 67, 69].”
π0: A Vision-Language-Action Flow Model for General Robot Control (2024, neutral): “Our work is most closely related to recently proposed vision-language action (VLA) models, which use pre-trained VLMs that are fine-tuned for robot control [7, 24, 55].”
Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success (2025, positive): “Prior works [51, 26, 3] have shown that vanilla LoRA fine-tuning with autoregressive VLAs [22] is impractical for such tasks, as its throughput (3-5 Hz for single-arm robots and even lower for bimanual tasks) falls well below the 25-50 Hz required for real-time deployment.”
RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation (2025, neutral): “Many task-specific policy architectures [36, 17, 43, 8, 12, 7, 24, 36, 22, 23, 38, 37] achieve strong single-task performance but struggle to transfer across embodiments.”
A Survey on Vision--Language--Action Models for Embodied AI (2024, neutral): “TinyVLA [176] focused on inference speed and data efficiency through smaller VLM and diffusion head for robot action.”
π0.5: a Vision-Language-Action Model with Open-World Generalization (2025, positive): “Vision-language-action models (VLAs) [23, 92, 42, 8, 83, 90, 55, 45, 3, 75, 64, 76, 84, 7, 37] offer an appealing solution: by ﬁne-tuning pre-trained vision-language models for robot control, VLAs can leverage the semantic knowledge acquired from web-scale pretraining and bring it to bear on the…”