Lite VLA: Efficient Vision-Language-Action Control on CPU-Bound Edge Robots

E. J. Hu, Y. Shen, P. Wallis, et al., “LoRA: Low-Rank Adaptation of Large Language Models,” arXiv preprint arXiv:2106.09685

Original

2021

Earlier work this paper cites.

M. Ahn, A. Brohan, N. Brown, et al., “Do As I Can, Not As I Say: Grounding Language in Robotic Affordances,” in Proceedings of the 6th Conference on Robot Learning (CoRL)

2022

Earlier work this paper cites.

A. Brohan, N. Brown, J. Ichter, et al., “RT-1: Robotics Transformer for Real-World Control at Scale,” arXiv preprint arXiv:2212.06817

Original

2022

Earlier work this paper cites.

M. Shridhar, C. Manuelli, and D. Fox, “CLIPort: What and Where Pathways for Robotic Manipulation,” in Proceedings of the Conference on Robot Learning (CoRL)

2022

Earlier work this paper cites.

Y. Jiang, A. Xu, C. Gupta, et al., “VIMA: General Robot Manipulation with Multimodal Prompts,” arXiv preprint arXiv:2210.03094

Original

2022

Earlier work this paper cites.

D. Driess, F. Xia, M. S. Sajjadi, et al., “PaLM-E: An Embodied Multimodal Language Model,” arXiv preprint arXiv:2303.03378

Original

2023

Earlier work this paper cites.

A. Brohan, C. Chebotar, and N. Brown, “RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control,” arXiv preprint arXiv:2307.15818

Original

2023

Earlier work this paper cites.

T. Dettmers, A. Lewis, S. Shen, et al., “QLoRA: Efficient Finetuning of Quantized LLMs,” arXiv preprint arXiv:2305.14314

Original

2023

Earlier work this paper cites.

J. Kim, D. Choi, et al., “OpenVLA: Open-Source Generalist Vision-Language-Action Model for Robotics,” arXiv preprint arXiv:2403.08265

Original

2024

Cited alongside, same era.

Z. Yang, S. Lin, et al., “Octo: Open-Vocabulary Object Manipulation with Pretrained Vision-Language Models,” arXiv preprint arXiv:2404.11012

Original

2024

Cited alongside, same era.

S. Wen, R. Zhao, and A. Fedorov, “TinyVLA: Lightweight Vision-Language-Action Models for Edge Robotics,” arXiv preprint arXiv:2404.19277

Original

2024

Cited alongside, same era.

M. Zhao and H. Wang, “LoRA+: Enhanced Low-Rank Adaptation for Faster Convergence in Fine-Tuning,” arXiv preprint arXiv:2401.03103

Original

2024

Cited alongside, same era.

Q. Chen, N. Gao, S. Huang, J. E. Low, T. Chen, J. Sun, and M. Schwager, “GRaD-Nav++: Vision-Language Model Enabled Visual Drone Navigation with Gaussian Radiance Fields and Differentiable Dynamics,” arXiv preprint arXiv:2506.14009

P. Budzianowski, W. Maa, M. Freed, et al

Original

2025

Closest in time.

J. Li, R. Patel, A. Fedorov, et al

Original

2025

Closest in time.

Q. Chen, N. Gao, and S. Huang, “GRaD-Nav++: Vision-Language Model Enabled Visual Drone Navigation with Gaussian Radiance Fields and Differentiable Dynamics,” arXiv preprint arXiv:2506.14009

Original

2025

Closest in time.

P. Budzianowski, W. Maa, and M. Freed, “EdgeVLA: Efficient Vision-Language-Action Models for Edge Devices,” arXiv preprint arXiv:2507.14049

Original

2025

Closest in time.

A. Marafioti, O. Zohar, and M. Farre, “SmolVLM: Redefining Small and Efficient Multimodal Models,” arXiv preprint arXiv:2504.05299

Original