Saved in:
Bibliographic Details
Main Authors: Li, Haoxuan, Yan, Sixu, Li, Yuhan, Wang, Xinggang
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.10322
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917955858595840
author Li, Haoxuan
Yan, Sixu
Li, Yuhan
Wang, Xinggang
author_facet Li, Haoxuan
Yan, Sixu
Li, Yuhan
Wang, Xinggang
contents Vision Language Models (VLMs) pretrained on Internet-scale vision-language data have demonstrated the potential to transfer their knowledge to robotic learning. However, the existing paradigm encounters three critical challenges: (1) expensive inference cost resulting from large-scale model parameters, (2) frequent domain shifts caused by mismatched data modalities, and (3) limited capacity to handle past or future experiences. In this work, we propose LiteVLP, a lightweight, memory-based, and general-purpose vision-language policy generation model. LiteVLP is built upon a pre-trained 1B-parameter VLM and fine-tuned on a tiny-scale and conversation-style robotic dataset. Through extensive experiments, we demonstrate that LiteVLP outperforms state-of-the-art vision-language policy on VIMA-Bench, with minimal training time. Furthermore, LiteVLP exhibits superior inference speed while maintaining exceptional high accuracy. In long-horizon manipulation tasks, LiteVLP also shows remarkable memory ability, outperforming the best-performing baseline model by 18.8%. These results highlight LiteVLP as a promising model to integrating the intelligence of VLMs into robotic learning.
format Preprint
id arxiv_https___arxiv_org_abs_2503_10322
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Towards Fast, Memory-based and Data-Efficient Vision-Language Policy
Li, Haoxuan
Yan, Sixu
Li, Yuhan
Wang, Xinggang
Computer Vision and Pattern Recognition
Vision Language Models (VLMs) pretrained on Internet-scale vision-language data have demonstrated the potential to transfer their knowledge to robotic learning. However, the existing paradigm encounters three critical challenges: (1) expensive inference cost resulting from large-scale model parameters, (2) frequent domain shifts caused by mismatched data modalities, and (3) limited capacity to handle past or future experiences. In this work, we propose LiteVLP, a lightweight, memory-based, and general-purpose vision-language policy generation model. LiteVLP is built upon a pre-trained 1B-parameter VLM and fine-tuned on a tiny-scale and conversation-style robotic dataset. Through extensive experiments, we demonstrate that LiteVLP outperforms state-of-the-art vision-language policy on VIMA-Bench, with minimal training time. Furthermore, LiteVLP exhibits superior inference speed while maintaining exceptional high accuracy. In long-horizon manipulation tasks, LiteVLP also shows remarkable memory ability, outperforming the best-performing baseline model by 18.8%. These results highlight LiteVLP as a promising model to integrating the intelligence of VLMs into robotic learning.
title Towards Fast, Memory-based and Data-Efficient Vision-Language Policy
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.10322