Scaling by Diversified Experience for Vision-Language-Action Models
Leiyu Wang, Zhaofengnian Wang, Xueqi Li, Luoyi Fan, Cewu Lu, Nanyang Ye
Abstract
Vision-Language-Action models face significant challenges in real-world deployment due to the entanglement of high-level reasoning with low-level control, and the instability of policy optimization. In this paper, we introduce SyVLA, a robust VLA model trained with diversified experiences. We propose an Intention Decoupling algorithm to isolate control-relevant features from reasoning contexts and a similar-sample guided RL pipeline to stabilize policy updates and mitigate distribution shift. Extensive experiments on real-world robotic tasks and multi-modal benchmarks demonstrate that SyVLA achieves superior task success rates and stronger out-of-distribution generalization compared to existing methods, while effectively preserving core vision-language capabilities.
BibTeX
@inproceedings{
wang2026scaling,
title={Scaling by Diversified Experience for Vision-Language-Action Models},
author={Leiyu Wang and Zhaofengnian Wang and Xueqi Li and Luoyi Fan and Cewu Lu and Nanyang Ye},
booktitle={Forty-third International Conference on Machine Learning},
year={2026},
url={https://openreview.net/forum?id=diM2jCKgZW}
}