发表

2026

1. ICML 2026

   Scaling by Diversified Experience for Vision-Language-Action Models

   Leiyu Wang, Zhaofengnian Wang, Xueqi Li, and 3 more authors

   In Proceedings of the 43rd International Conference on Machine Learning, 2026

   To appear

   Abs Bib

   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. Codes and Datasets is released on \hrefhttps://sy-vla.github.io/project page.

   @inproceedings{wang2026scalingdiversifiedexperiencevisionlanguageaction,
     title = {Scaling by Diversified Experience for Vision-Language-Action Models},
     author = {Wang, Leiyu and Wang, Zhaofengnian and Li, Xueqi and Fan, Luoyi and Lu, Cewu and Ye, Nanyang},
     booktitle = {Proceedings of the 43rd International Conference on Machine Learning},
     year = {2026},
     url = {https://arxiv.org/abs/2606.09009},
     note = {To appear}
   }

2024

1. ACL Findings

   What makes a good order of examples in in-context learning

   Qi Guo, Leiyu Wang, Yidong Wang, and 2 more authors

   In Findings of the Association for Computational Linguistics: ACL 2024, 2024

   Abs DOI Bib

   

   Although large language models (LLMs) have demonstrated impressive few-shot learning capabilities via in-context learning (ICL), ICL performance is known to be highly sensitive to the order of examples provided. To identify appropriate orders, recent studies propose heuristic methods to evaluate order performance using a set of unlabeled data. However, the requirement of in-domain data limits their utility in real-world scenarios where additional annotated data is challenging to acquire. Additionally, these dataset-based approaches are prone to being sub-optimal for a lack of consideration for individual differences. To address the problems, we first analyze the properties of performant example orders at both corpus level and instance level. Based on the analysis we propose **DEmO** to adaptively identify performant example order for each instance without extra data. DEmO works by filtering out a subset of orders featuring label fairness, then selecting the most influential order for each test instance. The employment of a content-free metric makes DEmO independent of in-domain data. Extensive experiments indicate the superiority of DEmO over a wide range of strong baselines. Further analysis validates the generalizability across various settings.

   @inproceedings{guo2024makes,
     title = {What makes a good order of examples in in-context learning},
     author = {Guo, Qi and Wang, Leiyu and Wang, Yidong and Ye, Wei and Zhang, Shikun},
     booktitle = {Findings of the Association for Computational Linguistics: ACL 2024},
     pages = {14892--14904},
     year = {2024},
     url = {https://aclanthology.org/2024.findings-acl.884/},
     doi = {10.18653/v1/2024.findings-acl.884},
   }