DreamVLA: A Vision-Language-Action Model
Dreamed with Comprehensive World Knowledge

NeurIPS 2025

⭐ If our project helps you, please give us a star on GitHub to support us!

The difference from previous works

Overall framework of DreamVLA

Clone this repo

git clone https://github.com/Zhangwenyao1/DreamVLA

This repository's code is based on the Seer.

Running on the Benchmark

CALVIN ABC-D

• Installation

• Running Code

• CALVIN Result

  Method	1	2	3	4	5	Avg. Len. ↑
  Roboflamingo [30]	82.4	61.9	46.6	33.1	23.1	2.47
  Susie [118]	87.0	69.0	49.0	38.0	26.0	2.69
  GR-1 [14]	85.4	71.2	59.6	49.7	40.1	3.06
  3D Diffusor Actor [93]	92.2	78.7	63.9	51.2	41.3	3.27
  OpenVLA [1]	91.3	77.8	62.0	52.1	43.5	3.27
  RoboDual [119]	94.4	82.7	72.1	62.4	54.4	3.66
  UNIVLA [120]	95.5	85.8	75.4	66.9	56.5	3.80
  Pi0 [32]	93.8	85.0	76.7	68.1	59.9	3.84
  CLOVER [121]	96.0	83.5	70.8	57.5	45.4	3.53
  UP-VLA [57]	92.8	86.5	81.5	76.9	69.9	4.08
  Robovlm [37]	98.0	93.6	85.4	77.8	70.4	4.25
  Seer [56]	96.3	91.6	86.1	80.3	74.0	4.28
  VPP [49]	95.7	91.2	86.3	81.0	75.0	4.29
  DreamVLA (Ours)	98.2	94.6	89.5	83.4	78.1	4.44

LIBERO

• Installation
• Running Code
• LIBERO Result

  Methods	LIBERO-Spatial	LIBERO-OBJECT	LIBERO-GOAL	LIBERO-LONG	Average
  Diffusion Policy [72]	78.3	92.5	68.3	50.5	72.4
  Octo [9]	78.9	85.7	84.6	51.1	75.1
  OpenVLA [1]	84.7	88.4	79.2	53.7	76.5
  SpatialVLA [31]	88.2	89.9	78.6	55.5	78.1
  DreamVLA (Ours)	97.5	94.0	89.5	89.5	92.6

TODO

• Release the code with LIBERO

Acknowledgement

We would like to express our deepest gratitude to Yang Tian for the technique support!!!

Citation

If you find our ideas / environments helpful, please cite our work at

article{dreamvla25,
          author = {Wenyao Zhang and
                    Hongsi Liu and
                    Zekun Qi and
                    Yunan Wang and
                    Xinqiang Yu and
                    Jiazhao Zhang and
                    Runpei Dong and
                    Jiawei He and
                    He Wang and
                    Zhizheng Zhang and
                    Li Yi and 
                    Wenjun Zeng and
                    Xin Jin},
          title        = {DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge},
          journal      = {CoRR},
          volume       = {abs/2507.04447},
          year         = {2025},
          url          = {https://doi.org/10.48550/arXiv.2507.04447},
          doi          = {10.48550/ARXIV.2507.04447},
          eprinttype    = {arXiv},
          eprint       = {2507.04447}
        }