conda create -n dreamvla python=3.10
conda activate dreamvla

cp dist_utils.py ./segment-anything/
mv ./data_info/ep_start_end_ids.npy <your_data_path>
mv ./data_process/sam_extractor.py ./segment-anything/
cd segment-anything
python sam_extractor.py

cp dist_utils.py ./dinov2/
mv ./data_process/dino_extractor.py ./dinov2/
cd dinov2
python dino_extractor.py

python ./data_process/merge_sam_dino.py # merge sam and dino feature into new dataset
python ./data_process/merge_track.py # merge optical flow into new dataset

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}
        }