|
Download README.md from Amazon-FAR/dreamfar: direct link, hf CLI and curl.
- Browser
- Download file 2.49 kB
-
https://huggingface.co/Amazon-FAR/dreamfar/resolve/main/README.md
- Command line
-
hf download hf://Amazon-FAR/dreamfar/README.md
-
curl -L -o README.md https://huggingface.co/Amazon-FAR/dreamfar/resolve/main/README.md
2.49 kB
| license: cc-by-nc-4.0 | |
| tags: | |
| - robotics | |
| - world-model | |
| - video-prediction | |
| - robot-learning | |
| library_name: pytorch | |
| # DreamFAR: Real-Time and Long-Horizon Interaction with Diverse Objects | |
| Checkpoints and sample scenes for **DreamFAR**, an action-conditioned world model for bimanual robot manipulation | |
| whose dynamics are trained from scratch on robot-native teleoperation data. | |
| * Paper: https://arxiv.org/abs/2611.22001 | |
| * Code: https://github.com/amazon-far/dreamfar | |
| * Project page: https://amazon-far.github.io/dreamfar/ | |
| | file | what | size | | |
| |---|---|---| | |
| | `tok256_step000200000.ckpt` | image tokenizer: a 256×256 image → 16×16×16 unit-sphere latent (weights only) | 386 MB | | |
| | `dreamfar_v9_step000054000.ckpt` | dynamics model, the paper's checkpoint (EMA weights, bf16; inference only) | 4.4 GB | | |
| | `spec_ee_joint_normalizer.pt` | action/state normalizer (also baked into the dynamics checkpoint) | 9 KB | | |
| | `yam.urdf` | YAM bimanual station kinematics (the XDOF YAM station model), used for the end-effector actions | 14 KB | | |
| | `scenes/` | 10 held-out sample start scenes to seed the model (see `scenes/README_scenes.md`) | 136 MB | | |
| ```bash | |
| hf download Amazon-FAR/dreamfar --local-dir dreamfar_assets | |
| (cd dreamfar_assets && sha256sum -c SHA256SUMS && cd scenes && sha256sum -c SHA256SUMS) | |
| ``` | |
| Usage (rollout, interactive demo, training): see the code repository's README. The checkpoints are PyTorch pickles | |
| loaded by the release code (`torch.load(..., weights_only=False)`); only load files from this repository. | |
| ## License | |
| * **Weights and sample scenes (this repository): [CC BY-NC 4.0](https://creativecommons.org/licenses/by-nc/4.0/).** | |
| The tokenizer was initialized from the [facebook/SSDD](https://github.com/facebookresearch/SSDD) `F16C16_M_256` | |
| weights (CC BY-NC 4.0); the sample scenes come from the XDOF teleoperation data. | |
| * **Code: Apache-2.0**, at [github.com/amazon-far/dreamfar](https://github.com/amazon-far/dreamfar). The release code | |
| depends on the SSDD package, which is CC BY-NC 4.0 and not included there. | |
| * `yam.urdf` is the XDOF YAM station model, provided for the end-effector kinematics. | |
| ## Citation | |
| ```bibtex | |
| @article{dreamfar2026, | |
| title = {DreamFAR: Real-Time and Long-Horizon Interaction with Diverse Objects}, | |
| author = {Dou, Yiming and He, Botao and Loquercio, Antonio and Owens, Andrew and Malik, Jitendra and Sontakke, Sumedh Anand and Liu, Ruoshi}, | |
| journal = {arXiv preprint arXiv:2611.22001}, | |
| year = {2026} | |
| } | |
| ``` | |