zhouhongyi commited on
Commit
ec3cb26
·
1 Parent(s): 790eb33

update the bibtex for neurips

Browse files
Files changed (1) hide show
  1. README.md +10 -11
README.md CHANGED
@@ -65,10 +65,10 @@ For integration with continuous generative models:
65
 
66
  ```python
67
  # Encode to normalized continuous parameters [-1, 1]
68
- params = tokenizer.encode_continuous(trajectories, update_bounds=True)
69
 
70
  # Decode back
71
- reconstructed = tokenizer.decode_continuous(params)
72
  ```
73
 
74
  ## Parameters
@@ -82,9 +82,7 @@ reconstructed = tokenizer.decode_continuous(params)
82
  | `degree_p` | B-spline polynomial degree. Higher degrees produce smoother curves (3=cubic, 4=quartic) | 4 |
83
  | `device` | Torch device (`"cuda"` or `"cpu"`) | `"cuda"` |
84
  | `gripper_zero_order` | Use piecewise-constant (degree 0) splines for gripper DOFs. Useful for binary gripper states | `False` |
85
- | `gripper_dof` | Number of gripper DOFs. Only used when `gripper_zero_order=True` | 1 |
86
- | `init_cond_order` | Initial boundary condition order: 0=none, 1=position only, 2=position+velocity | 0 |
87
- | `end_cond_order` | End boundary condition order (same options as `init_cond_order`) | 0 |
88
  | `enforce_init_pos` | Enforce initial position constraint during decoding | `False` |
89
 
90
  ### Token Count
@@ -144,11 +142,12 @@ If you use BEAST in your research, please cite:
144
  **BibTeX:**
145
 
146
  ```bibtex
147
- @article{zhou2025beast,
148
- title={BEAST: Efficient Tokenization of B-Splines Encoded Action Sequences for Imitation Learning},
149
- author={Zhou, Hongyi and Liao, Weiran and Huang, Xi and Tang, Yucheng and Otto, Fabian and Jia, Xiaogang and Jiang, Xinkai and Hilber, Simon and Li, Ge and Wang, Qian and others},
150
- journal={arXiv preprint arXiv:2506.06072},
151
- year={2025}
 
 
152
  }
153
-
154
  ```
 
65
 
66
  ```python
67
  # Encode to normalized continuous parameters [-1, 1]
68
+ params = beast.encode_continuous(trajectories, update_bounds=True)
69
 
70
  # Decode back
71
+ reconstructed = beast.decode_continuous(params)
72
  ```
73
 
74
  ## Parameters
 
82
  | `degree_p` | B-spline polynomial degree. Higher degrees produce smoother curves (3=cubic, 4=quartic) | 4 |
83
  | `device` | Torch device (`"cuda"` or `"cpu"`) | `"cuda"` |
84
  | `gripper_zero_order` | Use piecewise-constant (degree 0) splines for gripper DOFs. Useful for binary gripper states | `False` |
85
+ | `gripper_dof` | Number of gripper DOFs, assumed to be in the end. Only used when `gripper_zero_order=True` | 1 |
 
 
86
  | `enforce_init_pos` | Enforce initial position constraint during decoding | `False` |
87
 
88
  ### Token Count
 
142
  **BibTeX:**
143
 
144
  ```bibtex
145
+ @inproceedings{
146
+ zhou2025beast,
147
+ title={{BEAST}: Efficient Tokenization of B-Splines Encoded Action Sequences for Imitation Learning},
148
+ author={Hongyi Zhou and Weiran Liao and Xi Huang and Yucheng Tang and Fabian Otto and Xiaogang Jia and Xinkai Jiang and Simon Hilber and Ge Li and Qian Wang and {\"O}mer Erdin{\c{c}} Ya{\u{g}}murlu and Nils Blank and Moritz Reuss and Rudolf Lioutikov},
149
+ booktitle={The Thirty-ninth Annual Conference on Neural Information Processing Systems},
150
+ year={2025},
151
+ url={https://openreview.net/forum?id=rQCl1sf62w}
152
  }
 
153
  ```