Add project page and link to paper
#1
by
nielsr HF Staff - opened
README.md
CHANGED
|
@@ -2,8 +2,13 @@
|
|
| 2 |
license: mit
|
| 3 |
pipeline_tag: robotics
|
| 4 |
---
|
|
|
|
| 5 |
# Octo Base
|
| 6 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
See https://github.com/octo-models/octo for instructions for using this model.
|
| 8 |
|
| 9 |
Octo Base is trained with a window size of 2, predicting 7-dimensional actions 4 steps into the future using a diffusion policy. The model is a Transformer with 93M parameters (equivalent to a ViT-B). Images are tokenized by preprocessing with a lightweight convolutional encoder, then grouped into 16x16 patches. Language is tokenized by applying the T5 tokenizer, and then applying the T5-Base language encoder.
|
|
|
|
| 2 |
license: mit
|
| 3 |
pipeline_tag: robotics
|
| 4 |
---
|
| 5 |
+
|
| 6 |
# Octo Base
|
| 7 |
|
| 8 |
+
This model is described in [From Intention to Execution: Probing the Generalization Boundaries of Vision-Language-Action Models](https://huggingface.co/papers/2506.09930).
|
| 9 |
+
|
| 10 |
+
Project Page: https://ai4ce.github.io/INT-ACT/
|
| 11 |
+
|
| 12 |
See https://github.com/octo-models/octo for instructions for using this model.
|
| 13 |
|
| 14 |
Octo Base is trained with a window size of 2, predicting 7-dimensional actions 4 steps into the future using a diffusion policy. The model is a Transformer with 93M parameters (equivalent to a ViT-B). Images are tokenized by preprocessing with a lightweight convolutional encoder, then grouped into 16x16 patches. Language is tokenized by applying the T5 tokenizer, and then applying the T5-Base language encoder.
|