Other
Transformers
Safetensors
PyTorch
English
vision-language-action
humanoid-robotics
telepathy
multimodal
robotics-control
lora
Instructions to use Veltraxor/Sigma with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Veltraxor/Sigma with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Veltraxor/Sigma", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -41,7 +41,7 @@ It adds a semantic “telepathy” path and LoRA adapters that steer continuous
|
|
| 41 |
Sigma keeps the perception and control structure of π0.5, and introduces an additional pathway that:
|
| 42 |
|
| 43 |
- fuses **vision, language, and robot state** into a shared latent sequence,
|
| 44 |
-
- maintains a **semantic state**
|
| 45 |
- converts them into **telepathy factors** that modulate the policy’s action outputs as residual corrections.
|
| 46 |
|
| 47 |
---
|
|
|
|
| 41 |
Sigma keeps the perception and control structure of π0.5, and introduces an additional pathway that:
|
| 42 |
|
| 43 |
- fuses **vision, language, and robot state** into a shared latent sequence,
|
| 44 |
+
- maintains a **semantic state** m_t and an **intent vector** z_intent over time,
|
| 45 |
- converts them into **telepathy factors** that modulate the policy’s action outputs as residual corrections.
|
| 46 |
|
| 47 |
---
|