library_name: custom
tags:
- robotics
- diffusion
- mixture-of-experts
- multi-modal
license: mit
datasets:
- CALVIN
languages:
- en
pipeline_tag: robotics
---
# MoDE (Mixture of Denoising Experts) Diffusion Policy
## Model Description
This model implements a Mixture of Diffusion Experts architecture for robotic manipulation, combining transformer-based backbone with noise-only expert routing. For faster inference, we can precache the chosen expert for each timestep to reduce computation time.
The model has been pretrained on a subset of OXE for 300k steps and finetuned for downstream tasks on the CALVIN/LIBERO dataset.
## Model Details
### Architecture
- **Base Architecture**: MoDE with custom Mixture of Experts Transformer
- **Vision Encoder**: ResNet-50 with FiLM conditioning finetuned from ImageNet
- **EMA**: Enabled
- **Action Window Size**: 10
- **Sampling Steps**: 5 (optimal for performance)
- **Sampler Type**: DDIM
### Input/Output Specifications
#### Inputs
- RGB Static Camera: `(B, T, 3, H, W)` tensor
- RGB Gripper Camera: `(B, T, 3, H, W)` tensor
- Language Instructions: Text strings
#### Outputs
- Action Space: `(B, T, 7)` tensor representing delta EEF actions
## Usage
```python
obs = {
"rgb_obs": {
"rgb_static": static_image,
"rgb_gripper": gripper_image
}
}
goal = {"lang_text": "pick up the blue cube"}
action = model.step(obs, goal)
```
## Training Details
### Configuration
- **Optimizer**: AdamW
- **Learning Rate**: {config.optimizer.learning_rate}
- **Weight Decay**: {config.optimizer.transformer_weight_decay}
## License
This model is released under the MIT license.
