---
title: Xiaomi-Robotics-1-RoboCasa
canonical_url: "https://www.modelscope.ai/models/XiaomiRobotics/Xiaomi-Robotics-1-RoboCasa"
md_url: "https://www.modelscope.ai/models/XiaomiRobotics/Xiaomi-Robotics-1-RoboCasa.md"
repository: XiaomiRobotics/Xiaomi-Robotics-1-RoboCasa
last_updated: 2026-08-15
license: apache-2.0
model_type:
  - mibot
architectures:
  - MiBoTForActionGeneration
parameters: 5.1B
tensor_type:
  - BF16
library_name:
  - pytorch
  - transformer
  - safetensors
frameworks:
  - pytorch
downloads: 140
stars: 0
tags:
  - robotics
  - vision-language-action
  - robocasa
  - qwen3-vl
  - custom_code
---

# Xiaomi-Robotics-1-RoboCasa

> Xiaomi-Robotics-1-RoboCasa - An open-source model by XiaomiRobotics on ModelScope. Xiaomi-Robotics-1-RoboCasa

XiaomiRobotics/Xiaomi-Robotics-1-RoboCasa is a 5.1B-parameter machine learning model on ModelScope. licensed under apache-2.0.

- **Repository**: XiaomiRobotics/Xiaomi-Robotics-1-RoboCasa
- **License**: apache-2.0
- **Parameters**: 5.1B
- **Tags**: robotics, vision-language-action, robocasa, qwen3-vl, custom_code
- **Downloads**: 140
- **Stars**: 0
- **Last updated**: 2026-08-15

Source: https://www.modelscope.ai/models/XiaomiRobotics/Xiaomi-Robotics-1-RoboCasa

---

# Xiaomi-Robotics-1-RoboCasa

This repository contains the Hugging Face checkpoint used by
Xiaomi-Robotics-1 for RoboCasa evaluation. It includes the model weights,
custom Transformers model and processor code, tokenizer files, and
RoboCasa action normalization statistics.

## Requirements

The reference environment uses:

```text
Python 3.11
PyTorch 2.8.0
Transformers 4.57.1
FlashAttention 2
```

The custom model and processor must be loaded with `trust_remote_code=True`.

## Loading

```python
import torch
from transformers import AutoModel, AutoProcessor

model_id = "XiaomiRobotics/Xiaomi-Robotics-1-RoboCasa"

processor = AutoProcessor.from_pretrained(
    model_id,
    trust_remote_code=True,
    use_fast=False,
)
model = AutoModel.from_pretrained(
    model_id,
    trust_remote_code=True,
    attn_implementation="flash_attention_2",
    dtype=torch.bfloat16,
).cuda()
```

For reproducible multi-GPU evaluation, use the standard eight-server launcher in
the companion source repository.

## RoboCasa Evaluation

Use the companion Xiaomi-Robotics-1 source repository and follow
`eval_robocasa/README.md`. The server launcher accepts either this Hugging
Face repository ID after downloading it locally or a local snapshot path.

Reference configuration:

```text
tasks: 24
episodes per task: 100
crop ratio: 0.95
```

Reference result:

| Metric | Value |
| --- | ---: |
| Episodes | 2400 |
| Successes | 1781 |
| Episode success rate | 74.21% |

## License

Apache License 2.0. See `LICENSE`.

## Citation

```bibtex
@article{team2026xiaomi,
  title={Xiaomi-Robotics-1: Scaling Vision-Language-Action Models with over 100K Hours of Real-World Trajectories},
  author={Team, Xiaomi Robotics and Guo, Jun and Jin, Piaopiao and Li, Jason and Li, Peiyan and Li, Yingyan and Liu, Futeng and Peng, Wanli and Qin, Optimus and Su, Yifei and others},
  journal={arXiv preprint arXiv:2607.15330},
  year={2026}
}
```