README.md

---
license: cc-by-nc-sa-4.0
base_model:
- InternRobotics/InternVLA-A1-3B
tags:
- robotics
- vision-language-action-model
datasets:
- hxma/RoboTwin-LeRobot-v3.0
---

# InternVLA-A1: Unifying Understanding, Generation and Action for Robotic Manipulation

<div style="display: flex; justify-content: center; align-items: center; margin: 10px 0;">
    <img src="https://huggingface.co/spaces/Jia-Zeng/InternVLA_A1_Media/resolve/main/teaser_internvla-a1.jpg" alt="Teaser Image" style="max-width: 100%; border-radius: 10px; box-shadow: 0 4px 8px rgba(0, 0, 0, 0.1);">
</div>

[![Paper](https://img.shields.io/badge/Paper-arXiv-red.svg)](https://arxiv.org/pdf/2601.02456)
[![Code](https://img.shields.io/badge/GitHub-Code-800820?logo=github)](https://github.com/InternRobotics/InternVLA-A1)
[![Data](https://img.shields.io/badge/Data-HuggingFace-blue?logo=huggingface)](https://huggingface.co/datasets/InternRobotics/InternData-A1)
[![Website](https://img.shields.io/badge/Website-Pages-blue.svg)](https://internrobotics.github.io/internvla-a1.github.io/)


<strong>InternVLA-A1</strong>  integrates understanding, generation, and action experts via a Mixture-of-Transformers (MoT) framework, which synergizes MLLMs' semantic reasoning with world-model-style dynamics prediction to guide action execution.

Building upon InternVL3 and Qwen3-VL, we instantiate InternVLA-A1 at 2B and 3B parameter scales. Covering different model scales and pre-training data configurations, we release the InternVLA-A1 series:

- [x]  [InternVLA-A1-3B](https://huggingface.co/InternRobotics/InternVLA-A1-3B): pretrained on the large-scale, high-fidelity simulation data [InternData-A1](https://huggingface.co/datasets/InternRobotics/InternData-A1), together with open-source robot data (e.g. Agibot-World)
- [x]  [InternVLA-A1-3B-RoboTwin](https://huggingface.co/InternRobotics/InternVLA-A1-3B-RoboTwin): finetuned on RoboTwin 2.0 benchmark
- [ ] [InternVLA-A1-3B-Pretrain-InternData-A1](https://huggingface.co/InternRobotics/InternVLA-A1-3B-Pretrain-InternData-A1): pretrained on InternData-A1 only
- [ ] [InternVLA-A1-2B-Pretrain-InternData-A1](https://huggingface.co/InternRobotics/InternVLA-A1-2B-Pretrain-InternData-A1): pretrained on InternData-A1 only

## **Evaluation on RoboTwin 2.0 Simulation Benchmark**

**Setting:** All models are jointly fine-tuned across 50 tasks (50 clean + 500 randomized demos each).

**Performance Summary:** InternVLA-A1-3B achieves the highest success rates across both Easy and Hard settings on the RoboTwin 2.0 Benchmark (averaged over 50 tasks).

| Metric | pi0 | pi0.5 | **InternVLA-A1-3B** |
| :--- | :---: | :---: | :---: |
| Avg. Success (Easy) | 79.98% | 86.76% | **88.30%** |
| Avg. Success (Hard) | 79.50% | 86.96% | **88.48%** |

## 🔑 Key Features

<div style="display: flex; justify-content: center; align-items: center; margin: 10px 0;">
    <img src="https://huggingface.co/spaces/Jia-Zeng/InternVLA_A1_Media/resolve/main/method_InternVLA-A1.png" alt="Teaser Image" style="max-width: 100%; border-radius: 10px; box-shadow: 0 4px 8px rgba(0, 0, 0, 0.1);">
</div>

- 🔮 *The Core: Synergizes MLLM's semantic understanding with world-model-style dynamic prediction, enabling it to "imagine" the future and guide adaptive actions.*
- 🚀 *The Fuel: Enables joint training on heterogeneous data sources over real-world robot data, synthetic simulation data, and egocentric human videos.*
- ⚡ *The Output: Tackles highly dynamic scenarios with effortless mastery.*

## Usage
Please refer to our official repo [InternVLA-A1](https://github.com/InternRobotics/InternVLA-A1).

## Demonstrations
**InternVLA-A1** exhibits consistent robustness across static manipulation, dynamic manipulation, and simulation benchmarks, especially demonstrating remarkable superiority in dynamic scenarios.

<div align="center">

### ⚡ Dynamic Manipulation Tasks

<div style="display: flex; flex-direction: column; align-items: center; gap: 5px;">
    <!-- First Row -->
    <div style="display: flex; justify-content: center; align-items: center; gap: 5px;">
        <video controls autoplay loop muted width="200" style="border-radius: 5px; box-shadow: 0 2px 4px rgba(0, 0, 0, 0.1);">
            <source src="https://huggingface.co/spaces/Jia-Zeng/InternVLA_A1_Media/resolve/main/express_sorting_complete.mp4" type="video/mp4">
        </video>
        <video controls autoplay loop muted width="200" style="border-radius: 5px; box-shadow: 0 2px 4px rgba(0, 0, 0, 0.1);">
            <source src="https://huggingface.co/spaces/Jia-Zeng/InternVLA_A1_Media/resolve/main/In-motion_Ingredient_Picking_4x.mp4" type="video/mp4">
        </video>
        <video controls autoplay loop muted width="200" style="border-radius: 5px; box-shadow: 0 2px 4px rgba(0, 0, 0, 0.1);">
            <source src="https://huggingface.co/spaces/Jia-Zeng/InternVLA_A1_Media/resolve/main/express_sorting_upright_3.mp4" type="video/mp4">
        </video>
    </div>
    <!-- Second Row -->
    <div style="display: flex; justify-content: center; align-items: center; gap: 5px;">
        <video controls autoplay loop muted width="200" style="border-radius: 5px; box-shadow: 0 2px 4px rgba(0, 0, 0, 0.1);">
            <source src="https://huggingface.co/spaces/Jia-Zeng/InternVLA_A1_Media/resolve/main/express_sorting_inverted_2.mp4" type="video/mp4">
        </video>
        <video controls autoplay loop muted width="200" style="border-radius: 5px; box-shadow: 0 2px 4px rgba(0, 0, 0, 0.1);">
            <source src="https://huggingface.co/spaces/Jia-Zeng/InternVLA_A1_Media/resolve/main/express_sorting_upright_2.mp4" type="video/mp4">
        </video>
        <video controls autoplay loop muted width="200" style="border-radius: 5px; box-shadow: 0 2px 4px rgba(0, 0, 0, 0.1);">
            <source src="https://huggingface.co/spaces/Jia-Zeng/InternVLA_A1_Media/resolve/main/express_sorting_upright_1.mp4" type="video/mp4">
        </video>
    </div>
    <p><em>InternVLA-A1 exhibits exceptional robustness in highly dynamic scenarios.</em></p>
</div>

### 🤖 Static Manipulation Tasks

<div style="display: flex; flex-direction: column; align-items: center; gap: 5px;">
    <!-- First Row -->
    <div style="display: flex; justify-content: center; align-items: center; gap: 5px;">
        <video controls autoplay loop muted width="200" style="border-radius: 5px; box-shadow: 0 2px 4px rgba(0, 0, 0, 0.1);">
            <source src="https://huggingface.co/spaces/Jia-Zeng/InternVLA_A1_Media/resolve/main/zig_bag_4x.mp4" type="video/mp4">
        </video>
        <video controls autoplay loop muted width="200" style="border-radius: 5px; box-shadow: 0 2px 4px rgba(0, 0, 0, 0.1);">
            <source src="https://huggingface.co/spaces/Jia-Zeng/InternVLA_A1_Media/resolve/main/sort_parts_4x.mp4" type="video/mp4">
        </video>
        <video controls autoplay loop muted width="200" style="border-radius: 5px; box-shadow: 0 2px 4px rgba(0, 0, 0, 0.1);">
            <source src="https://huggingface.co/spaces/Jia-Zeng/InternVLA_A1_Media/resolve/main/unscrew_cap_4x.mp4" type="video/mp4">
        </video>
    </div>
    <!-- Second Row -->
    <div style="display: flex; justify-content: center; align-items: center; gap: 5px;">
        <video controls autoplay loop muted width="200" style="border-radius: 5px; box-shadow: 0 2px 4px rgba(0, 0, 0, 0.1);">
            <source src="https://huggingface.co/spaces/Jia-Zeng/InternVLA_A1_Media/resolve/main/wipe_stain_4x.mp4" type="video/mp4">
        </video>
        <video controls autoplay loop muted width="200" style="border-radius: 5px; box-shadow: 0 2px 4px rgba(0, 0, 0, 0.1);">
            <source src="https://huggingface.co/spaces/Jia-Zeng/InternVLA_A1_Media/resolve/main/place_flower_4x.mp4" type="video/mp4">
        </video>
        <video controls autoplay loop muted width="200" style="border-radius: 5px; box-shadow: 0 2px 4px rgba(0, 0, 0, 0.1);">
            <source src="https://huggingface.co/spaces/Jia-Zeng/InternVLA_A1_Media/resolve/main/sweep_trash_4x.mp4" type="video/mp4">
        </video>
    </div>
    <p><em>InternVLA-A1 demonstrates superior proficiency in dexterous and fine-grained manipulation.</em></p>
</div>

</div>



## License and Citation
All the code within this repo are under [CC BY-NC-SA 4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/). Please consider citing our project if it helps your research.

```BibTeX
@article{internvla_a1,
  title={InternVLA-A1: Unifying Understanding, Generation and Action for Robotic Manipulation},
  author={Cai, Junhao and Cai, Zetao and Cao, Jiafei and Chen, Yilun and He, Zeyu and Jiang, Lei and Li, Hang and Li, Hengjie and Li, Yang and Liu, Yufei and others},
  journal={arXiv preprint arXiv:2601.02456},
  year={2026}
}
```

## Acknowledgments

- [Lerobot](https://github.com/huggingface/lerobot)
- [openpi](https://github.com/Physical-Intelligence/openpi)
- [InternVL](https://github.com/OpenGVLab/InternVL)
- [Qwen3-VL](https://github.com/QwenLM/Qwen3-VL)
- [COSMOS](https://github.com/nvidia-cosmos)