---
license: cc-by-nc-4.0
library_name: transformers
pipeline_tag: video-text-to-text
---

# R1-Omni: Explainable Omni-Multimodal Emotion Recognition with Reinforcement Learning

[![ModelScope](https://img.shields.io/badge/ModelScope-R1Omni-blue)](https://modelscope.cn/models/iic/R1-Omni-0.5B)
[![Hugging Face](https://img.shields.io/badge/HuggingFace-R1Omni-yellow)](https://huggingface.co/StarJiaxing/R1-Omni-0.5B)
[![arXiv](https://img.shields.io/badge/arXiv-2503.05379-red)](https://arxiv.org/abs/2503.05379)

This model utilizes Reinforcement Learning with Verifiable Reward (RLVR) to perform omni-multimodal emotion recognition. Built upon the HumanOmni-0.5B model, R1-Omni excels at understanding visual and audio cues for emotion identification, even in out-of-distribution scenarios.

## 📖 Introduction
**R1-Omni** is the first application of Reinforcement Learning with Verifiable Reward (RLVR) to an Omni-multimodal large language model. It focuses on emotion recognition, where visual and audio modalities play crucial roles. Key insights include:

1) **Enhanced Reasoning Capability**: R1-Omni demonstrates superior reasoning abilities, enabling a clearer understanding of how visual and audio information contribute to emotion recognition.
2) **Improved Understanding Capability**: Compared to SFT, RLVR significantly boosts performance on emotion recognition tasks.
3) **Stronger Generalization Capability**: RLVR models exhibit markedly better generalization capabilities, particularly excelling in out-of-distribution scenarios.

## 📦 Model Download
The model is based on the open-source HumanOmni-0.5B model. The following models are available: HumanOmni-0.5B, the cold-start model EMER-SFT, the model MAFW-DFEW-SFT fine-tuned directly on the MAFW and DFEW training sets, and the final model R1-Omni.

<div align="center">

| **Model**              | **HuggingFace**                                                                 | **ModelScope**                                                          |
|------------------------|---------------------------------------------------------------------------------|-------------------------------------------------------------------------|
| `HumanOmni-0.5B`      |  [![HF](https://img.shields.io/badge/🤗-Download-yellow)](https://hf.co/StarJiaxing/HumanOmni-0.5B) | [![MS](https://img.shields.io/badge/ModelScope-Download-blue)](https://modelscope.cn/models/iic/HumanOmni-0.5B) |
| `EMER-SFT`      |  [![HF](https://img.shields.io/badge/🤗-Download-yellow)](https://hf.co/StarJiaxing/EMER-SFT-0.5B)  | [![MS](https://img.shields.io/badge/ModelScope-Download-blue)](https://modelscope.cn/models/iic/EMER-SFT-0.5B)  |
| `MAFW-DFEW-SFT`       | [![HF](https://img.shields.io/badge/🤗-Download-yellow)](https://huggingface.co/StarJiaxing/MAFW-DFEW-0.5B)         | [![MS](https://img.shields.io/badge/ModelScope-Download-blue)](https://modelscope.cn/models/iic/MAFW-DFEW-0.5B)         |
| `R1-Omni`       | [![HF](https://img.shields.io/badge/🤗-Download-yellow)](https://huggingface.co/StarJiaxing/R1-Omni-0.5B)         | [![MS](https://img.shields.io/badge/ModelScope-Download-blue)](https://modelscope.cn/models/iic/R1-Omni-0.5B)         |
</div>

## 🏆 Performance

Below are the performance on emotion recognition datasets. We use symbols to indicate whether the data is **in-distribution (⬤)** or **out-of-distribution (△)**.

| Method                          | DFEW (WAR) ⬤ | DFEW (UAR) ⬤ | MAFW (WAR) ⬤ | MAFW (UAR) ⬤ | RAVDESS (WAR) △ | RAVDESS (UAR) △ |
|----------------------------------|---------------|---------------|---------------|---------------|------------------|------------------|
| HumanOmni-0.5B                   | 22.64         | 19.44         | 20.18         | 13.52         | 7.33             | 9.38             |
| EMER-SFT                         | 38.66       | 35.31         | 38.39         | 28.02         | 29.00            | 27.19            |
| MAFW-DFEW-SFT                    | 60.23         | 44.39         | 50.44         | 30.39         | 29.33            | 30.75            |
| R1-Omni                          | 65.83         | 56.27         | 57.68         | 40.04         | 43.00            | 44.69            |

![image](https://github.com/user-attachments/assets/f0239753-8a70-4e8b-9088-35c420595978)

### Legend
- **⬤**: Indicates **in-distribution data** (DFEW and MAFW).
- **△**: Indicates **out-of-distribution data** (RAVDESS).

## 🛠️ Environment Setup
Our code is built on the R1-V framework. To set up the environment, please follow the installation instructions in the [R1-V repository](https://github.com/Deep-Agent/R1-V/)

## 🔍 Inference
Our inference code is based on the implementation from **HumanOmni**.

## 📚 Citation
If you find our work helpful, feel free to cite us.
```
{zhao2025r1omniexplainableomnimultimodalemotion,
      title={R1-Omni: Explainable Omni-Multimodal Emotion Recognition with Reinforcement Learning}, 
      author={Jiaxing Zhao and Xihan Wei and Liefeng Bo},
      journal={arXiv preprint arXiv:2503.05379},
      year={2025}
}
```