README.md

---
license: mit
datasets:
- CodeGoat24/HPD
- CodeGoat24/LiFT-HRA
- CodeGoat24/OIP
- CodeGoat24/EvalMuse
- CodeGoat24/ShareGPTVideo-DPO
- CodeGoat24/VideoFeedback
- CodeGoat24/LLaVA-Critic-113k
- CodeGoat24/VideoDPO
base_model:
- lmms-lab/llava-onevision-qwen2-7b-ov
---


# Unified-Reward-7B
We are actively gathering feedback from the community to improve our models. **We welcome your input and encourage you to stay updated through our repository**!


## Model Summary

`Unified-Reward-7b` is the first unified reward model for multimodal understanding and generation assessment based on [LLaVA-OneVision-7b](https://huggingface.co/lmms-lab/llava-onevision-qwen2-7b-ov), enabling both pairwise ranking and pointwise scoring, which can be employed for vision model preference alignment.

For further details, please refer to the following resources:
- 📰 Paper: https://arxiv.org/pdf/2503.05236
- 🪐 Project Page: https://codegoat24.github.io/UnifiedReward/
- 🤗 Model Collections: https://huggingface.co/collections/CodeGoat24/unifiedreward-models-67c3008148c3a380d15ac63a
- 🤗 Dataset Collections: https://huggingface.co/collections/CodeGoat24/unifiedreward-training-data-67c300d4fd5eff00fa7f1ede
- 👋 Point of Contact: [Yibin Wang](https://codegoat24.github.io)

# 🔥 News
[2025/10/23] 🔥🔥🔥 We release **UnifiedReward-Edit**-[[3b](https://huggingface.co/CodeGoat24/UnifiedReward-Edit-qwen-3b)/[7b](https://huggingface.co/CodeGoat24/UnifiedReward-Edit-qwen-7b)/[32b](https://huggingface.co/CodeGoat24/UnifiedReward-Edit-qwen-32b)/[72b](https://huggingface.co/CodeGoat24/UnifiedReward-Edit-qwen-72b)], a unified reward model for **both Text-to-Image and Image-to-Image generation** trained on approximately 700K unified image generation and editing reward data!!
For image editing reward task, our models support:

>1. Pairwise Rank — directly judge which of two edited images is better.
>
>2. Pairwise Score — assign a separate score to each image in a pair.
>
>3. Pointwise Score — rate a single image on two axes: instruction-following and overall image quality.

🚀 The image editing reward inference code is available at [`UnifiedReward-Edit/`](https://github.com/CodeGoat24/UnifiedReward/tree/main/UnifiedReward-Edit) directory, while T2I inference code is unchanged from previous models. The editing training data is preprocessed from [EditScore](https://huggingface.co/datasets/EditScore/EditScore-Reward-Data) and [EditReward](https://huggingface.co/datasets/TIGER-Lab/EditReward-Data) and will be released soon. We sincerely appreciate all contributors!!


[2025/9/25] 🔥🔥🔥 We release **UnifiedReward-2.0**-qwen-[[3b](https://huggingface.co/CodeGoat24/UnifiedReward-2.0-qwen-3b)/[7b](https://huggingface.co/CodeGoat24/UnifiedReward-2.0-qwen-7b)/[32b](https://huggingface.co/CodeGoat24/UnifiedReward-2.0-qwen-32b)/[72b](https://huggingface.co/CodeGoat24/UnifiedReward-2.0-qwen-72b)].
This version introduces several new capabilities:
>
>1. **Pairwise scoring** for image and video generation assessment on **_Alignment_**, **_Coherence_**, **_Style_** dimensions.
>
>2. **Pointwise scoring** for image and video generation assessment on **_Alignment_**, **_Coherence/Physics_**, **_Style_** dimensions. 
>
The added inference code is available at [`inference_qwen/UnifiedReward-2.0-inference`](https://github.com/CodeGoat24/UnifiedReward/tree/main/inference_qwen/UnifiedReward-2.0-inference) directory. The newly added training data has been released [here](https://huggingface.co/datasets/CodeGoat24/UnifiedReward-2.0-T2X-score-data) 😊.



## 🏁 Compared with Current Reward Models

|  Reward Model | Method| Image Generation | Image Understanding | Video Generation | Video Understanding
| :-----: | :-----: |:-----: |:-----: | :-----: | :-----: |
|  [PickScore](https://github.com/yuvalkirstain/PickScore) |Point | √ |  | ||
|  [HPS](https://github.com/tgxs002/HPSv2) | Point | √ |  |||
|  [ImageReward](https://github.com/THUDM/ImageReward) |  Point| √|  |||
|  [LLaVA-Critic](https://huggingface.co/lmms-lab/llava-critic-7b) | Pair/Point | | √  |||
|  [IXC-2.5-Reward](https://github.com/InternLM/InternLM-XComposer) | Pair/Point | | √  ||√|
|  [VideoScore](https://github.com/TIGER-AI-Lab/VideoScore) | Point |  |  |√ ||
|  [LiFT](https://github.com/CodeGoat24/LiFT) | Point |  |  |√| |
|  [VisionReward](https://github.com/THUDM/VisionReward) | Point |√  | |√||
|  [VideoReward](https://github.com/KwaiVGI/VideoAlign) | Point |  |  |√ ||
|  UnifiedReward (Ours) | Pair/Point | √ | √ |√|√|


### Quick Start
All pair rank and point score inference codes are provided in our [github](https://github.com/CodeGoat24/UnifiedReward).

We take image understanding assessment as example here:
~~~python
# pip install git+https://github.com/LLaVA-VL/LLaVA-NeXT.git
from llava.model.builder import load_pretrained_model
from llava.mm_utils import get_model_name_from_path, process_images, tokenizer_image_token
from llava.constants import IMAGE_TOKEN_INDEX, DEFAULT_IMAGE_TOKEN, DEFAULT_IM_START_TOKEN, DEFAULT_IM_END_TOKEN, IGNORE_INDEX
from llava.conversation import conv_templates, SeparatorStyle

from PIL import Image
import requests
import copy
import torch

import sys
import warnings
import os


warnings.filterwarnings("ignore")
pretrained = "CodeGoat24/UnifiedReward-7b"
model_name = "llava_qwen"
device = "cuda"
device_map = "auto"
tokenizer, model, image_processor, max_length = load_pretrained_model(pretrained, None, model_name, device_map=device_map)  # Add any other thing you want to pass in llava_model_args

model.eval()

url = "https://github.com/LLaVA-VL/blog/blob/main/2024-10-03-llava-critic/static/images/critic_img_seven.png?raw=True"
image = Image.open(requests.get(url, stream=True).raw)
image_tensor = process_images([image], image_processor, model.config)
image_tensor = [_image.to(dtype=torch.float16, device=device) for _image in image_tensor]

conv_template = "qwen_1_5"  # Make sure you use correct chat template for different models

# pairwise ranking
critic_prompt = "Given an image and a corresponding question, please serve as an unbiased and fair judge to evaluate the quality of the answers provided by a Large Multimodal Model (LMM). Determine which answer is better and explain your reasoning with specific details. Your task is provided as follows:\nQuestion: [What this image presents?]\nThe first response: [The image is a black and white sketch of a line that appears to be in the shape of a cross. The line is a simple and straightforward representation of the cross shape, with two straight lines intersecting at a point.]\nThe second response: [This is a handwritten number seven.]\nASSISTANT:\n"

# pointwise scoring
# critic_prompt = "Given an image and a corresponding question, please serve as an unbiased and fair judge to evaluate the quality of answer answers provided by a Large Multimodal Model (LMM). Score the response out of 100 and explain your reasoning with specific details. Your task is provided as follows:\nQuestion: [What this image presents?]\nThe LMM response: [This is a handwritten number seven.]\nASSISTANT:\n "

question = DEFAULT_IMAGE_TOKEN + "\n" + critic_prompt
conv = copy.deepcopy(conv_templates[conv_template])
conv.append_message(conv.roles[0], question)
conv.append_message(conv.roles[1], None)
prompt_question = conv.get_prompt()

input_ids = tokenizer_image_token(prompt_question, tokenizer, IMAGE_TOKEN_INDEX, return_tensors="pt").unsqueeze(0).to(device)
image_sizes = [image.size]


cont = model.generate(
    input_ids,
    images=image_tensor,
    image_sizes=image_sizes,
    do_sample=False,
    temperature=0,
    max_new_tokens=4096,
)
text_outputs = tokenizer.batch_decode(cont, skip_special_tokens=True)
print(text_outputs[0])
~~~


## Citation

```
@article{unifiedreward,
  title={Unified reward model for multimodal understanding and generation},
  author={Wang, Yibin and Zang, Yuhang and Li, Hao and Jin, Cheng and Wang, Jiaqi},
  journal={arXiv preprint arXiv:2503.05236},
  year={2025}
}
```