Update README.md
Browse files
README.md
CHANGED
|
@@ -32,6 +32,28 @@ For further details, please refer to the following resources:
|
|
| 32 |
- 🤗 Dataset Collections: https://huggingface.co/collections/CodeGoat24/unifiedreward-training-data-67c300d4fd5eff00fa7f1ede
|
| 33 |
- 👋 Point of Contact: [Yibin Wang](https://codegoat24.github.io)
|
| 34 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 35 |
|
| 36 |
## 🏁 Compared with Current Reward Models
|
| 37 |
|
|
|
|
| 32 |
- 🤗 Dataset Collections: https://huggingface.co/collections/CodeGoat24/unifiedreward-training-data-67c300d4fd5eff00fa7f1ede
|
| 33 |
- 👋 Point of Contact: [Yibin Wang](https://codegoat24.github.io)
|
| 34 |
|
| 35 |
+
# 🔥 News
|
| 36 |
+
[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)], 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!!
|
| 37 |
+
For image editing reward task, our models support:
|
| 38 |
+
|
| 39 |
+
>1. Pairwise Rank — directly judge which of two edited images is better.
|
| 40 |
+
>
|
| 41 |
+
>2. Pairwise Score — assign a separate score to each image in a pair.
|
| 42 |
+
>
|
| 43 |
+
>3. Pointwise Score — rate a single image on two axes: instruction-following and overall image quality.
|
| 44 |
+
|
| 45 |
+
🚀 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!!
|
| 46 |
+
|
| 47 |
+
[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)].
|
| 48 |
+
This version introduces several new capabilities:
|
| 49 |
+
>
|
| 50 |
+
>1. **Pairwise scoring** for image and video generation assessment on **_Alignment_**, **_Coherence_**, **_Style_** dimensions.
|
| 51 |
+
>
|
| 52 |
+
>2. **Pointwise scoring** for image and video generation assessment on **_Alignment_**, **_Coherence/Physics_**, **_Style_** dimensions.
|
| 53 |
+
>
|
| 54 |
+
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) 😊.
|
| 55 |
+
|
| 56 |
+
|
| 57 |
|
| 58 |
## 🏁 Compared with Current Reward Models
|
| 59 |
|