Update README.md
Browse files
README.md
CHANGED
|
@@ -28,8 +28,26 @@ For further details, please refer to the following resources:
|
|
| 28 |
- 👋 Point of Contact: [Yibin Wang](https://codegoat24.github.io)
|
| 29 |
|
| 30 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 31 |
### Quick Start
|
|
|
|
| 32 |
|
|
|
|
| 33 |
~~~python
|
| 34 |
# pip install git+https://github.com/LLaVA-VL/LLaVA-NeXT.git
|
| 35 |
from llava.model.builder import load_pretrained_model
|
|
|
|
| 28 |
- 👋 Point of Contact: [Yibin Wang](https://codegoat24.github.io)
|
| 29 |
|
| 30 |
|
| 31 |
+
## 🏁 Compared with Current Reward Models
|
| 32 |
+
|
| 33 |
+
| Reward Model | Method| Image Generation | Image Understanding | Video Generation | Video Understanding
|
| 34 |
+
| :-----: | :-----: |:-----: |:-----: | :-----: | :-----: |
|
| 35 |
+
| [PickScore](https://github.com/yuvalkirstain/PickScore) |Point | √ | | ||
|
| 36 |
+
| [HPS](https://github.com/tgxs002/HPSv2) | Point | √ | |||
|
| 37 |
+
| [ImageReward](https://github.com/THUDM/ImageReward) | Point| √| |||
|
| 38 |
+
| [LLaVA-Critic](https://huggingface.co/lmms-lab/llava-critic-7b) | Pair/Point | | √ |||
|
| 39 |
+
| [IXC-2.5-Reward](https://github.com/InternLM/InternLM-XComposer) | Pair/Point | | √ ||√|
|
| 40 |
+
| [VideoScore](https://github.com/TIGER-AI-Lab/VideoScore) | Point | | |√ ||
|
| 41 |
+
| [LiFT](https://github.com/CodeGoat24/LiFT) | Point | | |√| |
|
| 42 |
+
| [VisionReward](https://github.com/THUDM/VisionReward) | Point |√ | |√||
|
| 43 |
+
| [VideoReward](https://github.com/KwaiVGI/VideoAlign) | Point | | |√ ||
|
| 44 |
+
| UnifiedReward (Ours) | Pair/Point | √ | √ |√|√|
|
| 45 |
+
|
| 46 |
+
|
| 47 |
### Quick Start
|
| 48 |
+
All pair rank and point score inference codes are provided in our [github](https://github.com/CodeGoat24/UnifiedReward).
|
| 49 |
|
| 50 |
+
We take image understanding assessment as example here:
|
| 51 |
~~~python
|
| 52 |
# pip install git+https://github.com/LLaVA-VL/LLaVA-NeXT.git
|
| 53 |
from llava.model.builder import load_pretrained_model
|