Update README.md
Browse files
README.md
CHANGED
|
@@ -20,6 +20,7 @@ Welcome to VideoReward, a VLM-based reward model introduced in our paper [Improv
|
|
| 20 |
|
| 21 |
This versatile reward model can be used for data filtering, guidance, reject sampling, DPO, and other RL methods.
|
| 22 |
|
|
|
|
| 23 |
|
| 24 |
## Usage
|
| 25 |
|
|
|
|
| 20 |
|
| 21 |
This versatile reward model can be used for data filtering, guidance, reject sampling, DPO, and other RL methods.
|
| 22 |
|
| 23 |
+
<img src=https://gongyeliu.github.io/videoalign/pics/overview.png width="100%"/>
|
| 24 |
|
| 25 |
## Usage
|
| 26 |
|