Update README.md
Browse files
README.md
CHANGED
|
@@ -140,7 +140,7 @@ OOD Maze Sizes:
|
|
| 140 |
|
| 141 |
## 📊 Performance
|
| 142 |
|
| 143 |
-
Following [Visual Planning: Let's Think Only with Images](https://
|
| 144 |
|
| 145 |
- **Exact Match (EM)** measures whether the model **successfully generates the complete and correct trajectory** that aligns with the shortest optimal valid path.
|
| 146 |
- **Progress Rate (PR)** measures the **number of consecutively correct steps** (valid forward moves) from the start to the number of steps in the optimal path.
|
|
@@ -157,7 +157,7 @@ Following [Visual Planning: Let's Think Only with Images](https://arxiv.org/abs/
|
|
| 157 |
|
| 158 |
### Comparisons
|
| 159 |
|
| 160 |
-
Under the same amount of training data, we include performance metrics reported in [Visual Planning](https://
|
| 161 |
|
| 162 |
| Model | Thinking Modality | Maze EM (%) | Maze PR (%) |
|
| 163 |
| -------------------------------- | ----------------- | ----------- | ----------- |
|
|
|
|
| 140 |
|
| 141 |
## 📊 Performance
|
| 142 |
|
| 143 |
+
Following [Visual Planning: Let's Think Only with Images](https://github.com/yix8/VisualPlanning), we report two metrics:
|
| 144 |
|
| 145 |
- **Exact Match (EM)** measures whether the model **successfully generates the complete and correct trajectory** that aligns with the shortest optimal valid path.
|
| 146 |
- **Progress Rate (PR)** measures the **number of consecutively correct steps** (valid forward moves) from the start to the number of steps in the optimal path.
|
|
|
|
| 157 |
|
| 158 |
### Comparisons
|
| 159 |
|
| 160 |
+
Under the same amount of training data, we include performance metrics reported in [Visual Planning](https://github.com/yix8/VisualPlanning) for reference and comparison.
|
| 161 |
|
| 162 |
| Model | Thinking Modality | Maze EM (%) | Maze PR (%) |
|
| 163 |
| -------------------------------- | ----------------- | ----------- | ----------- |
|