Update README.md
Browse files
README.md
CHANGED
|
@@ -26,8 +26,6 @@ license: apache-2.0
|
|
| 26 |
</a>
|
| 27 |
</p>
|
| 28 |
|
| 29 |
-
|
| 30 |
-
|
| 31 |
<div align="center">
|
| 32 |
<span style="font-size: smaller;">
|
| 33 |
Kaihang Pan<sup>1*</sup>, Wendong Bu<sup>1*</sup>, Yuruo Wu<sup>1*</sup>, Yang Wu<sup>2</sup>, Kai Shen<sup>1</sup>, Yunfei Li<sup>2</sup>,
|
|
@@ -52,7 +50,7 @@ Key Contributions:
|
|
| 52 |
2. **FocusDiff Approach**: A method using paired data and reinforcement learning to enhance fine-grained text-image alignment.
|
| 53 |
|
| 54 |
<div style="text-align: center;">
|
| 55 |
-
<img src="https://raw.githubusercontent.com/wendell0218/FocusDiff/refs/heads/main/assets/grpo.png" width="
|
| 56 |
</div>
|
| 57 |
|
| 58 |
3. **SOTA Results**: Our model is evaluated with the top performance on multiple benchmarks including **GenEval**, **T2I-CompBench**, **DPG-Bench**, and our newly proposed **PairComp** benchmark.
|
|
|
|
| 26 |
</a>
|
| 27 |
</p>
|
| 28 |
|
|
|
|
|
|
|
| 29 |
<div align="center">
|
| 30 |
<span style="font-size: smaller;">
|
| 31 |
Kaihang Pan<sup>1*</sup>, Wendong Bu<sup>1*</sup>, Yuruo Wu<sup>1*</sup>, Yang Wu<sup>2</sup>, Kai Shen<sup>1</sup>, Yunfei Li<sup>2</sup>,
|
|
|
|
| 50 |
2. **FocusDiff Approach**: A method using paired data and reinforcement learning to enhance fine-grained text-image alignment.
|
| 51 |
|
| 52 |
<div style="text-align: center;">
|
| 53 |
+
<img src="https://raw.githubusercontent.com/wendell0218/FocusDiff/refs/heads/main/assets/grpo.png" width="100%" />
|
| 54 |
</div>
|
| 55 |
|
| 56 |
3. **SOTA Results**: Our model is evaluated with the top performance on multiple benchmarks including **GenEval**, **T2I-CompBench**, **DPG-Bench**, and our newly proposed **PairComp** benchmark.
|