wendell0218 commited on
Commit
dfb291f
·
verified ·
1 Parent(s): ff5ff92

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -3
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="80%" />
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.