Upload README.md with huggingface_hub

README.md

@@ -23,7 +23,7 @@ By applying DPO stage using OmniAlign-V-DPO datasets, we can further improve the
 ### Performance
 By integrating OmniAlign-V-DPO datasets in DPO stage, we can further improve the alignment of MLLMs with human preference. Our LLaVANext-OA-32B-DPO even surpasses Qwen2VL-72B on MM-AlignBench.
 
-| Model                         | Win Rate $\uparrow$           | Reward$\uparrow$ | Better+         | Better   | Tie  | Worse   | Worse+  |
+| Model                         | Win Rate         | Reward | Better+         | Better   | Tie  | Worse   | Worse+  |
 |-------------------------------|------------------------------|---------------------------|------------|-----|----|-----|-----|
 | Claude3.5V-Sonnet             | 84.9                         | +51.4                     | 70         | 144 | 12 | 31  | 4   |
 | GPT-4o                        | 81.3                         | +49.0                     | 81         | 124 | 12 | 31  | 4   |