[readme] add our work using EasyR1 (#331)

Author: kxfan2002

README.md

@@ -155,7 +155,8 @@ See [baselines.md](assets/baselines.md).
 - **RL-with-Cold-Start**: Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start. [![[code]](https://img.shields.io/github/stars/waltonfuture/RL-with-Cold-Start)](https://github.com/waltonfuture/RL-with-Cold-Start) [![[arxiv]](https://img.shields.io/badge/arxiv-2505.22334-blue)](https://arxiv.org/pdf/2505.22334)
 - **ViGoRL**: Grounded Reinforcement Learning for Visual Reasoning. [![[code]](https://img.shields.io/github/stars/Gabesarch/grounded-rl)](https://github.com/Gabesarch/grounded-rl) [![[arxiv]](https://img.shields.io/badge/arxiv-2505.22334-blue)](https://arxiv.org/abs/2505.23678)
 - **Revisual-R1**: Advancing Multimodal Reasoning: From Optimized Cold Start to Staged Reinforcement Learning. [![[code]](https://img.shields.io/github/stars/CSfufu/Revisual-R1)](https://github.com/CSfufu/Revisual-R1) [![[arxiv]](https://img.shields.io/badge/arxiv-2506.04207-blue)](https://arxiv.org/abs/2506.04207)
-
+- **SophiaVL-R1**: Reinforcing MLLMs Reasoning with Thinking Reward. [![[code]](https://img.shields.io/github/stars/kxfan2002/SophiaVL-R1)](https://github.com/kxfan2002/SophiaVL-R1) [![[arxiv]](https://img.shields.io/badge/arxiv-2505.17018-blue)](https://arxiv.org/abs/2505.17018)
+  
 ## TODO
 
 - Support LoRA (high priority).