Update README.md

README.md

@@ -8,4 +8,16 @@ datasets:
 - Xkev/LLaVA-CoT-100k
 pipeline_tag: image-text-to-text
 library_name: transformers
----
+---
+
+# Sherlock: Self-Correcting Reasoning in Vision-Language Models
+
+## Introduction
+
+**Sherlock is a training framework focus on improving Vision-Language Models reasoning and self-correction capabilities.** 
+
+GitHub repo: [https://github.com/DripNowhy/Sherlock](https://github.com/DripNowhy/Sherlock)
+
+Project Page: [https://dripnowhy.github.io/Sherlock/](https://dripnowhy.github.io/Sherlock/) 
+
+arXiv: [https://arxiv.org/abs/2505.22651](https://arxiv.org/abs/2505.22651)