Update README.md

README.md

@@ -26,7 +26,7 @@ We present SPHINX, a versatile multi-modal large language model (MLLM) with a mi
   <img src="figs/pipeline1.png"/ width="100%"> <br>
 </p>
 
-On top of SPHINX, we propose to further mixvisual scales and sub-images for better capture fine-grained semantics on high-resolution images.
+On top of SPHINX, we propose to further mix visual scales and sub-images for better capture fine-grained semantics on high-resolution images.
 <p align="left">                                                                                                                                          
   <img src="figs/pipeline2.png"/ width="100%"> <br>
 </p>