Update README.md

add method description

README.md

@@ -11,7 +11,7 @@ pipeline_tag: image-to-video
 ---
 
 <p align="center">
-  <img src="assets/logo2.jpeg" alt="MultiTalk" width="240"/>
+  <img src="assets/logo2.jpeg" alt="MultiTalk" width="300"/>
 </p>
 
 # MeiGen-MultiTalk • Audio-Driven Multi-Person Conversational Video Generation
@@ -56,6 +56,11 @@ This repository hosts the model weights for **MultiTalk**. For installation, usa
 
 
 ## Method
+We propose a novel framework, MultiTalk, for audio-driven multi-person conversational video generation. We investigate several schemes for audio injection and introduce
+the Label Rotary Position Embedding (L-RoPE) method. By assigning identical labels to audio embeddings and video latents, it effectively activates specific regions within the audio cross-attention
+map, thereby resolving incorrect binding issues. To localize the region of the specified person, we introduce the adaptive person localization by computing the similarity 
+between the features of the given region of a person in the reference image and all the features of the whole video. 
+
 <p align="left"><img src="assets/pipe.png" width="80%"></p>