teaser GIFs side by side

README.md

@@ -14,8 +14,7 @@ tags:
 Predictable Semantic Tokens for Efficient Autoregressive Video Generation
 
 <p align="center">
-  <img src="./assets/GenerationUCO3D_Basketball.gif" width="49%" alt="Text-to-video on uCO3D at token budgets k=4 to 256">
-  <img src="./assets/GenerationK600_Yoga.gif" width="49%" alt="Class-to-video on Kinetics-600 at token budgets k=4 to 256">
+  <img src="./assets/GenerationUCO3D_Basketball.gif" width="48%" alt="Text-to-video on uCO3D at token budgets k=4 to 256"><img src="./assets/GenerationK600_Yoga.gif" width="48%" alt="Class-to-video on Kinetics-600 at token budgets k=4 to 256">
 </p>
 
 SemanTok is a flexible (coarse-to-fine) video tokenizer whose first tokens carry the clip's semantics.