Upload moss-video-preview-base

README.md

@@ -41,7 +41,7 @@ This repo contains the **pretrained weights** that are intended to serve as the
   <img src="assets/model_structure.png" width="90%" alt="Model Architecture"/>
 </p>
 
-- **Native Isomorphic Design**: Unlike traditional projection-based models, this architecture provides native, unified support for both image and video streams, ensuring seamless temporal consistency and visual-language decoupling.
+- **Native Unified Design**: Unlike traditional projection-based models, this architecture provides native, unified support for both image and video streams, ensuring seamless temporal consistency and visual-language decoupling.
 - **Cross-Modal Projector**: Powered by the proprietary `VideoMllamaTextCrossAttention` mechanism, it achieves high-efficiency semantic alignment between temporal visual features and linguistic context.
 - **Unified Spatio-Temporal Encoding**: Aligns video frame sequences with text tokens, providing a robust backbone for long-context multimodal reasoning.