Update README.md

README.md

@@ -67,9 +67,6 @@ MOSS-VL utilizes Cross-attention Rotary Position Embedding (XRoPE), tailored to
     <img src="assets/3d-rope.png" alt="MOSS-VL mRoPE Architecture Illustration" width="80%"/>
 </p>
 
-## 📊 Model Performance
-
-This release focuses on providing a strong pretrained foundation rather than a fully instruction-tuned evaluation snapshot. Public benchmark tables and detailed metrics for the base checkpoint will be released in future updates.
 
 ## 🚀 Quickstart
 ### 🛠️ Requirements
@@ -274,13 +271,6 @@ texts = [item["text"] for item in result["results"]]
 
 </details>
 
-## 🎯 Intended Use
-
-- offline image understanding
-- offline video understanding
-- multimodal prompt experiments for release validation
-- checkpoint-level inference integration and debugging
-
 ## 🚧 Limitations and Future Work
 
 MOSS-VL-Base-0408 is a pretrained base checkpoint, and we are actively improving several core capabilities for future iterations:
@@ -295,7 +285,7 @@ MOSS-VL-Base-0408 is a pretrained base checkpoint, and we are actively improving
 ## 📜 Citation
 ```bibtex
 @misc{moss_vl_2026,
-  title         = {{MOSS-VL Technical Report}},
+  title         = {MOSS-VL Technical Report},
   author        = {OpenMOSS Team},
   year          = {2026},
   howpublished  = {\url{https://github.com/fnlp-vision/MOSS-VL}},