Upload 10 files

README.md

@@ -6,7 +6,7 @@ license: mit
 ---
 
 <div align="center">
-  <img src="./assets/acebrain.png" width=600>
+  <img src="./assets/title.png" width=600>
 </div>
 
 <br/>
@@ -26,7 +26,7 @@ license: mit
 
 ## Overview
 
-**ACE-Brain** is a spatial-centric multimodal foundation model designed to unify perception, reasoning, and decision-making across diverse embodied domains, including **spatial intelligence**, **embodied interaction**, **autonomous driving**, and **low-altitude sensing**. Built upon a unified multimodal large language model (MLLM) architecture, ACE-Brain learns a shared spatial reasoning substrate that enables generalization across heterogeneous physical environments and agent embodiments. 
+**ACE-Brain** is a spatial-centric multimodal foundation model designed to unify perception, reasoning, and decision-making across diverse embodied domains, including **spatial cognition**, **autonomous driving**, **low-altitude sensing** and **embodied interaction**. Built upon a unified multimodal large language model (MLLM) architecture, ACE-Brain learns a shared spatial reasoning substrate that enables generalization across heterogeneous physical environments and agent embodiments. 
 
 Extensive evaluation across **24** benchmarks demonstrates that ACE-Brain achieves state-of-the-art or competitive performance across multiple domains, validating its effectiveness as a unified embodied intelligence model. 
 
@@ -50,7 +50,7 @@ Extensive evaluation across **24** benchmarks demonstrates that ACE-Brain achiev
 
 ## Performance Highlights
 
-ACE-Brain achieves strong performance across **24 benchmarks covering Spatial Intelligence, Embodied Interaction, Autonomous Driving, and Low-Altitude Sensing**, consistently outperforming existing open-source embodied VLMs and remaining competitive with closed-source models.
+ACE-Brain achieves strong performance across **24 benchmarks covering Spatial Cognition, Autonomous Driving, Low-Altitude Sensing and Embodied Interaction**, consistently outperforming existing open-source embodied VLMs and remaining competitive with closed-source models.
 
 The model shows robust capability in **spatial reasoning, physical interaction understanding, task-oriented decision-making, and dynamic scene interpretation**, enabling reliable performance across diverse real-world embodiment scenarios.