Upload 9 files

.gitattributes

@@ -34,3 +34,10 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
+assets/fig2.png filter=lfs diff=lfs merge=lfs -text
+assets/radarchart.png filter=lfs diff=lfs merge=lfs -text
+assets/table1.png filter=lfs diff=lfs merge=lfs -text
+assets/table2.png filter=lfs diff=lfs merge=lfs -text
+assets/table3.png filter=lfs diff=lfs merge=lfs -text
+assets/table4.png filter=lfs diff=lfs merge=lfs -text
+assets/teaser.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,113 @@
----
-license: apache-2.0
----
+---
+base_model:
+- ACE-Brain/ACE-Brain-8B
+library_name: transformers
+license: mit
+---
+
+<div align="center">
+  <img src="./assets/acebrain.png" width=600>
+</div>
+
+<br/>
+
+<div align="center" style="line-height: 1;">
+  |
+  <a href="https://huggingface.co/ACE-Brain/ACE-Brain-8B" target="_blank">🤗 HuggingFace</a>
+  &nbsp;|
+  <a href="|https://ace-brain.github.io/" target="_blank"> 📁 Project Page</a>
+  &nbsp;|
+  <a href="" target="_blank">📔 Technical Report</a>
+  &nbsp;|
+  <a href="https://github.com/ACE-BRAIN/ACE-Brain" target="_blank"> 🤖 Github</a>
+  &nbsp;|
+  <br/>
+</div>
+
+## 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. 
+
+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. 
+
+
+<div align="center">
+  <img src="./assets/teaser.png" width=800>
+</div>
+
+
+## Key Features
+
+
+- Unified multimodal foundation model for embodied intelligence  
+- Strong spatial reasoning as a universal intelligence scaffold  
+- Supports diverse embodiment platforms:
+  - Spatial Intelligence
+  - Autonomous Driving
+  - UAV and Aerial Perception
+  - Embodied Interaction
+- Cross-domain generalization across perception, reasoning, and planning  
+- Evaluated on 24 real-world embodied intelligence benchmarks  
+
+## Core Capabilities
+
+<div align="center">
+  <img src="./assets/fig2.png" width=800>
+</div>
+
+## Performance Highlights
+
+<div align="center">
+  <img src="./assets/radarchart.png" width=800>
+</div>
+
+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.
+
+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.
+
+In driving and aerial domains, ACE-Brain demonstrates excellent performance in **environment understanding, motion reasoning, and planning-aware prediction**, highlighting its effectiveness in complex, large-scale, and safety-critical environments.
+
+Despite its domain specialization, ACE-Brain maintains strong general multimodal reasoning ability, confirming that spatial-centric training enhances overall visual-language intelligence rather than limiting generalization.
+
+### Spatial Benchmarks
+
+<div align="center">
+  <img src="./assets/table1.png" width=800>
+</div>
+
+
+###  Autonomous Driving Benchmarks
+
+<div align="center">
+  <img src="./assets/table2.png" width=800>
+</div>
+
+
+### Low-Altitude Benchmarks
+
+<div align="center">
+  <img src="./assets/table3.png" width=800>
+</div>
+
+
+###  Embodied Benchmarks
+
+<div align="center">
+  <img src="./assets/table4.png" width=800>
+</div>
+
+
+
+> **Bold** numbers indicate the best results, <u>underlined</u> numbers indicate the second-best results, and results marked with \* are obtained using our evaluation framework.
+
+
+## Citation
+
+```bibtex
+@article{gong2026acebrain,
+  title={ACE-Brain: A Spatial-Centric Foundation Brain for Universal Embodiments},
+  author={Gong, Ziyang and Luo, Zehang and Tang, Anke and Liu, Zhe and others},
+  journal={arXiv preprint arXiv:2502.xxxxx},
+  year={2026}
+}
+```