ACE-Brain commited on
Commit
8fbcd0a
·
verified ·
1 Parent(s): f57184f

update readme

Browse files
README.md CHANGED
@@ -26,7 +26,7 @@ license: mit
26
 
27
  ## Overview
28
 
29
- **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.
30
 
31
  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.
32
 
@@ -45,8 +45,7 @@ Extensive evaluation across **24** benchmarks demonstrates that ACE-Brain achiev
45
  - Autonomous Driving
46
  - Low-Altitude Sensing
47
  - Embodied Interaction
48
- - Cross-domain generalization across perception, reasoning, and planning
49
- - Evaluated on 24 real-world embodied intelligence benchmarks
50
 
51
  ## Performance Highlights
52
 
 
26
 
27
  ## Overview
28
 
29
+ **ACE-Brain-0** is a generalist 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.
30
 
31
  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.
32
 
 
45
  - Autonomous Driving
46
  - Low-Altitude Sensing
47
  - Embodied Interaction
48
+ - Cross-domain generalization across perception, reasoning, and planning
 
49
 
50
  ## Performance Highlights
51
 
assets/table1.png CHANGED

Git LFS Details

  • SHA256: c0e18e854d410594ff772d579ffda7f0484e1b52f873e1f0aded85b25006d7cc
  • Pointer size: 131 Bytes
  • Size of remote file: 208 kB

Git LFS Details

  • SHA256: 848f675e42a4c3cfb9af0b21f7f8d706cf971943a68d8070073fb15f70ac56d3
  • Pointer size: 130 Bytes
  • Size of remote file: 81.8 kB
assets/table2.png CHANGED

Git LFS Details

  • SHA256: c0aa61f8923f4dca1e00154271bb50e3d9e1f4a9edba455972fc4220a61427a8
  • Pointer size: 131 Bytes
  • Size of remote file: 202 kB

Git LFS Details

  • SHA256: feac2b53b187b3916e611fad4b456b1d8143150dc182e04f9179ba8b1c1d42a0
  • Pointer size: 130 Bytes
  • Size of remote file: 87.5 kB
assets/table3.png CHANGED

Git LFS Details

  • SHA256: 29b59f0f3003028f539dfbfcf2195846257ae589c3684c6240c3add104b11cf8
  • Pointer size: 131 Bytes
  • Size of remote file: 176 kB

Git LFS Details

  • SHA256: 7aa37b8cbf76bc77f2113a613044ca89580692ce28912f162fa79ada88533b91
  • Pointer size: 130 Bytes
  • Size of remote file: 77.1 kB
assets/table4.png CHANGED

Git LFS Details

  • SHA256: cd7ded01e3fdb35b0f2f9c9f833d0856ff743d96ad494ce27cc7be96d18aa36a
  • Pointer size: 131 Bytes
  • Size of remote file: 179 kB

Git LFS Details

  • SHA256: f7cc843e9919ad60ac16d9b3416bef40097a45649ab09e29e1e8dfa9dde70cbf
  • Pointer size: 130 Bytes
  • Size of remote file: 75.6 kB