Hugging Face's logo

OpenMOSS-Team
/
RoboOmni

Robotics
Transformers
Safetensors
English
qwen2_5_omni_thinker
text-generation
Model card Files
xet
Community
1
sinwang commited on
Commit
308fa0f
·
verified ·
1 Parent(s): 862610c

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -2
README.md CHANGED
@@ -13,7 +13,8 @@ language:
13
  </h1>
14
  </div>
15
 
16
- ![logo](./assets/logo.png)
 
17
 
18
  ---
19
 
@@ -28,9 +29,10 @@ To address the absence of training data for proactive intention recognition in r
28
 
29
  At the heart of RoboOmni lies the Perceiver-Thinker-Talker-Executor architecture, which unifies multiple modalities (vision, speech, environmental sounds) into a single, seamless framework for robot action execution.
30
 
31
- ![Omni Logo](./assets/model.jpg)
32
 
33
 
 
 
34
 
35
 
36
 
 
13
  </h1>
14
  </div>
15
 
16
+
17
+ ![logo](https://cdn-uploads.huggingface.co/production/uploads/64c3c631e77ea9f28111172a/Lb55aSaitdpNl1iSC8xrm.png)
18
 
19
  ---
20
 
 
29
 
30
  At the heart of RoboOmni lies the Perceiver-Thinker-Talker-Executor architecture, which unifies multiple modalities (vision, speech, environmental sounds) into a single, seamless framework for robot action execution.
31
 
 
32
 
33
 
34
+ ![WechatIMG2567](https://cdn-uploads.huggingface.co/production/uploads/64c3c631e77ea9f28111172a/z5hqTgAPU0BiFtdrKwq8A.jpeg)
35
+
36
 
37
 
38