Image-Text-to-Text
Safetensors
llava_llama
BoyuNLP commited on
Commit
87b58f0
·
verified ·
1 Parent(s): 91dd55e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -56,7 +56,7 @@ UGround is a storng GUI visual grounding model trained with a simple recipe. Che
56
 
57
  ### GUI Visual Grounding: ScreenSpot (Standard Setting)
58
 
59
- | Model | Arch | SFT data | Mobile-Text | Mobile-Icon | Desktop-Text | Desktop-Icon | Web-Text | Web-Icon | Avg |
60
  | ---------------------------- | ---------------- | ---------------- | ----------- | ----------- | ------------ | ------------ | -------- | -------- | -------- |
61
  | GPT-4 | | | 22.6 | 24.5 | 20.2 | 11.8 | 9.2 | 8.8 | 16.2 |
62
  | GPT-4o | | | 20.2 | 24.9 | 21.1 | 23.6 | 12.2 | 7.8 | 18.3 |
 
56
 
57
  ### GUI Visual Grounding: ScreenSpot (Standard Setting)
58
 
59
+ | Grounding Model | Arch | SFT data | Mobile-Text | Mobile-Icon | Desktop-Text | Desktop-Icon | Web-Text | Web-Icon | Avg |
60
  | ---------------------------- | ---------------- | ---------------- | ----------- | ----------- | ------------ | ------------ | -------- | -------- | -------- |
61
  | GPT-4 | | | 22.6 | 24.5 | 20.2 | 11.8 | 9.2 | 8.8 | 16.2 |
62
  | GPT-4o | | | 20.2 | 24.9 | 21.1 | 23.6 | 12.2 | 7.8 | 18.3 |