Update README.md
Browse files
README.md
CHANGED
|
@@ -14,9 +14,17 @@ UGround is a storng GUI visual grounding model trained with a simple recipe. Che
|
|
| 14 |
- **Point of Contact:** [Boyu Gou](mailto:gou.43@osu.edu)
|
| 15 |
|
| 16 |
- [x] Model Weights
|
| 17 |
-
- [x]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
- [ ] Code
|
| 19 |
-
- [
|
| 20 |
- [x] Offline Experiments
|
| 21 |
- [x] Screenspot (along with referring expressions generated by GPT-4/4o)
|
| 22 |
- [x] Multimodal-Mind2Web
|
|
|
|
| 14 |
- **Point of Contact:** [Boyu Gou](mailto:gou.43@osu.edu)
|
| 15 |
|
| 16 |
- [x] Model Weights
|
| 17 |
+
- [x] Initial V1 (the one used in the paper)
|
| 18 |
+
- [x] Qwen2-VL-based V1
|
| 19 |
+
- [x] 2B
|
| 20 |
+
- [x] 7B
|
| 21 |
+
- [ ] 72B
|
| 22 |
+
- [ ] V1.1
|
| 23 |
+
- [ ] 2B
|
| 24 |
+
- [ ] 7B
|
| 25 |
+
- [ ] 72B
|
| 26 |
- [ ] Code
|
| 27 |
+
- [x] Inference Code of UGround
|
| 28 |
- [x] Offline Experiments
|
| 29 |
- [x] Screenspot (along with referring expressions generated by GPT-4/4o)
|
| 30 |
- [x] Multimodal-Mind2Web
|