| Paper | Code | Accuracy | number | other | overall | yes/no | ModelName | ReleaseDate |
|---|---|---|---|---|---|---|---|---|
| LXMERT Model Compression for Visual Question Answering | ✓ Link | 70.87 | LXMERT (low-magnitude pruning) | 2023-10-23 | ||||
| OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework | ✓ Link | 71.44 | 73.35 | 81.98 | 94.66 | OFA | 2022-02-07 | |
| Florence: A New Foundation Model for Computer Vision | ✓ Link | 80.36 | Florence | 2021-11-22 |