Categorical Visual Question Answering on InstaOrder Occ.
0.627AccuracySN
Evaluation results
| Method | Links | ||
|---|---|---|---|
| SNBase Model=LLaVA-v1.5-7b, Probing Set Size=3,000, Configuration=Best probed2026.03 | 0.627 | 0.69 | |
| SNBase Model=Qwen-VL-4b-Instruct, Probing Set Size=3,000, Configuration=Best probed2026.03 | 0.626 | 0.691 | |
| LLaVA-v1.5-7bProbing Set Size=3,0002026.03 | 0.539 | 0.461 | |
| Qwen-VL-4b-InstructProbing Set Size=3,0002026.03 | 0.508 | 0.042 |