Visual Question Answering on IllusionVQA
42AccuracyTASM
Evaluation Results
| Method | Links | |
|---|---|---|
| TASMExample Number=20, Average Context Length=17572026.06 | 42 | |
| MLoC (Qwen2-VL)Example Number=20, Average Context Length=72712026.06 | 40.9 | |
| EMLoC (Qwen2-VL)Example Number=20, Average Context Length=18782026.06 | 40.9 | |
| MLoC (Qwen2-VL)Example Number=5, Average Context Length=18262026.06 | 38.8 | |
| Qwen2-VL (7B)Example Number=02026.06 | 35.3 | |
| MiniCPM-V2.6 (8B)Example Number=02026.06 | 34.6 | |
| Llama3.2-V (11B)Example Number=02026.06 | 33 | |
| InternVL2 (8B)Example Number=02026.06 | 28 | |
| Llava1.5 (7B)Example Number=02026.06 | 24.1 |