Visual Question Answering on OK-VQA full (val)
62.24AccuracyHyper-ICL
Evaluation Results
| Method | Links | |
|---|---|---|
| Hyper-ICLModel=Idefics2-8b, Method Type=Learnable, # Params (M)=1.18 (×1)2026.06 | 62.24 | |
| MimICModel=Idefics2-8b, Method Type=Learnable, # Params (M)=0.26 (×0.22)2026.06 | 58.74 | |
| 8-shot ICLModel=Idefics2-8b, Method Type=Direct ICDs2026.06 | 57.68 | |
| RICESModel=Idefics2-8b, Method Type=Direct ICDs2026.06 | 55.73 | |
| Hyper-ICLModel=Idefics-9b, Method Type=Learnable, # Params (M)=1.18 (×1)2026.06 | 55.31 | |
| LoRAModel=Idefics2-8b, Method Type=Learnable, # Params (M)=17.6 (×14.9)2026.06 | 55.05 | |
| LIVEModel=Idefics2-8b, Method Type=Learnable, # Params (M)=0.13 (×0.11)2026.06 | 54.86 | |
| MimICModel=Idefics-9b, Method Type=Learnable, # Params (M)=0.26 (×0.22)2026.06 | 52.05 | |
| RICESModel=Idefics-9b, Method Type=Direct ICDs2026.06 | 51.11 | |
| 32-shot ICLModel=Idefics-9b, Method Type=Direct ICDs2026.06 | 48.48 | |
| LoRAModel=Idefics-9b, Method Type=Learnable, # Params (M)=25.0 (×21.2)2026.06 | 47.06 | |
| LIVEModel=Idefics-9b, Method Type=Learnable, # Params (M)=0.13 (×0.11)2026.06 | 46.05 | |
| Zero-shotModel=Idefics2-8b, Method Type=Direct ICDs2026.06 | 43.08 | |
| TVModel=Idefics2-8b, Method Type=Non-Learnable2026.06 | 38.27 | |
| FVModel=Idefics2-8b, Method Type=Non-Learnable2026.06 | 34.58 | |
| TVModel=Idefics-9b, Method Type=Non-Learnable2026.06 | 32.68 | |
| FVModel=Idefics-9b, Method Type=Non-Learnable2026.06 | 31.02 | |
| Zero-shotModel=Idefics-9b, Method Type=Direct ICDs2026.06 | 30.54 |