Visual Question Answering on VC-GVQA
83.7AccuracyOracle
Evaluation results
| Method | Links | |
|---|---|---|
| OracleData Source Type=Real Data Reweighting, Sampling Strategy Category=Gold, Compute Budget=280K datapoints2026.03 | 83.7 | |
| D.P.Data Source Type=Real Data Reweighting, Sampling Strategy Category=Ours, Compute Budget=280K datapoints2026.03 | 83.5 | |
| ICONSData Source Type=Real Data Reweighting, Sampling Strategy Category=Baseline, Compute Budget=280K datapoints2026.03 | 82.3 | |
| UniformData Source Type=Real Data Reweighting, Sampling Strategy Category=Baseline, Compute Budget=280K datapoints2026.03 | 81.5 | |
| D.P.Data Source Type=Synthetic Data Selection, Sampling Strategy Category=Ours, Compute Budget=280K datapoints2026.03 | 76.8 | |
| ICONSData Source Type=Synthetic Data Selection, Sampling Strategy Category=Baseline, Compute Budget=280K datapoints2026.03 | 75.9 | |
| DATAPROPHETRL Post-training Setup=Real RL, Data Selection Strategy=D.P.2026.03 | 69 | |
| UniformData Source Type=Synthetic Data Selection, Sampling Strategy Category=Baseline, Compute Budget=280K datapoints2026.03 | 67.8 | |
| BaselineRL Post-training Setup=Real RL, Data Selection Strategy=Equal2026.03 | 67 | |
| BaselineRL Post-training Setup=No RL, Data Selection Strategy=Baseline2026.03 | 65 | |
| DATAPROPHETRL Post-training Setup=Synthetic RL, Data Selection Strategy=D.P.2026.03 | 65 | |
| BaselineRL Post-training Setup=Synthetic RL, Data Selection Strategy=Random2026.03 | 64 |