Visual Reasoning on CLEVR R
46ScoreDATAPROPHET
Evaluation Results
| Method | Links | |
|---|---|---|
| DATAPROPHETRL Post-training Setup=Real RL, Data Selection Strategy=D.P.2026.03 | 46 | |
| BaselineRL Post-training Setup=Real RL, Data Selection Strategy=Equal2026.03 | 44 | |
| BaselineRL Post-training Setup=Synthetic RL, Data Selection Strategy=Random2026.03 | 42 | |
| DATAPROPHETRL Post-training Setup=Synthetic RL, Data Selection Strategy=D.P.2026.03 | 42 | |
| BaselineRL Post-training Setup=No RL, Data Selection Strategy=Baseline2026.03 | 41 |