Unfold The World: Factorize 4D Properties in Reinforcing Spatial Understanding

Benchmark Model Rank Results
spatial-reasoning-on-vsi-benchFactoSR-8B-RL–Accuracy: 61.5
visual-question-answering-vqa-on-blinkFactoSR-8B-RL–Accuracy: 55.4
visual-question-answering-vqa-on-realworldqaFactoSR-8B-RL–Accuracy: 47.3