UniCorn: Towards Self-Improving Unified Multimodal Models through Self-Generated Supervision

Benchmark Model Rank Results
text-to-image-generation-on-tiif-bench-miniUniCorn#9Accuracy: 74.7
text-to-image-generation-on-oneig-enUniCorn#25OneIG Overall Score: 0.426
image-generation-on-wiseUniCorn#28Overall: 0.55
text-to-image-generation-on-dpg-benchUniCorn#32DPG-Bench Score: 86.8
text-to-image-generation-on-genevalUniCorn#88Overall: 0.82