C3-UniMM: Causal Cycle-Consistent Unified Multimodal Modeling via Super Alignment and Shared Decoding Space
Open paper
Benchmark
Model
Rank
Results
text-to-image-generation-on-geneval
C3-UniMM (1.5B)
–
Overall: 0.78
text-to-image-generation-on-geneval
C3-UniMM (7B)
–
Overall: 0.82
Rank counts only results with a code link.