Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation
Open paper
Benchmark
Model
Rank
Results
on-wise
Janus
#9
Overall: 0.23
Cultural: 0.16
Time: 0.26
Space: 0.35
Biology: 0.28
…
visual-question-answering-on-mm-vet
Janus
#116
GPT-4 score: 34.3
Rank counts only results with a code link.