Calibrated Self-Rewarding Vision Language Models
Open paper
Benchmark
Model
Rank
Results
visual-question-answering-on-mm-vet
LLaVA-1.5-13B (+CSR)
#85
GPT-4 score: 37.8
Params: 13B
visual-question-answering-on-mm-vet
LLaVA-1.5-7B (CSR)
#118
GPT-4 score: 33.9
Params: 7B
Rank counts only results with a code link.