SQ-LLaVA: Self-Questioning for Large Vision-Language Assistant
Open paper
Benchmark
Model
Rank
Results
visual-question-answering-on-mm-vet
SQ-LLaVA∗
#104
GPT-4 score: 39.7
visual-question-answering-on-mm-vet
SQ-LLaVA
#137
GPT-4 score: 35.5
Rank counts only results with a code link.