List your company

Visual Question Answering on POPE GQA

86.62AccuracySeeMe
75.512878.396481.2884.1636Jul 5, 2026

Evaluation results

MethodLinks
SeeMeModel=LLaVA-NEXT, Decoding=SeeMe2026.0786.6286.47
DCLAModel=LLaVA-NEXT, Decoding=DCLA2026.0786.6186.41
RegularModel=LLaVA-NEXT, Decoding=Regular2026.0786.5886.41
SPINModel=LLaVA-NEXT, Decoding=SPIN2026.0785.9985.67
DoLaModel=LLaVA-NEXT, Decoding=DoLa2026.0784.6483.2
SeeMeModel=INF-MLLM, Decoding=SeeMe2026.0783.6785.01
DoLaModel=mPLUG-Owl2, Decoding=DoLa2026.0783.4980.38
SPINModel=INF-MLLM, Decoding=SPIN2026.0783.4784.98
DCLAModel=INF-MLLM, Decoding=DCLA2026.0783.0484.94
DoLaModel=INF-MLLM, Decoding=DoLa2026.0782.8884.81
RegularModel=INF-MLLM, Decoding=Regular2026.0782.7784.73
SeeMeModel=mPLUG-Owl2, Decoding=SeeMe2026.0782.3382.27
SPINModel=mPLUG-Owl2, Decoding=SPIN2026.0782.1181.78
DCLAModel=mPLUG-Owl2, Decoding=DCLA2026.0781.6181.94
RegularModel=mPLUG-Owl2, Decoding=Regular2026.0781.1881.61
VCDModel=INF-MLLM, Decoding=VCD2026.0779.7982.05
VCDModel=mPLUG-Owl2, Decoding=VCD2026.0779.0378
VCDModel=LLaVA-NEXT, Decoding=VCD2026.0778.8575.27
SeeMeModel=LLaVA-1.5, Decoding=SeeMe2026.0777.581.52
DCLAModel=LLaVA-1.5, Decoding=DCLA2026.0777.4181.51
SPINModel=LLaVA-1.5, Decoding=SPIN2026.0777.2281.4
RegularModel=LLaVA-1.5, Decoding=Regular2026.0776.5780.98
DoLaModel=LLaVA-1.5, Decoding=DoLa2026.0776.5680.84
VCDModel=LLaVA-1.5, Decoding=VCD2026.0775.9480.36