List your company

Visual Question Answering on POPE A-OKVQA

87.61AccuracySeeMe
77.4780.102582.73585.3675Jul 5, 2026

Evaluation results

MethodLinks
SeeMeModel=LLaVA-NEXT, Decoding=SeeMe2026.0787.6187.77
DCLAModel=LLaVA-NEXT, Decoding=DCLA2026.0787.5587.58
RegularModel=LLaVA-NEXT, Decoding=Regular2026.0787.4187.46
SPINModel=LLaVA-NEXT, Decoding=SPIN2026.0787.1187.06
DoLaModel=LLaVA-NEXT, Decoding=DoLa2026.0786.4685.63
SeeMeModel=INF-MLLM, Decoding=SeeMe2026.0784.786.01
DCLAModel=INF-MLLM, Decoding=DCLA2026.0784.1485.91
DoLaModel=INF-MLLM, Decoding=DoLa2026.0784.1285.89
SeeMeModel=mPLUG-Owl2, Decoding=SeeMe2026.0783.7684.42
RegularModel=INF-MLLM, Decoding=Regular2026.0783.6684.37
SPINModel=INF-MLLM, Decoding=SPIN2026.0783.4684.33
SPINModel=mPLUG-Owl2, Decoding=SPIN2026.0783.4384.25
DoLaModel=mPLUG-Owl2, Decoding=DoLa2026.0783.4283.42
DCLAModel=mPLUG-Owl2, Decoding=DCLA2026.0783.284.31
RegularModel=mPLUG-Owl2, Decoding=Regular2026.0783.0383.69
VCDModel=INF-MLLM, Decoding=VCD2026.0781.783.7
DCLAModel=LLaVA-1.5, Decoding=DCLA2026.0779.7683.12
SeeMeModel=LLaVA-1.5, Decoding=SeeMe2026.0779.6682.99
SPINModel=LLaVA-1.5, Decoding=SPIN2026.0779.4182.86
VCDModel=LLaVA-NEXT, Decoding=VCD2026.0779.2475.8
VCDModel=mPLUG-Owl2, Decoding=VCD2026.0779.0378.56
RegularModel=LLaVA-1.5, Decoding=Regular2026.0778.8482.51
DoLaModel=LLaVA-1.5, Decoding=DoLa2026.0778.782.28
VCDModel=LLaVA-1.5, Decoding=VCD2026.0777.8681.41