List your company

Visual Question Answering on POPE MSCOCO

88.47AccuracySeeMe
78.652481.201283.7586.2988Jul 5, 2026

Evaluation results

MethodLinks
SeeMeModel=INF-MLLM, Decoding=SeeMe2026.0788.4788.56
DCLAModel=INF-MLLM, Decoding=DCLA2026.0788.4388.46
SPINModel=INF-MLLM, Decoding=SPIN2026.0788.3188.41
RegularModel=INF-MLLM, Decoding=Regular2026.0788.2988.36
DoLaModel=INF-MLLM, Decoding=DoLa2026.0788.2888.36
DCLAModel=LLaVA-NEXT, Decoding=DCLA2026.0787.7186.49
RegularModel=LLaVA-NEXT, Decoding=Regular2026.0787.6286.42
SeeMeModel=LLaVA-NEXT, Decoding=SeeMe2026.0787.6286.44
SPINModel=LLaVA-NEXT, Decoding=SPIN2026.0786.8985.35
SeeMeModel=mPLUG-Owl2, Decoding=SeeMe2026.0786.7786.32
DCLAModel=mPLUG-Owl2, Decoding=DCLA2026.0786.5186.19
SPINModel=mPLUG-Owl2, Decoding=SPIN2026.0786.4186.03
RegularModel=mPLUG-Owl2, Decoding=Regular2026.0786.3985.91
SeeMeModel=LLaVA-1.5, Decoding=SeeMe2026.0786.0786.73
DoLaModel=mPLUG-Owl2, Decoding=DoLa2026.0785.9886.34
DCLAModel=LLaVA-1.5, Decoding=DCLA2026.0785.8286.45
VCDModel=INF-MLLM, Decoding=VCD2026.0785.5685.73
SPINModel=LLaVA-1.5, Decoding=SPIN2026.0785.3486.12
RegularModel=LLaVA-1.5, Decoding=Regular2026.0785.1986.1
DoLaModel=LLaVA-1.5, Decoding=DoLa2026.0785.0885.99
DoLaModel=LLaVA-NEXT, Decoding=DoLa2026.0784.9182.55
VCDModel=LLaVA-1.5, Decoding=VCD2026.0784.6685.35
VCDModel=LLaVA-NEXT, Decoding=VCD2026.0779.6574.82
VCDModel=mPLUG-Owl2, Decoding=VCD2026.0779.0378.56