List your company

Visual Question Answering on GQA (Accuracy and Relative Accuracy)

63.2AccuracyVanilla
55.9257.8159.761.59May 28, 2026

Evaluation results

MethodLinks
VanillaBackbone=LLaVA-v1.5 13B, Token Retention Budget=576, Token Retention Ratio=100%2026.0563.2100
OccamTokenBackbone=LLaVA-v1.5 13B, Token Retention Budget=128, Token Retention Ratio=22.2%2026.0561.298.8
OccamTokenBackbone=LLaVA-v1.5 13B, Token Retention Budget=64, Token Retention Ratio=11.1%2026.0559.397.9
VisionZipBackbone=LLaVA-v1.5 13B, Token Retention Budget=128, Token Retention Ratio=22.2%2026.0557.997.1
VisionZipBackbone=LLaVA-v1.5 13B, Token Retention Budget=64, Token Retention Ratio=11.1%2026.0556.293.6