List your company

Visual Question Answering on GQA v1.2 (test)

61.9GQA ScoreVanilla
41.146.551.957.3Feb 4, 2026

Evaluation results

MethodLinks
VanillaBackbone=LLaVA-1.5-7B, Token Budget=576, Method Type=Baseline2026.0261.9100
PIO-FVLMBackbone=LLaVA-1.5-7B, Token Budget=192, VE=w/ VE, Venue=Ours2026.0261.198.9
PIO-FVLMBackbone=LLaVA-1.5-7B, Token Budget=192, VE=w/o VE, Venue=Ours2026.026198.8
SCOPEBackbone=LLaVA-1.5-7B, Token Budget=192, VE=w/ VE, Venue=NeurIPS’252026.0260.198.3
DARTBackbone=LLaVA-1.5-7B, Token Budget=192, VE=w/o VE, Venue=EMNLP’252026.026098.3
PIO-FVLMBackbone=LLaVA-1.5-7B, Token Budget=128, VE=w/o VE, Venue=Ours2026.026098.1
PIO-FVLMBackbone=LLaVA-1.5-7B, Token Budget=128, VE=w/ VE, Venue=Ours2026.026098.1
SCOPEBackbone=LLaVA-1.5-7B, Token Budget=128, VE=w/ VE, Venue=NeurIPS’252026.0259.797.5
SparseVLMBackbone=LLaVA-1.5-7B, Token Budget=192, VE=w/o VE, Venue=ICML’252026.0259.597.2
VisionZipBackbone=LLaVA-1.5-7B, Token Budget=192, VE=w/ VE, Venue=CVPR’252026.0259.397.8
HoloVBackbone=LLaVA-1.5-7B, Token Budget=192, VE=w/ VE, Venue=NeurIPS’252026.025998.7
DARTBackbone=LLaVA-1.5-7B, Token Budget=128, VE=w/o VE, Venue=EMNLP’252026.0258.797
SparseVLMBackbone=LLaVA-1.5-7B, Token Budget=128, VE=w/o VE, Venue=ICML’252026.0258.495.6
SCOPEBackbone=LLaVA-1.5-7B, Token Budget=64, VE=w/ VE, Venue=NeurIPS’252026.0258.395.4
PIO-FVLMBackbone=LLaVA-1.5-7B, Token Budget=64, VE=w/ VE, Venue=Ours2026.0258.396.6
PIO-FVLMBackbone=LLaVA-1.5-7B, Token Budget=64, VE=w/o VE, Venue=Ours2026.025894.7
HoloVBackbone=LLaVA-1.5-7B, Token Budget=128, VE=w/ VE, Venue=NeurIPS’252026.0257.797.2
VisionZipBackbone=LLaVA-1.5-7B, Token Budget=128, VE=w/ VE, Venue=CVPR’252026.0257.696.4
PDropBackbone=LLaVA-1.5-7B, Token Budget=192, VE=w/o VE, Venue=CVPR’252026.0257.196.2
PDropBackbone=LLaVA-1.5-7B, Token Budget=128, VE=w/o VE, Venue=CVPR’252026.025694
DARTBackbone=LLaVA-1.5-7B, Token Budget=64, VE=w/o VE, Venue=EMNLP’252026.0255.992.8
HoloVBackbone=LLaVA-1.5-7B, Token Budget=64, VE=w/ VE, Venue=NeurIPS’252026.0255.394.4
VisionZipBackbone=LLaVA-1.5-7B, Token Budget=64, VE=w/ VE, Venue=CVPR’252026.0255.193
SparseVLMBackbone=LLaVA-1.5-7B, Token Budget=64, VE=w/o VE, Venue=ICML’252026.0253.890.6
FastVBackbone=LLaVA-1.5-7B, Token Budget=192, VE=w/o VE, Venue=ECCV’242026.0252.789
FastVBackbone=LLaVA-1.5-7B, Token Budget=128, VE=w/o VE, Venue=ECCV’242026.0249.683.2
FastVBackbone=LLaVA-1.5-7B, Token Budget=64, VE=w/o VE, Venue=ECCV’242026.0246.174
PDropBackbone=LLaVA-1.5-7B, Token Budget=64, VE=w/o VE, Venue=CVPR’252026.0241.974.4