List your company

Accuracy on GQA (Visual Question Answering)

61.97AccuracyOriginal
50.706853.630956.55559.4791May 13, 2026

Evaluation results

MethodLinks
OriginalBackbone=LLaVA-1.5-7B, Token Budget=Full2026.0561.97
GRIP+decoder+rlBackbone=LLaVA-1.5-7B, Token Budget=192 tokens, Optimization Strategy=rl, Pruning Component=decoder2026.0561.79
GRIP+decoder+slBackbone=LLaVA-1.5-7B, Token Budget=192 tokens, Optimization Strategy=sl, Pruning Component=decoder2026.0560.61
GRIP+decoder+rlBackbone=LLaVA-1.5-7B, Token Budget=128 tokens, Optimization Strategy=rl, Pruning Component=decoder2026.0560.57
DivPruneBackbone=LLaVA-1.5-7B, Token Budget=192 tokens2026.0560.07
GRIP+encoder+rlBackbone=LLaVA-1.5-7B, Token Budget=192 tokens, Optimization Strategy=rl, Pruning Component=encoder2026.0559.82
GRIP+encoder+slBackbone=LLaVA-1.5-7B, Token Budget=192 tokens, Optimization Strategy=sl, Pruning Component=encoder2026.0559.77
VisprunerBackbone=LLaVA-1.5-7B, Token Budget=192 tokens2026.0559.58
DARTBackbone=LLaVA-1.5-7B, Token Budget=192 tokens2026.0559.52
SparseVLMBackbone=LLaVA-1.5-7B, Token Budget=192 tokens2026.0559.48
DivPruneBackbone=LLaVA-1.5-7B, Token Budget=128 tokens2026.0559.27
GRIP+decoder+slBackbone=LLaVA-1.5-7B, Token Budget=128 tokens, Optimization Strategy=sl, Pruning Component=decoder2026.0559.27
VisionZipBackbone=LLaVA-1.5-7B, Token Budget=192 tokens2026.0559.26
PruneSIDBackbone=LLaVA-1.5-7B, Token Budget=192 tokens2026.0559.17
GRIP+encoder+rlBackbone=LLaVA-1.5-7B, Token Budget=128 tokens, Optimization Strategy=rl, Pruning Component=encoder2026.0558.66
GRIP+encoder+slBackbone=LLaVA-1.5-7B, Token Budget=128 tokens, Optimization Strategy=sl, Pruning Component=encoder2026.0558.54
SparseVLMBackbone=LLaVA-1.5-7B, Token Budget=128 tokens2026.0558.38
VisprunerBackbone=LLaVA-1.5-7B, Token Budget=128 tokens2026.0558.29
PruneSIDBackbone=LLaVA-1.5-7B, Token Budget=128 tokens2026.0557.91
DARTBackbone=LLaVA-1.5-7B, Token Budget=128 tokens2026.0557.78
VisionZipBackbone=LLaVA-1.5-7B, Token Budget=128 tokens2026.0557.67
DivPruneBackbone=LLaVA-1.5-7B, Token Budget=64 tokens2026.0557.62
PruneSIDBackbone=LLaVA-1.5-7B, Token Budget=64 tokens2026.0557.1
GRIP+encoder+rlBackbone=LLaVA-1.5-7B, Token Budget=64 tokens, Optimization Strategy=rl, Pruning Component=encoder2026.0556.79
GRIP+encoder+slBackbone=LLaVA-1.5-7B, Token Budget=64 tokens, Optimization Strategy=sl, Pruning Component=encoder2026.0556.5
VisprunerBackbone=LLaVA-1.5-7B, Token Budget=64 tokens2026.0555.76
VisionZipBackbone=LLaVA-1.5-7B, Token Budget=64 tokens2026.0555.1
GRIP+decoder+slBackbone=LLaVA-1.5-7B, Token Budget=64 tokens, Optimization Strategy=sl, Pruning Component=decoder2026.0554.48
GRIP+decoder+rlBackbone=LLaVA-1.5-7B, Token Budget=64 tokens, Optimization Strategy=rl, Pruning Component=decoder2026.0554.4
SparseVLMBackbone=LLaVA-1.5-7B, Token Budget=64 tokens2026.0553.68
DARTBackbone=LLaVA-1.5-7B, Token Budget=64 tokens2026.0551.14