List your company

Semantic Probing on Visual Genome (VG) (test)

56.42Top-1 AccuracyCOMiT-L
24.845633.042841.2449.4372Feb 24, 2026

Evaluation results

MethodLinks
COMiT-L#params=610M, msg length=256, voc. size=64k2026.0256.42
COMiT-XL#params=900M, msg length=256, voc. size=64k2026.0255.61
FlexTok(d18-d18)#params=860M, msg length=256, voc. size=64k2026.0254.46
FlexTok(d18-d28)#params=2.5B, msg length=256, voc. size=64k2026.0254.35
FlexTok(d12-d12)#params=254M, msg length=256, voc. size=64k2026.0253.75
COMiT-B#params=174M, msg length=256, voc. size=64k2026.0252.11
SelfTok#params=2.17B, msg length=512, voc. size=2^15, trained on larger data mixtures=true2026.0237.15
SelfTok#params=2.17B, msg length=1024, voc. size=2^16, trained on larger data mixtures=true2026.0236.69
ALIT#params=229M, msg length=256, voc. size=2^102026.0232.14
TiTok-B#params=172M, msg length=64, voc. size=2^122026.0227.31
TiTok-S#params=44M, msg length=128, voc. size=2^122026.0226.81
TiTok-L#params=614M, msg length=32, voc. size=2^122026.0226.06