Semantic Probing on Visual Genome (VG) (test)
56.42Top-1 AccuracyCOMiT-L
Evaluation Results
| Method | Links | |
|---|---|---|
| COMiT-L#params=610M, msg length=256, voc. size=64k2026.02 | 56.42 | |
| COMiT-XL#params=900M, msg length=256, voc. size=64k2026.02 | 55.61 | |
| FlexTok(d18-d18)#params=860M, msg length=256, voc. size=64k2026.02 | 54.46 | |
| FlexTok(d18-d28)#params=2.5B, msg length=256, voc. size=64k2026.02 | 54.35 | |
| FlexTok(d12-d12)#params=254M, msg length=256, voc. size=64k2026.02 | 53.75 | |
| COMiT-B#params=174M, msg length=256, voc. size=64k2026.02 | 52.11 | |
| SelfTok#params=2.17B, msg length=512, voc. size=2^15, trained on larger data mixtures=true2026.02 | 37.15 | |
| SelfTok#params=2.17B, msg length=1024, voc. size=2^16, trained on larger data mixtures=true2026.02 | 36.69 | |
| ALIT#params=229M, msg length=256, voc. size=2^102026.02 | 32.14 | |
| TiTok-B#params=172M, msg length=64, voc. size=2^122026.02 | 27.31 | |
| TiTok-S#params=44M, msg length=128, voc. size=2^122026.02 | 26.81 | |
| TiTok-L#params=614M, msg length=32, voc. size=2^122026.02 | 26.06 |