Image Reconstruction on ImageNet-1k (test)
0.54rFIDSelfTok
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| SelfTok#params=2.17B, msg length=1024, voc. size=2^16, trained on larger data mixtures=true2026.02 | 0.54 | 26.3 | |
| SelfTok#params=2.17B, msg length=512, voc. size=2^15, trained on larger data mixtures=true2026.02 | 0.7 | 24.14 | |
| FlexTok(d18-d28)#params=2.5B, msg length=256, voc. size=64k2026.02 | 1.45 | 18.46 | |
| FlexTok(d18-d18)#params=860M, msg length=256, voc. size=64k2026.02 | 1.61 | 18.59 | |
| TiTok-B#params=172M, msg length=64, voc. size=2^122026.02 | 1.7 | 16.8 | |
| TiTok-S#params=44M, msg length=128, voc. size=2^122026.02 | 1.71 | 17.52 | |
| TiTok-L#params=614M, msg length=32, voc. size=2^122026.02 | 2.21 | 15.6 | |
| COMiT-XL#params=900M, msg length=256, voc. size=64k2026.02 | 3.5 | 17.83 | |
| COMiT-L#params=610M, msg length=256, voc. size=64k2026.02 | 3.67 | 17.81 | |
| FlexTok(d12-d12)#params=254M, msg length=256, voc. size=64k2026.02 | 4.2 | 18.41 | |
| ALIT#params=229M, msg length=256, voc. size=2^102026.02 | 7.39 | 19.76 | |
| COMiT-B#params=174M, msg length=256, voc. size=64k2026.02 | 11.06 | 17.75 |