AliTok-XL, autoregressive, 318M

Reported on 2 benchmarks across 1 task · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Medical2 results

Image GenerationonImageNet 256x256
FID· 2025-06-05
1.42
best: 1.06 (SiT-XL/2 + UCGM-S (E2E-VAE + 40 sampling steps + CFG))
AliTok: Towards Sequence Modeling Alignment between Tokenizer and Autoregressive Model arXiv:2506.05289
Image GenerationonImageNet 256x256
Inception score· 2025-06-05
326.6
best: 338.08 (LEGO-XL)
AliTok: Towards Sequence Modeling Alignment between Tokenizer and Autoregressive Model arXiv:2506.05289