MAR-L, Diff Loss

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 512x512
FID· 2024-06-17
1.73
best: 1.21 (EDM2-L + DDO (SD-VAE, 25 steps, DPM-Solver-v3))
Autoregressive Image Generation without Vector Quantization arXiv:2406.11838
Image GenerationonImageNet 256x256
FID· 2024-06-17
1.78
best: 1.06 (SiT-XL/2 + UCGM-S (E2E-VAE + 40 sampling steps + CFG))
Autoregressive Image Generation without Vector Quantization arXiv:2406.11838