A mix of signed and unsigned 4-bit floating-point formats, timestep-aware LoRA experts, and a denoising-weighted loss keeps diffusion-model image quality close to full precision.
Learned step size quantization
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
other 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
other 1polarities
unclear 1representative citing papers
citing papers explorer
-
Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning
A mix of signed and unsigned 4-bit floating-point formats, timestep-aware LoRA experts, and a denoising-weighted loss keeps diffusion-model image quality close to full precision.