A quantization transform combining dynamic per-token mean centering, channel scaling, and Hadamard transforms reduces 4-bit activation quantization error in diffusion transformers, achieving a CLIP score of 31.69 on PixArt-Sigma.
Affinequant: Affine transformation quantization for large language models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
HadaNorm: Diffusion Transformer Quantization through Mean-Centered Transformations
A quantization transform combining dynamic per-token mean centering, channel scaling, and Hadamard transforms reduces 4-bit activation quantization error in diffusion transformers, achieving a CLIP score of 31.69 on PixArt-Sigma.