3 papers
cs.LG2026
KroQuant: Kronecker-Structured Block Transforms for Efficient Post-Training Quantization of Diffusion Transformers
Yann Bouquet, Alireza Khodamoradi, Kristof Denolf +1
Post-training quantization (PTQ) of diffusion transformers (DiTs) to W4A4 severely degrades output quality, because activations entering each linear layer contain outliers that 4-b…
cs.LG2026
AdaHOP: Fast and Accurate Low-Precision Training via Outlier-Pattern-Aware Rotation
Seonggon Kim, Alireza Khodamoradi, Pranathi Vasireddy +2
Hadamard transforms have become a key tool for stabilizing low-precision training, but existing methods apply them uniformly across tensors and computation paths. We show that this…
cs.LG2026
LoRaQ: Optimized Low Rank Approximation for 4-bit Quantization
Yann Bouquet, Alireza Khodamoradi, Sophie Yáng Shen +2
Post-training quantization (PTQ) is essential for deploying large diffusion transformers on resource-constrained hardware, but aggressive 4-bit quantization significantly degrades…