SOURCE-LINKED INTELLIGENCE

DSAQuant: Denoising-Stage-Aligned Quantization-Aware Training for Video Generation

arXiv · AI, language, vision and robotics · article · Sep 3, 2026 · UTC

Video diffusion models (VDMs) have achieved impressive progress in text-to-video generation, but their high memory and computational costs hinder practical deployment. Quantization-aware training (QAT) is an effective solution for compressing and accelerating advanced generative models without runtime overhead at inference. However, existing QAT methods suffer from a distinctive challenge in VDMs: while they often preserve prompt semantics, global layout, and coarse motion, the quantized model severely degrades visual details, texture fidelity, and sharpness. In this paper, we trace this degra

Read original source ↗ Open in workspace

recordType

paper

region

Global