Paper-Conference

CacheQuant: Comprehensively Accelerated Diffusion Models
Diffusion models have gradually gained prominence in the field of image synthesis, showcasing remarkable generative capabilities. …
引用 代码 DOI
K-sort arena: Efficient and reliable benchmarking for generative models via k-wise human preferences
The rapid advancement of visual generative models necessitates efficient and reliable evaluation methods. Arena platform, which gathers …
引用 代码 DOI
I-ViT: Integer-only Quantization for Efficient Vision Transformer Inference
Vision Transformers (ViTs) have achieved state-of-the-art performance on various computer vision applications. However, these models …
引用 代码 DOI