Article-Journal

ZipAR: Accelerating Autoregressive Image Generation through Spatial Locality

ZipVL: Efficient Large Vision-Language Models with Dynamic Token Sparsification and KV Cache Compression

ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification

MiniCache: KV Cache Compression in Depth Dimension for Large Language Models

Paragraph-to-image generation with information-enriched diffusion model

Ptqd: Accurate post-training quantization for diffusion models

Datasetdm: Synthesizing data with perception annotations using diffusion models

Binarizing by classification: Is soft function really necessary?