Zhenzhong Xu

Hanwen Chang, Haihao Shen, Yiyang Cai et al.

Diffusion models have gained popularity for generating images from textual descriptions. Nonetheless, the substantial need for computational resources continues to present a noteworthy challenge, contributing to time-consuming processes. Quantization, a technique employed to compress deep learning models for enhanced efficiency, presents challenges when applied to diffusion models. These models are notably more sensitive to quantization compared to other model types, potentially resulting in a degradation of image quality. In this paper, we introduce a novel approach to quantize the diffusion models by leveraging both quantization-aware training and distillation. Our results show the quantized models can maintain the high image quality while demonstrating the inference efficiency on CPUs. The code is publicly available at: https://github.com/intel/intel-extension-for-transformers.

Su Chang, Xu Zhenzhong, Gao Xuan

With the development of the E-commerce and reviews website, the comment information is influencing people's life. More and more users share their consumption experience and evaluate the quality of commodity by comment. When people make a decision, they will refer these comments. The dependency of the comments make the fake comment appear. The fake comment is that for profit and other bad motivation, business fabricate untrue consumption experience and they preach or slander some products. The fake comment is easy to mislead users' opinion and decision. The accuracy of humans identifying fake comment is low. It's meaningful to detect fake comment using natural language processing technology for people getting true comment information. This paper uses the sentimental analysis to detect fake comment.