Xiaolan Ke
YOU?
Author Swipe
View article: GAN-Prototype: Generative Adversarial Networks for Rapid UX Prototype Generation
GAN-Prototype: Generative Adversarial Networks for Rapid UX Prototype Generation Open
Generative Adversarial Networks (GANs) have shown remarkable potential in various domains, and their application in user experience (UX) design offers a transformative approach. In this paper, we present GAN-Prototype, a novel framework de…
View article: DP-MemArc: Differential Privacy Transfer Learning for Memory Efficient Language Models
DP-MemArc: Differential Privacy Transfer Learning for Memory Efficient Language Models Open
Large language models have repeatedly shown outstanding performance across diverse applications. However, deploying these models can inadvertently risk user privacy. The significant memory demands during training pose a major challenge in …
View article: Enhancing Gastrointestinal Diagnostics with YOLO-Based Deep Learning Techniques
Enhancing Gastrointestinal Diagnostics with YOLO-Based Deep Learning Techniques Open
Gastrointestinal (GI) tract disorders, ranging from benign polyps to aggressive forms of cancer, pose significant health challenges globally. Early detection and precise classification of these conditions are crucial for effective treatmen…
View article: Enhancing Gastrointestinal Diagnostics with YOLO-Based Deep Learning Techniques
Enhancing Gastrointestinal Diagnostics with YOLO-Based Deep Learning Techniques Open
Gastrointestinal (GI) tract disorders, ranging from benign polyps to aggressive forms of cancer, pose significant health challenges globally. Early detection and precise classification of these conditions are crucial for effective treatmen…
View article: Baechi: Fast Device Placement of Machine Learning Graphs
Baechi: Fast Device Placement of Machine Learning Graphs Open
Machine Learning graphs (or models) can be challenging or impossible to train when either devices have limited memory, or models are large. To split the model across devices, learning-based approaches are still popular. While these result …