IEEE

Monolithically Integrated GaN Gate Drivers– A Design Guide

Abstract: In recent years, an increasing trend towards GaN integration can be observed, enabled by the lateral structure of the GaN technology. A key improvement over a discrete implementation is the ...
IEEE

ASM GaN: Industry Standard Model for GaN RF and Power Devices—Part 1: DC, CV, and RF Model

Abstract: We present the latest developments in Advance SPICE Model for GaN (ASM GaN) HEMTs in this paper. The ASM GaN model has been recently selected as an industry-standard compact model for GaN ...
GitHub

MI-GAN: A Simple Baseline for Image Inpainting on Mobile Devices

Our method MI-GAN can produce plausible results both on complex scene images as well as on face images. The bubble chart on the right shows the advantage of our network over state-of-the-art ...
GitHub

COT-GAN: Generating Sequential Data via Causal Optimal Transport

COT-GAN is an adversarial algorithm to train implicit generative models optimized for producing sequential data. The loss function of this algorithm is formulated using ideas from Causal Optimal ...
www.cs.cmu.edu

Ensembling Off-the-shelf Models for GAN Training

The advent of large-scale training has produced a cornucopia of powerful visual recognition models. However, generative models, such as GANs, have traditionally been trained from scratch in an ...