Survey of Likelihood-based Generative Models Keyword: VAE, Normalizing Flows, Neural ODE, Energy-based Models, Diffusion Models, Score Models, Schrodinger Bridge, Rectified Flows, Flow Models, Consistency Models, Flow Map Models, Distribution Matching Distillation, Drifting Models Abstract

아래 글은 비공식적인 개인의 사견임을 밝힌다. VALL-E and residual quantization. Keyword: VALL-E, EnCodec, Residual Quantization, DDPM, Diffusion Introduction

아래 글은 비공식적인 개인의 사견임을 밝힌다. Essay of generative models, Mode coverage Keyword: Excplicit, Implicit modeling, Contrastive learning Introduction

David Bau et al., 2020, arXiv Keyword: Generative, Adversarial learning Problem: How to manipulate specific rules encoded by a deep generative model.

Stanislav Pidhorskyi et al., 2020, arXiv Keyword: Generative, Adversarial learning Problem: AE based approach has poor quality of output distribution.