Generative Autoencoder

Generative autoencoders are neural networks designed to learn compressed representations (latent codes) of input data and then reconstruct the data from these representations, aiming to capture the underlying data distribution. Current research focuses on improving model architectures like variational autoencoders (VAEs) and exploring alternatives such as masked generative autoencoders and those employing invertible layers, often addressing challenges like disentanglement of latent features, robustness to adversarial attacks, and efficient training. These advancements have significant implications for various fields, including image generation, drug discovery, and natural language processing, by enabling improved data generation, manipulation, and analysis.

Papers

October 9, 2024

UniAutoML: A Human-Centered Framework for Unified Discriminative and Generative AutoML with Large Language Models
Jiayi Guo, Zan Chen, Yingrui Ji, Liyun Zhang, Daqin Luo, Zhigang Li, Yiqin Shen
Online autoML Human Centric AutoML System AutoML Framework Generative Autoencoder AutoML Approach Unified Learning

September 2, 2024

Masked Mixers for Language Generation and Retrieval
Benjamin L. Badger
Language Generation App to App Retrieval Causal Language Generative Autoencoder

May 29, 2024

MEGA: Masked Generative Autoencoder for Human Mesh Recovery
Guénolé Fiche, Simon Leglaive, Xavier Alameda-Pineda, Francesc Moreno-Noguer
Generative Modeling Human Mesh Recovery Masked Generative Generative Autoencoder Alignment Distillation Surface Mesh Mesh Segmentation

December 28, 2023

On the rate of convergence of an over-parametrized Transformer classifier learned by gradient descent
Michael Kohler, Adam Krzyzak
Language Model Gradient Descent Early Stage Convergence Transformer Network Universal Rate Generative Autoencoder

December 22, 2023

Latents2Semantics: Leveraging the Latent Space of Generative Models for Localized Style Manipulation of Face Images
Snehal Singh Tomar, A. N. Rajagopalan
Generative Model Latent Space Face Image Latent Direction Generative Autoencoder

October 3, 2023

Generative Autoencoding of Dropout Patterns
Shunta Maeda
Generative Model Supervised Autoencoder Structured Dropout Generative Autoencoder

July 5, 2023

On the Adversarial Robustness of Generative Autoencoders in the Latent Space
Mingfei Lu, Badong Chen
Latent Space Adversarial Robustness Variational Autoencoders Latent Vulnerability Generative Autoencoder

February 23, 2023

Causally Disentangled Generative Variational AutoEncoder
Seunghwan An, Kyungwoo Song, Jong-June Jeon
Variational Autoencoder Causal Disentanglement Generative Autoencoder Supervised Regularization

November 21, 2022

Exploring the Effectiveness of Mask-Guided Feature Modulation as a Mechanism for Localized Style Editing of Real Images
Snehal Singh Tomar, Maitreya Suin, A. N. Rajagopalan
Deep Generative Model Functional Mechanism Real Image Generative Autoencoder Latent Space Manipulation

October 12, 2022

Auto-Encoding Goodness of Fit
Aaron Palmer, Zhiyi Chi, Derek Aguiar, Jinbo Bi
Latent Representation Autoencoder Model Auto Encoders Better FiT Generative Autoencoder

July 14, 2022

Attribute Graphs Underlying Molecular Generative Models: Path to Learning with Limited Data
Samuel C. Hoffman, Payel Das, Karthikeyan Shanmugam, Kahini Wadhawan, Prasanna Sattigeri
Generative Model Causal Graph Limited Data Root to Leaf Path Structural Causal Generative Autoencoder

July 5, 2022

Latents2Segments: Disentangling the Latent Space of Generative Models for Semantic Segmentation of Face Images
Snehal Singh Tomar, A. N. Rajagopalan
Generative Model Semantic Segmentation Fine Grained Latent Space Face Image Latent Structure Generative Autoencoder Face Segmentation Semantic Facial

June 16, 2022

Pythae: Unifying Generative Autoencoders in Python -- A Benchmarking Use Case
Clément Chadebec, Louis J. Vincent, Stéphanie Allassonnière
Variational Autoencoders VAE Model Generative Autoencoder Scenario Based Benchmark

May 19, 2022

Deterministic training of generative autoencoders using invertible layers
Gianluigi Silvestri, Daan Roos, Luca Ambrogioni
Supervised Autoencoder Stochastic Variational Inference Generative Autoencoder Reversible Architecture Deterministic Learner

December 17, 2021

Generation of data on discontinuous manifolds via continuous stochastic non-invertible networks
Mariia Drozdova, Vitaliy Kinakh, Guillaume Quétant, Tobias Golling, Slava Voloshynovskiy
Generative Adversarial Network Raw Data Faithful Generation Variational Autoencoders Latent Space Representation Invertible Network Generative Autoencoder Invertible Generative Model

November 21, 2021

Denoised Internal Models: a Brain-Inspired Autoencoder against Adversarial Attacks
Kaiyuan Liu, Xingyu Li, Yurui Lai, Ge Zhang, Hang Su, Jiachen Wang, Chunxu Guo, Jisong Guan, Yi Zhou
Deep Learning Deep Neural Network Adversarial Attack Autoencoder Based Denoising Model Generative Autoencoder

November 15, 2021

Scalable Variational Quantum Circuits for Autoencoder-based Drug Discovery
Junde Li, Swaroop Ghosh
Variational Autoencoder Quantum Machine Learning Variational Quantum Circuit 3D Molecule Generative Autoencoder