Latent Space

Latent space refers to a lower-dimensional representation of high-dimensional data, aiming to capture essential features while reducing computational complexity and improving interpretability. Current research focuses on developing efficient algorithms and model architectures, such as variational autoencoders (VAEs), generative adversarial networks (GANs), and diffusion models, to learn and manipulate these latent spaces for tasks ranging from anomaly detection and image generation to controlling generative models and improving the efficiency of autonomous systems. This work has significant implications across diverse fields, enabling advancements in areas like drug discovery, autonomous driving, and cybersecurity through improved data analysis, model efficiency, and enhanced control over generative processes.

Papers

August 8, 2022

Adversarial robustness of VAEs through the lens of local geometry
Asif Khan, Amos Storkey
Latent Space Adversarial Robustness Variational Autoencoder Variational Autoencoders Camera Lens Local Geometry Unsupervised Anomaly

August 7, 2022

Hierarchical Semantic Regularization of Latent Spaces in StyleGANs
Tejan Karmali, Rishubh Parihar, Susmit Agrawal, Harsh Rangwani, Varun Jampani, Maneesh Singh, R. Venkatesh Babu
Latent Space GAN Model StyleGAN Latent Style Vector Hierarchical Regularisation

August 4, 2022

Embedding Alignment for Unsupervised Federated Learning via Smart Data Exchange
Satyavrat Wagle, Seyyedali Hosseinalipour, Naji Khosravan, Mung Chiang, Christopher G. Brinton
Contrastive Learning Latent Space Alignment Problem Ad Hoc Unsupervised Federated Learning

August 1, 2022

Composable Text Controls in Latent Space with ODEs
Guangyi Liu, Zeyu Feng, Yuan Gao, Zichao Yang, Xiaodan Liang, Junwei Bao, Xiaodong He, Shuguang Cui, Zhen Li, Zhiting Hu
Language Model Latent Space Ordinary Differential Equation Latent Vector Text Sequence Text Control

July 29, 2022

Content-Aware Differential Privacy with Conditional Invertible Neural Networks
Malte Tölle, Ullrich Köthe, Florian André, Benjamin Meder, Sandy Engelhardt
Differential Privacy Latent Space Privacy Preserving Image Invertible Neural Network Conditional Invertible Neural Network

July 27, 2022

ShAPO: Implicit Representations for Multi-Object Shape, Appearance, and Pose Optimization
Muhammad Zubair Irshad, Sergey Zakharov, Rares Ambrus, Thomas Kollar, Zsolt Kira, Adrien Gaidon
Latent Space Object Detection Object Shape Object Representation Implicit Representation Object Centric Subject Appearance Fusion SHAP Pose Optimization

July 26, 2022

July 23, 2022

Tensor-based Multi-view Spectral Clustering via Shared Latent Space
Qinghua Tao, Francesco Tonin, Panagiotis Patrinos, Johan A. K. Suykens
Latent Space Multi View Kernel Principal Component Analysis Tensor Clustering

July 21, 2022

Unveiling the Latent Space Geometry of Push-Forward Generative Models
Thibaut Issenhuth, Ugo Tanielian, Jérémie Mary, David Picard
Generative Model Generative Adversarial Network Latent Space Probabilistic Generative Model Latent Geometry

July 20, 2022

July 19, 2022

July 15, 2022

Outcome-Guided Counterfactuals for Reinforcement Learning Agents from a Jointly Trained Generative Latent Space
Eric Yeh, Pedro Sequeira, Jesse Hostetler, Melinda Gervasio
Reinforcement Learning Latent Space Variational Autoencoder Reinforcement Learning Agent Counterfactual Example Consistent Counterfactuals Latent Space Interpolation

July 14, 2022

Comparing the latent space of generative models
Andrea Asperti, Valerio Tonelli
Generative Model Latent Space Disentanglement Capability

July 8, 2022

UDRN: Unified Dimensional Reduction Neural Network for Feature Selection and Feature Projection
Zelin Zang, Yongjie Xu, Linyan Lu, Yulan Geng, Senqiao Yang, Stan Z. Li
Latent Space Feature Selection Manifold Learning High Dimensional Data Dimension Reduction Projection Domain

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

Latent Space

Papers

Adversarial robustness of VAEs through the lens of local geometry

Hierarchical Semantic Regularization of Latent Spaces in StyleGANs

Embedding Alignment for Unsupervised Federated Learning via Smart Data Exchange

Composable Text Controls in Latent Space with ODEs

Content-Aware Differential Privacy with Conditional Invertible Neural Networks

ShAPO: Implicit Representations for Multi-Object Shape, Appearance, and Pose Optimization

Generalized Probabilistic U-Net for medical image segementation

Advanced Conditional Variational Autoencoders (A-CVAE): Towards interpreting open-domain conversation generation via disentangling latent feature representation

Tensor-based Multi-view Spectral Clustering via Shared Latent Space

Unveiling the Latent Space Geometry of Push-Forward Generative Models

Structural Causal 3D Reconstruction

Semantic uncertainty intervals for disentangled latent spaces

Everything is There in Latent Space: Attribute Editing and Attribute Style Manipulation by StyleGAN Latent Space Exploration

Interpreting Latent Spaces of Generative Models for Medical Images using Unsupervised Methods

Multimodal hierarchical Variational AutoEncoders with Factor Analysis latent space

Expert-LaSTS: Expert-Knowledge Guided Latent Space for Traffic Scenarios

Outcome-Guided Counterfactuals for Reinforcement Learning Agents from a Jointly Trained Generative Latent Space

Comparing the latent space of generative models

UDRN: Unified Dimensional Reduction Neural Network for Feature Selection and Feature Projection

Latents2Segments: Disentangling the Latent Space of Generative Models for Semantic Segmentation of Face Images