Related papers: Entropic Auto-Encoding via Implicit Free-Energy Mi…

Early detection of Barrett's Esophagus (BE), the only known precursor to Esophageal adenocarcinoma (EAC), is crucial for effectively preventing and treating esophageal cancer. In this work, we investigate the potential of geometric…

There have been many recent advances in representation learning; however, unsupervised representation learning can still struggle with model identification issues related to rotations of the latent space. Variational Auto-Encoders (VAEs)…

Current state-of-the-art generative approaches frequently rely on a two-stage training procedure, where an autoencoder (often a VAE) first performs dimensionality reduction, followed by training a generative model on the learned latent…

Modern visual world modeling systems increasingly rely on high-capacity architectures and large-scale data to produce plausible motion, yet they often fail to preserve underlying 3D geometry or physically consistent camera dynamics. A key…

Variational Autoencoders (VAEs) are powerful generative models that have been widely used in various fields, including image and text generation. However, one of the known challenges in using VAEs is the model's sensitivity to its…

In this tutorial, we explore Variational Autoencoders (VAEs), an essential framework for unsupervised learning, particularly suited for high-dimensional datasets such as neuroimaging. By integrating deep learning with Bayesian inference,…

Latent generative models have emerged as a leading approach for high-quality image synthesis. These models rely on an autoencoder to compress images into a latent space, followed by a generative model to learn the latent distribution. We…

Learning useful representations without supervision remains a key challenge in machine learning. In this paper, we propose a simple yet powerful generative model that learns such discrete representations. Our model, the Vector…

VAEs (Variational AutoEncoders) have proved to be powerful in the context of density modeling and have been used in a variety of contexts for creative purposes. In many settings, the data we model possesses continuous attributes that we…

Imitation learning is an intuitive approach for teaching motion to robotic systems. Although previous studies have proposed various methods to model demonstrated movement primitives, one of the limitations of existing methods is that the…

Syntactic information contains structures and rules about how text sentences are arranged. Incorporating syntax into text modeling methods can potentially benefit both representation learning and generation. Variational autoencoders (VAEs)…

Purpose: Handling heterogeneous and mixed data types has become increasingly critical with the exponential growth in real-world databases. While deep generative models attempt to merge diverse data views into a common latent space, they…

The latent space of generative modeling is long dominated by the VAE encoder. The latents from the pretrained representation encoders (e.g., DINO, SigLIP, MAE) are previously considered inappropriate for generative modeling. Recently, RAE…

In this thesis, we develop methods to enhance the interpretability of recent representation learning techniques in natural language processing (NLP) while accounting for the unavailability of annotated data. We choose to leverage…

Despite advancements in Autoencoders (AEs) for tasks like dimensionality reduction, representation learning and data generation, they remain vulnerable to adversarial attacks. Variational Autoencoders (VAEs), with their probabilistic…

We propose a new concept of rateless auto-encoders (RL-AEs) that enable a flexible latent dimensionality, which can be seamlessly adjusted for varying distortion and dimensionality requirements. In the proposed RL-AEs, instead of a…

Variational autoencoders employ an amortized inference model to approximate the posterior of latent variables. However, such amortized variational inference faces two challenges: (1) the limited posterior expressiveness of fully-factorized…

In variational autoencoders (VAEs), the variational posterior often collapses to the prior, known as posterior collapse, which leads to poor representation learning quality. An adjustable hyperparameter beta has been introduced in VAEs to…

Learning a robust video Variational Autoencoder (VAE) is essential for reducing video redundancy and facilitating efficient video generation. Directly applying image VAEs to individual frames in isolation can result in temporal…

Probabilistic generative models are attractive for scientific modeling because their inferred parameters can be used to generate hypotheses and design experiments. This requires that the learned model provide an accurate representation of…