Related papers: Visual Disentangled Diffusion Autoencoders: Scalab…

Disentangled and interpretable latent representations in generative models typically come at the cost of generation quality. The $\beta$-VAE framework introduces a hyperparameter $\beta$ to balance disentanglement and reconstruction…

The goal of a classification model is to assign the correct labels to data. In most cases, this data is not fully described by the given set of labels. Often a rich set of meaningful concepts exist in the domain that can much more precisely…

Predicting cellular responses to various perturbations is a critical focus in drug discovery and personalized therapeutics, with deep learning models playing a significant role in this endeavor. Single-cell datasets contain technical…

Existing unlearning algorithms in text-to-image generative models often fail to preserve the knowledge of semantically related concepts when removing specific target concepts: a challenge known as adjacency. To address this, we propose FADE…

Deep Learning has become a very valuable tool in different fields, and no one doubts the learning capacity of these models. Nevertheless, since Deep Learning models are often seen as black boxes due to their lack of interpretability, there…

Complex physical systems, from supersonic turbulence to the macroscopic structure of the universe, are governed by continuous multiscale dynamics. While modern machine learning architectures excel at mapping the high-dimensional observables…

With the explosion of graph-structured data, link prediction has emerged as an increasingly important task. Embedding methods for link prediction utilize neural networks to generate node embeddings, which are subsequently employed to…

Vector Quantized-Variational AutoEncoders (VQ-VAE) are generative models based on discrete latent representations of the data, where inputs are mapped to a finite set of learned embeddings.To generate new samples, an autoregressive prior…

We introduce a novel semi-supervised Graph Counterfactual Explainer (GCE) methodology, Dynamic GRAph Counterfactual Explainer (DyGRACE). It leverages initial knowledge about the data distribution to search for valid counterfactuals while…

We present a new generative autoencoder model with dual contradistinctive losses to improve generative autoencoder that performs simultaneous inference (reconstruction) and synthesis (sampling). Our model, named dual contradistinctive…

Recent advancements in diffusion models have enabled the generation of realistic deepfakes from textual prompts in natural language. While these models have numerous benefits across various sectors, they have also raised concerns about the…

Latent generative modeling, where a pretrained autoencoder maps pixels into a latent space for the diffusion process, has become the standard strategy for Diffusion Transformers (DiT); however, the autoencoder component has barely evolved.…

Due to the high potential for abuse of GenAI systems, the task of detecting synthetic images has recently become of great interest to the research community. Unfortunately, existing image-space detectors quickly become obsolete as new…

Learning robust representations of authorial style is crucial for authorship attribution and AI-generated text detection. However, existing methods often struggle with content-style entanglement, where models learn spurious correlations…

Due to their powerful image generation capabilities, diffusion-based adversarial example generation methods through image editing are rapidly gaining popularity. However, due to reliance on the discriminative capability of the diffusion…

Imbalanced distribution learning is a common and significant challenge in predictive modeling, often reducing the performance of standard algorithms. Although various approaches address this issue, most are tailored to classification…

Counterfactual explanations play a pivotal role in explainable artificial intelligence (XAI) by offering intuitive, human-understandable alternatives that elucidate machine learning model decisions. Despite their significance, existing…

Representation Autoencoders (RAEs) leverage frozen vision foundation models (VFMs) as tokenizer encoders, providing robust high-level representations that facilitate fast convergence and high-quality generation in latent diffusion models.…

Counterfactual image generation presents significant challenges, including preserving identity, maintaining perceptual quality, and ensuring faithfulness to an underlying causal model. While existing auto-encoding frameworks admit semantic…

Unlearning specific concepts in text-to-image diffusion models has become increasingly important for preventing undesirable content generation. Among prior approaches, sparse autoencoder (SAE)-based methods have attracted attention due to…