Related papers: Towards Accurate Image Coding: Improved Autoregres…

Although deep convolutional neural network has been proved to efficiently eliminate coding artifacts caused by the coarse quantization of traditional codec, it's difficult to train any neural network in front of the encoder for gradient's…

Learning interpretable representations of data remains a central challenge in deep learning. When training a deep generative model, the observed data are often associated with certain categorical labels, and, in parallel with learning to…

Generating high-quality Scalable Vector Graphics (SVGs) from text remains a significant challenge. Existing LLM-based models that generate SVG code as a flat token sequence struggle with poor structural understanding and error accumulation,…

Learning discrete representations with vector quantization (VQ) has emerged as a powerful approach in various generative models. However, most VQ-based models rely on a single, fixed-rate codebook, requiring extensive retraining for new…

Variational Autoencoders (VAEs) provide a theoretically-backed and popular framework for deep generative models. However, learning a VAE from data poses still unanswered theoretical questions and considerable practical challenges. In this…

Graph self-supervised learning has gained significant attention recently. However, many existing approaches heavily depend on perturbations, and inappropriate perturbations may corrupt the graph's inherent information. The Vector Quantized…

Variational Convertor-Encoder (VCE) converts an image to various styles; we present this novel architecture for the problem of one-shot generalization and its transfer to new tasks not seen before without additional training. We also…

Recent advances in video generation have been dominated by diffusion and flow-matching models, which produce high-quality results but remain computationally intensive and difficult to scale. In this work, we introduce VideoAR, the first…

We propose TC-AE, a ViT-based architecture for deep compression autoencoders. Existing methods commonly increase the channel number of latent representations to maintain reconstruction quality under high compression ratios. However, this…

This thesis is a proof of concept for the potential of Variational Auto-Encoder (VAE) on representation learning of real-world Knowledge Graphs (KG). Inspired by successful approaches to the generation of molecular graphs, we evaluate the…

Vector-quantized variational autoencoders (VQ-VAEs) are central to models that rely on high reconstruction fidelity, from neural compression to generative pipelines. Hierarchical extensions, such as VQ-VAE2, are often credited with superior…

Image tokenization plays a central role in modern generative modeling by mapping visual inputs into compact representations that serve as an intermediate signal between pixels and generative models. Diffusion-based decoders have recently…

While latent diffusion models achieve impressive image editing results, their application to iterative editing of the same image is severely restricted. When trying to apply consecutive edit operations using current models, they accumulate…

We propose an out-of-distribution detection method that combines density and restoration-based approaches using Vector-Quantized Variational Auto-Encoders (VQ-VAEs). The VQ-VAE model learns to encode images in a categorical latent space.…

Most 3D scene generation methods are limited to only generating object bounding box parameters while newer diffusion methods also generate class labels and latent features. Using object size or latent feature, they then retrieve objects…

The vector quantization is a widely used method to map continuous representation to discrete space and has important application in tokenization for generative mode, bottlenecking information and many other tasks in machine learning. Vector…

Deep generative models applied to audio have improved by a large margin the state-of-the-art in many speech and music related tasks. However, as raw waveform modelling remains an inherently difficult task, audio generative models are either…

Generative modeling of high-dimensional data is a key problem in machine learning. Successful approaches include latent variable models and autoregressive models. The complementary strengths of these approaches, to model global and local…

Ultra-high-definition (UHD) image restoration often faces computational bottlenecks and information loss due to its extremely high resolution. Existing studies based on Variational Autoencoders (VAE) improve efficiency by transferring the…

Visual tokenizers are pivotal in multimodal large models, acting as bridges between continuous inputs and discrete tokens. Nevertheless, training high-compression-rate VQ-VAEs remains computationally demanding, often necessitating thousands…