Related papers: Universal Approximation of Visual Autoregressive T…

Image generation has advanced rapidly over the past decade, yet the literature seems fragmented across different models and application domains. This paper aims to offer a comprehensive survey of breakthrough image generation models,…

Recent feed-forward models have significantly advanced geometry perception for inferring dense 3D structure from sensor observations. However, its essential capabilities remain fragmented across multiple incompatible paradigms, including…

The Variational Autoencoder (VAE) is a powerful framework for learning probabilistic latent variable generative models. However, typical assumptions on the approximate posterior distribution of the encoder and/or the prior, seriously…

We investigate the universal approximation property (UAP) of transformer-type architectures, providing a unified theoretical framework that extends prior results on residual networks to models incorporating attention mechanisms. Our work…

For autoregressive (AR) modeling of high-resolution images, vector quantization (VQ) represents an image as a sequence of discrete codes. A short sequence length is important for an AR model to reduce its computational costs to consider…

Real-world data is high-dimensional: a book, image, or musical performance can easily contain hundreds of thousands of elements even after compression. However, the most commonly used autoregressive models, Transformers, are prohibitively…

Transformer is eminently suitable for auto-regressive image synthesis which predicts discrete value from the past values recursively to make up full image. Especially, combined with vector quantised latent representation, the…

Visual autoregressive (VAR) models generate images through next-scale prediction, naturally achieving coarse-to-fine, fast, high-fidelity synthesis mirroring human perception. In practice, this hierarchy can drift at inference time, as…

Visual autoregressive (VAR) models have recently emerged as an efficient paradigm for text-to-image generation. Despite their strong generative capability, existing VAR-based personalization methods remain limited to static settings,…

Monocular depth estimation can benefit from autoregressive (AR) generation, but direct AR modeling is hindered by the modality gap between RGB and depth, inefficient pixel-wise generation, and instability in continuous depth prediction. We…

Synthetic Aperture Radar (SAR) offers all-weather, high-resolution imaging capabilities, but its complex imaging mechanism often poses challenges for interpretation. In response to these limitations, this paper introduces an innovative…

We approach instantaneous mapping, converting images to a top-down view of the world, as a translation problem. We show how a novel form of transformer network can be used to map from images and video directly to an overhead map or…

Autoregressive image modeling relies on visual tokenizers to compress images into compact latent representations. We design an end-to-end training pipeline that jointly optimizes reconstruction and generation, enabling direct supervision…

After their initial success in natural language processing, transformer architectures have rapidly gained traction in computer vision, providing state-of-the-art results for tasks such as image classification, detection, segmentation, and…

Generating multi-view images from human instructions is crucial for 3D content creation. The primary challenges involve maintaining consistency across multiple views and effectively synthesizing shapes and textures under diverse conditions.…

Video prediction is an important yet challenging problem; burdened with the tasks of generating future frames and learning environment dynamics. Recently, autoregressive latent video models have proved to be a powerful video prediction…

Real-world perception and interaction are inherently multimodal, encompassing not only language but also vision and speech, which motivates the development of "Omni" MLLMs that support both multimodal inputs and multimodal outputs. While a…

Deep neural networks have achieved substantial success across various scientific computing tasks. A pivotal challenge within this domain is the rapid and parallel approximation of matrix inverses, critical for numerous applications. Despite…

Recently, AutoRegressive (AR) models for the whole image generation empowered by transformers have achieved comparable or even better performance to Generative Adversarial Networks (GANs). Unfortunately, directly applying such AR models to…

Essential to visual generation is efficient modeling of visual data priors. Conventional next-token prediction methods define the process as learning the conditional probability distribution of successive tokens. Recently, next-scale…