相关论文: RandAR: Decoder-only Autoregressive Visual Generat…

In autoregressive (AR) image generation, visual tokenizers compress images into compact discrete latent tokens, enabling efficient training of downstream autoregressive models for visual generation via next-token prediction. While scaling…

We present Spanning Tree Autoregressive (STAR) modeling, which can incorporate prior knowledge of images, such as center bias and locality, to maintain sampling performance while also providing sufficiently flexible sequence orders to…

Autoregressive (AR) diffusion offers a promising framework for generating videos of theoretically infinite length. However, a major challenge is maintaining temporal continuity while preventing the progressive quality degradation caused by…

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…

Existing vector quantization (VQ) based autoregressive models follow a two-stage generation paradigm that first learns a codebook to encode images as discrete codes, and then completes generation based on the learned codebook. However, they…

Diffusion language models hold the promise of fast parallel generation, while autoregressive (AR) models typically excel in quality due to their causal structure aligning naturally with language modeling. This raises a fundamental question:…

Autoregressive (AR) visual generation relies on tokenizers to map images to and from discrete sequences. However, tokenizers are trained to reconstruct clean images from ground-truth tokens, while AR generators are optimized only for token…

We introduce Causal Diffusion as the autoregressive (AR) counterpart of Diffusion models. It is a next-token(s) forecasting framework that is friendly to both discrete and continuous modalities and compatible with existing next-token…

Diffusion models have become the dominant approach for visual generation. They are trained by denoising a Markovian process which gradually adds noise to the input. We argue that the Markovian property limits the model's ability to fully…

We introduce Autoregressive Retrieval Augmentation (AR-RAG), a novel paradigm that enhances image generation by autoregressively incorporating knearest neighbor retrievals at the patch level. Unlike prior methods that perform a single,…

Most of the recent generative image super-resolution (SR) methods rely on adapting large text-to-image (T2I) diffusion models pretrained on web-scale text-image data. While effective, this paradigm starts from a generic T2I generator,…

In this paper, we treat the image generation task using an autoencoder, a representative latent model. Unlike many studies regularizing the latent variable's distribution by assuming a manually specified prior, we approach the image…

We study the problem of self-supervised structured representation learning using autoencoders for downstream tasks such as generative modeling. Unlike most methods which rely on matching an arbitrary, relatively unstructured, prior…

This paper addresses a practical task: High-Resolution Image Anomaly Detection (HRIAD). In comparison to conventional image anomaly detection for low-resolution images, HRIAD imposes a heavier computational burden and necessitates superior…

In the rapidly advancing field of image generation, Visual Auto-Regressive (VAR) modeling has garnered considerable attention for its innovative next-scale prediction approach. This paradigm offers substantial improvements in efficiency,…

Removing modeling constraints and unifying architectures across domains has been a key driver of the recent progress in training large multimodal models. However, most of these models still rely on many separately trained components such as…

Diffusion models have gained significant attention in the realm of image generation due to their exceptional performance. Their success has been recently expanded to text generation via generating all tokens within a sequence concurrently.…

Synthesizing natural human motions that enable a 3D human avatar to walk and reach for arbitrary goals in 3D space remains an unsolved problem with many applications. Existing methods (data-driven or using reinforcement learning) are…

Inspired by the success of self-supervised autoregressive representation learning in natural language (GPT and its variants), and advances in recent visual architecture design with Vision Transformers (ViTs), in this paper, we explore the…

Conditional visual generation has witnessed remarkable progress with the advent of diffusion models (DMs), especially in tasks like control-to-image generation. However, challenges such as expensive computational cost, high inference…