相关论文: DART: Denoising Autoregressive Transformer for Sca…

In this paper, we explore a new generative approach for learning visual representations. Our method, DARL, employs a decoder-only Transformer to predict image patches autoregressively. We find that training with Mean Squared Error (MSE)…

Self-supervised learning has garnered increasing attention in time series analysis for benefiting various downstream tasks and reducing reliance on labeled data. Despite its effectiveness, existing methods often struggle to comprehensively…

In text generation, models that generate text from scratch one token at a time are currently the dominant paradigm. Despite being performant, these models lack the ability to revise existing text, which limits their usability in many…

Several recent studies have attempted to autoregressively generate continuous speech representations without discrete speech tokens by combining diffusion and autoregressive models, yet they often face challenges with excessive…

Recently, continuous diffusion models (CDM) have been introduced into non-autoregressive (NAR) text-to-text generation. However, the discrete nature of text increases the difficulty of CDM to generate coherent and fluent texts, and also…

We propose a novel Auto-Regressive (AR) image generation approach that models images as hierarchical compositions of interpretable visual layers. While AR models have achieved transformative success in language modeling, replicating this…

Text-conditioned human motion generation, which allows for user interaction through natural language, has become increasingly popular. Existing methods typically generate short, isolated motions based on a single input sentence. However,…

Autoregressive (AR) transformers have emerged as a powerful paradigm for visual generation, largely due to their scalability, computational efficiency and unified architecture with language and vision. Among them, next scale prediction…

We propose Stratified Image Transformer(StraIT), a pure non-autoregressive(NAR) generative model that demonstrates superiority in high-quality image synthesis over existing autoregressive(AR) and diffusion models(DMs). In contrast to the…

Autoregressive models and their sequential factorization of the data likelihood have recently demonstrated great potential for image representation and synthesis. Nevertheless, they incorporate image context in a linear 1D order by…

The field of image synthesis is currently flourishing due to the advancements in diffusion models. While diffusion models have been successful, their computational intensity has prompted the pursuit of more efficient alternatives. As a…

We reinterpret Visual Autoregressive (VAR) models as iterative refinement models to identify which design choices drive their quality-efficiency trade-off. Instead of treating VAR only as next-scale autoregression, we formalise it as a…

We introduce Hybrid Autoregressive Transformer (HART), an autoregressive (AR) visual generation model capable of directly generating 1024x1024 images, rivaling diffusion models in image generation quality. Existing AR models face…

Autoregressive models have demonstrated remarkable success in sequential data generation, particularly in NLP, but their extension to continuous-domain image generation presents significant challenges. Recent work, the masked autoregressive…

We present DiffusionBERT, a new generative masked language model based on discrete diffusion models. Diffusion models and many pre-trained language models have a shared training objective, i.e., denoising, making it possible to combine the…

The content-agnostic, fixed-grid tokenizers used by standard large-scale vision models like Vision Transformer (ViT) and Vision Mamba (Vim) represent a fundamental performance bottleneck, creating a trade-off between capturing fine-grained…

This paper presents Diffusion via Autoregressive models (D-AR), a new paradigm recasting the image diffusion process as a vanilla autoregressive procedure in the standard next-token-prediction fashion. We start by designing the tokenizer…

Diffusion models have achieved state-of-the-art synthesis quality on both visual and audio tasks, and recent works further adapt them to textual data by diffusing on the embedding space. In this paper, we conduct systematic studies of the…

Latent Diffusion Models (LDMs) are generally trained at fixed resolutions, limiting their capability when scaling up to high-resolution images. While training-based approaches address this limitation by training on high-resolution datasets,…

We introduce TransDiff, the first image generation model that marries Autoregressive (AR) Transformer with diffusion models. In this joint modeling framework, TransDiff encodes labels and images into high-level semantic features and employs…