Related papers: ARINAR: Bi-Level Autoregressive Feature-by-Feature…
Recently, Vector Quantized AutoRegressive (VQ-AR) models have shown remarkable results in text-to-image synthesis by equally predicting discrete image tokens from the top left to bottom right in the latent space. Although the simple…
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:…
We present BitDance, a scalable autoregressive (AR) image generator that predicts binary visual tokens instead of codebook indices. With high-entropy binary latents, BitDance lets each token represent up to $2^{256}$ states, yielding a…
We introduce DC-AR, a novel masked autoregressive (AR) text-to-image generation framework that delivers superior image generation quality with exceptional computational efficiency. Due to the tokenizers' limitations, prior masked AR models…
We introduce RandAR, a decoder-only visual autoregressive (AR) model capable of generating images in arbitrary token orders. Unlike previous decoder-only AR models that rely on a predefined generation order, RandAR removes this inductive…
AutoRegressive (AR) models have made notable progress in image generation, with Masked AutoRegressive (MAR) models gaining attention for their efficient parallel decoding. However, MAR models have traditionally underperformed when compared…
This paper challenges the dominance of continuous pipelines in visual generation. We systematically investigate the performance gap between discrete and continuous methods. Contrary to the belief that discrete tokenizers are intrinsically…
In the current research landscape, multimodal autoregressive (AR) models have shown exceptional capabilities across various domains, including visual understanding and generation. However, complex tasks such as style-aligned text-to-image…
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…
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…
Recent studies have demonstrated the importance of high-quality visual representations in image generation and have highlighted the limitations of generative models in image understanding. As a generative paradigm originally designed for…
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…
This paper proposes an autoregressive (AR) model for sequences of graphs, which generalises traditional AR models. A first novelty consists in formalising the AR model for a very general family of graphs, characterised by a variable…
Autoregressive (AR) models have achieved remarkable success in natural language and image generation, but their application to 3D shape modeling remains largely unexplored. Unlike diffusion models, AR models enable more efficient and…
Auto-Regressive (AR) models have achieved impressive results in 2D image generation by modeling joint distributions in the grid space. While this approach has been extended to the 3D domain for powerful shape generation, it still has two…
We introduce an efficient, resolution-agnostic autoregressive (AR) image synthesis approach that generalizes to arbitrary resolutions and aspect ratios, narrowing the gap to diffusion models at scale. At its core is VibeToken, a novel…
Autoregressive image generation aims to predict the next token based on previous ones. However, this process is challenged by the bidirectional dependencies inherent in conventional image tokenizations, which creates a fundamental…
In this work, we first revisit the sampling issues in current autoregressive (AR) image generation models and identify that image tokens, unlike text tokens, exhibit lower information density and non-uniform spatial distribution.…
Autoregressive (AR) visual generators model images as sequences of discrete tokens and are trained with a next-token likelihood objective. This strict causal supervision optimizes each step based only on the immediate next token, which can…
Autoregressive models have shown remarkable success in image generation by adapting sequential prediction techniques from language modeling. However, applying these approaches to images requires discretizing continuous pixel data through…