Related papers: FlexVAR: Flexible Visual Autoregressive Modeling w…

This paper presents a novel approach that enables autoregressive video generation with high efficiency. We propose to reformulate the video generation problem as a non-quantized autoregressive modeling of temporal frame-by-frame prediction…

Autoregressive visual generation has garnered increasing attention due to its scalability and compatibility with other modalities compared with diffusion models. Most existing methods construct visual sequences as spatial patches for…

Despite rapid progress in autonomous driving, reliable training and evaluation of driving systems remain fundamentally constrained by the lack of scalable and interactive simulation environments. Recent generative video models achieve…

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 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 and diffusion models drive the recent breakthroughs on text-to-image generation. Despite their huge success of generating high-realistic images, a common shortcoming of these models is their high inference latency -…

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.…

Effective and generalizable control in video generation remains a significant challenge. While many methods rely on ambiguous or task-specific signals, we argue that a fundamental disentanglement of "appearance" and "motion" provides a more…

Autoregressive models have emerged as a powerful approach for visual generation but suffer from slow inference speed due to their sequential token-by-token prediction process. In this paper, we propose a simple yet effective approach for…

Visual autoregressive models typically adhere to a raster-order ``next-token prediction" paradigm, which overlooks the spatial and temporal locality inherent in visual content. Specifically, visual tokens exhibit significantly stronger…

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…

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…

Building on the success of diffusion models in visual generation, flow-based models reemerge as another prominent family of generative models that have achieved competitive or better performance in terms of both visual quality and inference…

Nature is infinitely resolution-free. In the context of this reality, existing diffusion models, such as Diffusion Transformers, often face challenges when processing image resolutions outside of their trained domain. To overcome this…

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…

Most recent real-world image super-resolution (Real-ISR) methods employ pre-trained text-to-image (T2I) diffusion models to synthesize the high-quality image either from random Gaussian noise, which yields realistic results but is slow due…

Recently, Visual Autoregressive ($\mathsf{VAR}$) Models introduced a groundbreaking advancement in the field of image generation, offering a scalable approach through a coarse-to-fine ``next-scale prediction'' paradigm. Suppose that $n$…

We present Reversible Vision Transformers, a memory efficient architecture design for visual recognition. By decoupling the GPU memory requirement from the depth of the model, Reversible Vision Transformers enable scaling up architectures…

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…

We present Infinity, a Bitwise Visual AutoRegressive Modeling capable of generating high-resolution, photorealistic images following language instruction. Infinity redefines visual autoregressive model under a bitwise token prediction…