Related papers: FlowAR: Scale-wise Autoregressive Image Generation…

Autoregressive models, often built on Transformer architectures, represent a powerful paradigm for generating ultra-long videos by synthesizing content in sequential chunks. However, this sequential generation process is notoriously slow.…

We investigate the fundamental limits of transformer-based foundation models, extending our analysis to include Visual Autoregressive (VAR) transformers. VAR represents a big step toward generating images using a novel, scalable,…

Inspired by the remarkable success of autoregressive models in language modeling, this paradigm has been widely adopted in visual generation. However, the sequential token-by-token decoding mechanism inherent in traditional autoregressive…

Autoregressive (AR) models have achieved state-of-the-art performance in text and image generation but suffer from slow generation due to the token-by-token process. We ask an ambitious question: can a pre-trained AR model be adapted 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…

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…

While inference-time scaling has significantly enhanced generative quality in large language and diffusion models, its application to vector-quantized (VQ) visual autoregressive modeling (VAR) remains unexplored. We introduce VAR-Scaling,…

Flow matching is a recent framework to train generative models that exhibits impressive empirical performance while being relatively easier to train compared with diffusion-based models. Despite its advantageous properties, prior methods…

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…

The current conditional autoregressive image generation methods have shown promising results, yet their potential remains largely unexplored in the practical unsupervised image translation domain, which operates without explicit…

Visual Autoregressive (VAR) models have recently garnered significant attention for their innovative next-scale prediction paradigm, offering notable advantages in both inference efficiency and image quality compared to traditional…

Autoregressive models for video generation typically operate frame-by-frame, extending next-token prediction from language to video's temporal dimension. We question that unlike word as token is universally agreed in language if frame is a…

Visual Autoregressive (VAR) models have emerged as a powerful paradigm for image synthesis by performing hierarchical next-scale prediction. However, VAR models are inherently prone to cascading error propagation, where subtle coarse-scale…

Flow-based generative models are an important class of exact inference models that admit efficient inference and sampling for image synthesis. Owing to the efficiency constraints on the design of the flow layers, e.g. split coupling flow…

Current feed-forward 3D/4D reconstruction systems rely on dense geometry and pose supervision -- expensive to obtain at scale and particularly scarce for dynamic real-world scenes. We present Flow3r, a framework that augments visual…

Autoregressive (AR) language models generate text one token at a time, which limits their inference speed. Diffusion-based language models offer a promising alternative, as they can decode multiple tokens in parallel. However, we identify a…

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…

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…

Coarse-to-fine autoregressive modeling has recently shown strong promise for visuomotor policy learning, combining the inference efficiency of autoregressive methods with the global trajectory coherence of diffusion-based policies. However,…

While inference-time scaling through search has revolutionized Large Language Models, translating these gains to image generation has proven difficult. Recent attempts to apply search strategies to continuous diffusion models show limited…