Related papers: Mirai: Autoregressive Visual Generation Needs Fore…

Existing 1D visual tokenizers for autoregressive (AR) generation largely follow the design principles of language modeling, as they are built directly upon transformers whose priors originate in language, yielding single-hierarchy latent…

We present UniFluid, a unified autoregressive framework for joint visual generation and understanding leveraging continuous visual tokens. Our unified autoregressive architecture processes multimodal image and text inputs, generating…

While diffusion models dominate the field of visual generation, they are computationally inefficient, applying a uniform computational effort regardless of different complexity. In contrast, autoregressive (AR) models are inherently…

Text-to-image (T2I) models have achieved remarkable progress, yet they continue to struggle with complex prompts that require simultaneously handling multiple objects, relations, and attributes. Existing inference-time strategies, such as…

Autoregressive (AR) video diffusion has recently emerged as a promising paradigm for long video generation, enabling causal synthesis beyond the limits of bidirectional models. To address training-inference mismatch, a series of…

While most prior work in video generation relies on bidirectional architectures, recent efforts have sought to adapt these models into autoregressive variants to support near real-time generation. However, such adaptations often depend…

In this paper, we propose ZipAR, a training-free, plug-and-play parallel decoding framework for accelerating auto-regressive (AR) visual generation. The motivation stems from the observation that images exhibit local structures, and…

Generative artificial intelligence (AI) technology is revolutionizing the computing industry. Not only its applications have broadened to various sectors but also poses new system design and optimization opportunities. The technology is…

Recent visual autoregressive (AR) models have shown promising capabilities in text-to-image generation, operating in a manner similar to large language models. While test-time computation scaling has brought remarkable success in enabling…

Image Super-Resolution (ISR) has seen significant progress with the introduction of remarkable generative models. However, challenges such as the trade-off issues between fidelity and realism, as well as computational complexity, have also…

As generative models scale to larger inputs across language, vision, and video domains, the cost of token-level computation has become a key bottleneck. While prior work suggests that only a subset of tokens significantly influence…

Discrete autoregressive (AR) text-to-image (T2I) models pair a VQ tokenizer with an AR policy, and current post-training pipelines optimize only the policy while keeping the VQ decoder frozen. Recent diffusion T2I work, exemplified by…

Visual autoregressive models achieve remarkable generation quality through next-scale predictions across multi-scale token pyramids. However, the conventional method uses uniform scale downsampling to build these pyramids, leading to…

Autoregressive models, built based on the Next Token Prediction (NTP) paradigm, show great potential in developing a unified framework that integrates both language and vision tasks. Pioneering works introduce NTP to autoregressive visual…

Video prediction models combined with planning algorithms have shown promise in enabling robots to learn to perform many vision-based tasks through only self-supervision, reaching novel goals in cluttered scenes with unseen objects.…

This paper enhances image-GPT (iGPT), one of the pioneering works that introduce autoregressive pretraining to predict the next pixels for visual representation learning. Two simple yet essential changes are made. First, we shift the…

Numerous efforts have been made to extend the ``next token prediction'' paradigm to visual contents, aiming to create a unified approach for both image generation and understanding. Nevertheless, attempts to generate images through…

Visual generation has witnessed remarkable progress in single-image tasks, yet extending these capabilities to temporal sequences remains challenging. Current approaches either build specialized video models from scratch with enormous…

Autoregressive (AR) models have recently shown strong performance in image generation, where a critical component is the visual tokenizer (VT) that maps continuous pixel inputs to discrete token sequences. The quality of the VT largely…

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…