paper-with-me

홈 › Papers

Frequency Autoregressive Image Generation with Continuous Tokens

2025-03-07 · Hu Yu, Hao Luo, Hangjie Yuan, Yu Rong, Feng Zhao

Autoregressive (AR) models for image generation typically adopt a two-stage paradigm of vector quantization and raster-scan ``next-token prediction", inspired by its great success in language modeling. However, due to the huge modality gap, image autoregressive models may require a systematic reevaluation from two perspectives: tokenizer format and regression direction. In this paper, we introduce the frequency progressive autoregressive (\textbf{FAR}) paradigm and instantiate FAR with the continuous tokenizer. Specifically, we identify spectral dependency as the desirable regression direction for FAR, wherein higher-frequency components build upon the lower one to progressively construct a complete image. This design seamlessly fits the causality requirement for autoregressive models and preserves the unique spatial locality of image data. Besides, we delve into the integration of FAR and the continuous tokenizer, introducing a series of techniques to address optimization challenges and improve the efficiency of training and inference processes. We demonstrate the efficacy of FAR through comprehensive experiments on the ImageNet dataset and verify its potential on text-to-image generation.

📄 PDF Abstract BibTeX arXiv:2503.05305

Code (0)

등록된 구현이 없습니다.

Tasks

Image GenerationLanguage ModelingLanguage ModellingQuantizationregressionText to Image GenerationText-to-Image Generation

Methods 이 논문이 사용한 방법론

ADOPT Please enter a description about the method here

Similar Papers 제목 키워드 기반

NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale

2025-08-14 · NextStep Team, Chunrui Han, Guopeng Li, Jingwei Wu 외 arxiv

Prevailing autoregressive (AR) models for text-to-image generation either rely on heavy, computationally-intensive diffusion models to process continuous image tokens, or employ vector quantization (VQ) to obtain discret…

Text-to-Image GenerationImage Editing

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis

2025-07-02 · Peng Zheng, Junke Wang, Yi Chang, Yizhou Yu 외

Recent advances in large language models (LLMs) have spurred interests in encoding images as discrete tokens and leveraging autoregressive (AR) frameworks for visual generation. However, the quantization process in AR-ba…

Density EstimationImage GenerationQuantization

MixAR: Mixture Autoregressive Image Generation

2025-11-15 · Jinyuan Hu, Jiayou Zhang, Shaobo Cui, Kun Zhang 외 arxiv

Autoregressive (AR) approaches, which represent images as sequences of discrete tokens from a finite codebook, have achieved remarkable success in image generation. However, the quantization process and the limited codeb…

Computational EfficiencyImage Generation

Unified Autoregressive Visual Generation and Understanding with Continuous Tokens

2025-03-17 · Lijie Fan, Luming Tang, Siyang Qin, Tianhong Li 외

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 input…

Image CaptioningImage GenerationQuestion Answering

Bridging Continuous and Discrete Tokens for Autoregressive Visual Generation

2025-03-20 · Yuqing Wang, Zhijie Lin, Yao Teng, Yuanzhi Zhu 외

Autoregressive visual generation models typically rely on tokenizers to compress images into tokens that can be predicted sequentially. A fundamental dilemma exists in token representation: discrete tokens enable straigh…

Quantization