Learning to Expand Images for Efficient Visual Autoregressive Modeling

2025-11-19

AI Summary

Existing autoregressive vision generation models suffer from inefficiency in token-by-token decoding or complexity in multi-scale modeling. This paper proposes Expanding Autoregressive Representation (EAR), a novel framework inspired by human centric-outward visual perception, which employs a spiral token expansion order to explicitly model spatial continuity. EAR integrates parallel autoregressive decoding with a length-adaptive mechanism that dynamically adjusts the number of tokens predicted per step—thereby jointly optimizing generation quality, inference speed, and perceptual relevance. Experiments on ImageNet demonstrate that EAR achieves, for the first time within a single-scale autoregressive framework, a Pareto-optimal trade-off between synthesis fidelity and inference efficiency, significantly outperforming state-of-the-art methods. This work establishes a new paradigm for efficient, scalable, and cognitively aligned autoregressive visual modeling.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Deep Generative Models & Autoencoders
• Natural Language Processing: Generation

Application Category

• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Autoregressive models have recently shown great promise in visual generation by leveraging discrete token sequences akin to language modeling. However, existing approaches often suffer from inefficiency, either due to token-by-token decoding or the complexity of multi-scale representations. In this work, we introduce Expanding Autoregressive Representation (EAR), a novel generation paradigm that emulates the human visual system's center-outward perception pattern. EAR unfolds image tokens in a spiral order from the center and progressively expands outward, preserving spatial continuity and enabling efficient parallel decoding. To further enhance flexibility and speed, we propose a length-adaptive decoding strategy that dynamically adjusts the number of tokens predicted at each step. This biologically inspired design not only reduces computational cost but also improves generation quality by aligning the generation order with perceptual relevance. Extensive experiments on ImageNet demonstrate that EAR achieves state-of-the-art trade-offs between fidelity and efficiency on single-scale autoregressive models, setting a new direction for scalable and cognitively aligned autoregressive image generation.

Problem

• Inefficient token-by-token decoding in visual autoregressive models
• Complexity issues with multi-scale representations in image generation
• Poor alignment between generation order and perceptual relevance patterns

Innovation

• Expanding Autoregressive Representation spiral generation
• Length-adaptive decoding for dynamic token prediction
• Center-outward perception pattern for spatial continuity