cs.CVNov 8, 2026

G-STAR: Group-Scaled Token Capacity for Deeply Compressed Autoregressive Generation

Authors: Xu Huang, Ye Huang, Xiaotong Li, Zhengrong Yue, Jialv Zou, Minhao Jing, Haodong Li, Wenhao Yan, 

Organizations: Peking University · Meituan Longcat · Shanghai Jiao Tong University · Huazhong University of Science and Technology · 

Abstract

Discrete autoregressive models offer a scalable framework for image generation. However, they face a fundamental trade-off: long token sequences preserve representation quality but slow generation, while aggressive spatial compression reduces representation capacity. Based on product quantization, we show that, under a fixed nominal information budget, group size should scale quadratically with the per-axis spatial compression factor. Building on this principle, we propose GSTAR, a spatial--group co-scaling framework that enables 32×32\times and even effective 64×64\times compression while preserving strong reconstruction, understanding, and generation performance. Since larger groups introduce intra-group dependencies that must be modeled efficiently, we analyze their impact on inference latency and generation quality and introduce a semi-autoregressive decoder that combines parallel feature computation with lightweight causal modeling. With these designs, our highly compressed models perform competitively with leading models across five representative text-to-image benchmarks (GenEval, DPG-Bench, PRISM, LongText-Bench, and Qwen-Image-Bench). At 1024×10241024\times1024 resolution, our model delivers a 20×20\times speedup over prior discrete autoregressive models, generating each image in 2.5 seconds on a single NVIDIA H200. Together, these results show that highly compressed discrete representations can enable high-quality autoregressive generation at low latency.

Figures & tables

Appendix figures & tables5 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. End-to-End Autoregressive Image Generation with 1D Semantic Tokenizer

    May 1, 2026Wenda Chu, Bingliang Zhang, Jiaqi Han +4Image TokenizationVisual Tokenization

  2. ScalingAR: Scaling Confidence for Autoregressive Image Generation

    Sep 30, 2025Harold Haodong Chen, Xianfeng Wu, Wen-Jie Shu +4Language Model DecodingVisual Autoregressive Models

  3. DC-SAE: Deep Compression Semantic Autoencoder for Faster Diffusion Convergence

    Sep 30, 2026Xu Huang, Ye Huang, Zijun Liao +6AutoencodersDiffusion-Based Image Generation