2026-11-13 · America/Los_Angeles · 社区动态 · #13
[Paper & Model] G-STAR: Group-Scaled Token Capacity for Deeply Compressed Autoregressive Generation
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 32x and even effective 64x compression while preserving strong…
热度 45.9 / 100;排名与评分保留该期记录。