Rethinking Visual Autoregressive Sampling with Information-Grounding Guidance
Ky Dan Nguyen, Hoang Lam Tran, Anh-Dung Dinh, Daochang Liu, Weidong Cai, Xiuying Wang, Chang Xu
Abstract
Autoregressive (AR) models based on next-scale prediction are rapidly emerging as a powerful tool for image generation, but they face a critical weakness: information inconsistencies between patches across timesteps introduced by progressive resolution scaling. These inconsistencies scatter guidance signals, causing them to drift away from conditioning information and leaving behind ambiguous, unfaithful features. We tackle this challenge with Information-Grounding Guidance (IGG), a novel mechanism that anchors guidance to semantically important regions through attention. By adaptively reinforcing informative patches during sampling, IGG ensures that guidance and content remain tightly aligned. Across both class-conditioned and text-to-image generation tasks, IGG delivers sharper, more coherent, and semantically grounded images, setting a new benchmark for AR-based methods.
BibTeX
@inproceedings{
nguyen2026rethinking,
title={Rethinking Visual Autoregressive Sampling with Information-Grounding Guidance},
author={Ky Dan Nguyen and Hoang Lam Tran and Anh-Dung Dinh and Daochang Liu and Weidong Cai and Xiuying Wang and Chang Xu},
booktitle={Forty-third International Conference on Machine Learning},
year={2026},
url={https://openreview.net/forum?id=4PL5wouooK}
}