Lichuan Gu — accepted AI-conference papers

2026

Continuous Test-Time Adaptation via Dual Alignment

Boyuan Zhang, Jie Pan, Shuai Yang, Lichuan Gu

IJCAI 2026

Continual test-time adaptation (CTTA) seeks to adapt a source-pretrained model to continuously shifting target distributions. Recent advances in this field either minimize prediction entropy on streaming target samples, which is efficient but prone to error accumulation, or rely on teacher–student p

Cited by 0 Scholar ↗

2025

Split-and-Combine: Enhancing Style Augmentation for Single Domain Generalization

Zhen Zhang, Shuai Yang, Qianlong Dang, Zhize Wu, Lichuan Gu

ICCV 2025poster

Single domain generalization aims to learn a model with good generalization ability from a single source domain. Recent advances in this field have focused on increasing the diversity of the training data through style (e.g., color and texture) augmentation. However, most existing methods apply unif…

Cited by 0 Source ↗PDF ↗Scholar ↗