Chenggong Ni — accepted AI-conference papers

2026

Exposing Mixture and Annotating Confusion for Active Universal Test-Time Adaptation

Jiayao Tan, Fan Lyu, Chenggong Ni, Wei Feng, Fuyuan Hu, Rui Yao

ICLR 2026poster

Universal Test-Time Adaptation (UTTA) tackles the challenge of handling both class and domain shifts in unsupervised settings with stream testing data. Currently, most UTTA methods can only deal with minor shifts and heavily rely on heuristic approaches. To advance UTTA under dual shifts, we propose…

Cited by 0 Source ↗Scholar ↗

2025

DAA: Amplifying Unknown Discrepancy for Test-Time Discovery

Tianle Liu, Fan Lyu, Chenggong Ni, Zhang Zhang, Fuyuan Hu, Liang Wang

NeurIPS 2025poster

Test-Time Discovery (TTD) addresses the critical challenge of identifying and adapting to novel classes during inference while maintaining performance on known classes, which is a capability essential for dynamic real-world environments such as healthcare and autonomous driving. Recent TTD methods a…

Cited by 0 Source ↗Scholar ↗