Xianhang Chu — accepted AI-conference papers

2026

Cross-Architecture Adaptation: Cloud-Edge Continual Test-Time Adaptation with Dynamic Sampling and Heterogeneous Distillation

Zirui Xu, Xianhang Chu, Jiahao Li, Xu Yang, Cheng Deng

CVPR 2026

Cloud-Edge Continual Test-Time Adaptation (CTTA)--with edge devices processing real-time data and the cloud offering strong computing power--is a critical paradigm for models that adapt to dynamic data distributions in real-world scenarios. However, most existing frameworks assume architectural homo

Cited by 0 Source ↗Scholar ↗

2026

Towards Robust Edge Model Adaptation via Elastic Architecture Search

Xianhang Chu, Xu Yang, Kun Wei, Xi Wang

AAAI 2026technical

Continual test-time adaptation (CTTA) enables online model adjustment under dynamic distribution shifts in real-world environments. However, most existing CTTA frameworks adopt fixed model architectures, lacking the structural flexibility required for deployment across heterogeneous edge devices wit

Cited by 0 Source ↗PDF ↗Scholar ↗