Pre-Conference Talk by MA Xiao | Architecture-Agnostic Test-Time Adaptation via Backprop-Free Embedding Alignment

Test-Time Adaptation (TTA) adapts a deployed model during online inference to mitigate the impact of domain shift. While achieving strong accuracy, most existing methods rely on backpropagation, which is memory and computation intensive, making them unsuitable for resource-constrained devices. Recent attempts to reduce this overhead often suffer from high latency or are tied to specific architectures such as ViT-only or CNN-only. In this work, we revisit domain shift from an embedding perspective. Our analysis reveals that domain shift induces three distinct structural changes in the embedding space: translation (mean shift), scaling (variance shift), and rotation (covariance shift). Based on this insight, we propose Progressive Embedding Alignment (PEA), a backpropagation-free and architecture-agnostic TTA approach. By applying a novel covariance alignment procedure at each intermediate layer, PEA efficiently corrects the embedding distortions with only two forward passes. Extensive experiments demonstrate that PEA achieves state-of-the-art performance in both accuracy and efficiency, while also proving versatile across different architectures including ViTs and CNNs.

This is a Pre-Conference talk for The Fourteenth International Conference on Learning Representations (ICLR 2026).

MA Xiao is a fourth-year Ph.D. candidate in Computer Science at the School of Computing and Information Systems under the supervision of Professor Baihua Zheng. His research focuses on developing efficient machine learning algorithms for resource-constrained devices.