arXiv:2606. 31420v1 Announce Type: new Abstract: Test-Time Adaptation (TTA) enables models trained on a source domain to adapt online to unlabeled test data under distribution shifts.
Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.
arXiv:2607. 23735v1 Announce Type: new Abstract: In many real-world scenarios, encountering continual shifts in domain during inference is very common.
arXiv:2602. 06136v2 Announce Type: replace Abstract: Test-time adaptation (TTA) offers a compelling remedy for machine learning (ML) models that degrade under domain shifts, improving generalisation on-the-fly with only unlabelled samples.
arXiv:2608. 01074v1 Announce Type: new Abstract: Tabular data is used extensively in many real-world use cases.
arXiv:2606. 26457v1 Announce Type: cross Abstract: This paper presents a probabilistic framework for online test-time adaptation problems.
arXiv:2607. 18899v1 Announce Type: new Abstract: Forecasting under real-world conditions is inherently non-stationary, as the conditional distribution of future observations evolves over time.
Deep neural nets achieve remarkable performance when training and test data share the same distribution, but this assumption frequently breaks in real-world deployment, where data undergoes continual distributional shifts. Continual Test-Time Adaptation (CTTA) addresses this challenge by adapting pretrained models to non-stationary target distributions on-the-fly, without access to source data or labeled targets, while mitigating two critical failure modes: catastrophic forgetting of source knowledge and error accumulation from noisy pseudo-labels over extended time horizons.