mlsanityData to 14 Oct 2026

A probabilistic framework for online test-time adaptation

arXiv 2606.26457 ↗First posted 24 Jun 2026stat.ML cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

This paper presents a probabilistic framework for online test-time adaptation problems. In them, a model is trained on labeled data but must adapt to unlabeled data at test time under the assumption that training and test distributions potentially differ, that is, there might have been a distributional shift. The framework is based on a state-space modelling architecture from which parameter learning, parameter time evolution, prior tuning, and prediction can be characterized.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 19 of its 34 references that are in the map. First posted on arXiv 24 Jun 2026.

Builds on

19 of 34 references.

References · 19

  1. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  2. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,375
  3. 2020Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptationcited by 848
  4. 2022Continual Test-Time Domain Adaptationcited by 525
  5. 2022Efficient Test-Time Model Adaptation without Forgettingcited by 469
  6. 2014New insights and perspectives on the natural gradient methodcited by 443
  7. 2021MEMO: Test Time Robustness via Adaptation and Augmentationcited by 377
  8. 2021Laplace Redux -- Effortless Bayesian Deep Learningcited by 365
  9. 2023A Comprehensive Survey on Test-Time Adaptation under Distribution Shiftscited by 359
  10. 2013A General Framework for Updating Belief Distributionscited by 175
  11. 2022Test-Time Adaptation via Conjugate Pseudo-labelscited by 98
  12. 2023Universal Test-time Adaptation through Weight Ensembling, Diversity Weighting, and Prior Correctioncited by 65
7 more
  1. 2024Beyond Model Adaptation at Test Time: A Surveycited by 59
  2. 2024Bayesian Online Natural Gradient (BONG)cited by 14
  3. 2024Temporal Test-Time Adaptation with State-Space Modelscited by 7
  4. 2025LoRA-TTT: Low-Rank Test-Time Training for Vision-Language Modelscited by 7
  5. 2024A unifying framework for generalised Bayesian online learning in non-stationary environmentscited by 5
  6. 2025Martingale Posterior Neural Networks for Fast Sequential Decision Makingcited by 4
  7. 2025Evasion Attacks Against Bayesian Predictive Modelscited by 1

Built on by

Not cited yet.