arXiv Machine Learning
Jun 26
A probabilistic framework for online test-time adaptation
arXiv:2606. 26457v1 Announce Type: cross Abstract: This paper presents a probabilistic framework for online test-time adaptation problems.
A probabilistic framework for online test-time adaptation
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.
Related stories
arXiv AI
Jul 1
BP-TTA: Balanced and Prototype-Guided Test-Time Adaptation in Dynamic Scenarios
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.
arXiv Machine Learning
Jul 28
Source-Free Controlled Adaptation of Teachers for Continual Test-Time Adaptation
arXiv:2607. 23735v1 Announce Type: new Abstract: In many real-world scenarios, encountering continual shifts in domain during inference is very common.
arXiv AI
Jul 22
Black-Mamba: Biologically-Inspired Leaky Accumulation for Conceptual Knowledge under Distribution Drift
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.
arXiv Machine Learning
Aug 4
Logit-Origin Centering for Singleton Test-Time Adaptation
arXiv:2608. 01074v1 Announce Type: new Abstract: Tabular data is used extensively in many real-world use cases.
arXiv Machine Learning
Jun 2
Tempora: Characterising the Time-Contingent Utility of Online Test-Time Adaptation
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 AI
Jun 10
On the Learnability of Test-Time Adaptation: A Recovery Complexity Perspective
arXiv:2605. 28057v2 Announce Type: replace-cross Abstract: Test-time adaptation (TTA) aims to adapt models to maintain reliable performance on non-stationary test streams without requiring labeled data.
arXiv Machine Learning
Jun 16
A Decision-Theoretic View of Test-Time Training: When, How Far, and Which Directions to Adapt
arXiv:2606. 15569v1 Announce Type: new Abstract: Test-time training (TTT) adapts a pretrained model to each prompt via parameter updates, improving accuracy under pretraining-to-test distribution shifts.
arXiv Machine Learning
Jun 2
Agile Online Model Selection: Resolving Adaptation Lag via Safeguarded Large Learning Rates
arXiv:2605. 26919v2 Announce Type: replace Abstract: Maintaining predictive accuracy in non-stationary environments requires online model selection to adapt autonomously to unknown distribution shifts.
Hugging Face Trending Papers
Jul 9
Continual Test-Time Adaptation in Computer Vision: Methods, Benchmarks, and Future Directions
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.
arXiv AI
Jun 30
T3R: Deeper Test-Time Adaptation for Graph Neural Networks via Gradient Rotation
arXiv:2606. 30011v1 Announce Type: cross Abstract: Graph Neural Networks (GNNs) deployed in real-world systems typically have fixed weights, often leading to degraded performance under distribution shifts.
arXiv AI
Jul 2
Loss Smoothing for Stable Adaptation Under Distribution Shift
arXiv:2607. 00634v1 Announce Type: cross Abstract: In settings such as fine-tuning and reinforcement learning, neural networks are often adapted under distribution shift.