# Beyond Model Adaptation at Test Time: A Survey

arXiv: https://arxiv.org/abs/2411.03687 · HTML: https://mlsanity.com/paper/2411.03687/

## Key facts

- Cited by 59 papers in the map (data through 14 Oct 2026).
- Builds on 44 of its 401 references that are in the map.
- First posted on arXiv 6 Nov 2024.

## Builds on (most cited first, 30 of 44)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization](https://mlsanity.com/paper/1911.08731/) (2019)
- [Instance Normalization: The Missing Ingredient for Fast Stylization](https://mlsanity.com/paper/1607.08022/) (2016)
- [Towards Out-Of-Distribution Generalization: A Survey](https://mlsanity.com/paper/2108.13624/) (2021)
- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [Learning to (Learn at Test Time): RNNs with Expressive Hidden States](https://mlsanity.com/paper/2407.04620/) (2024)
- [Revisiting Batch Normalization For Practical Domain Adaptation](https://mlsanity.com/paper/1603.04779/) (2016)
- [Meta-Learning: A Survey](https://mlsanity.com/paper/1810.03548/) (2018)
- [Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shift](https://mlsanity.com/paper/2006.10963/) (2020)
- [Do CIFAR-10 Classifiers Generalize to CIFAR-10?](https://mlsanity.com/paper/1806.00451/) (2018)
- [BREEDS: Benchmarks for Subpopulation Shift](https://mlsanity.com/paper/2008.04859/) (2020)
- [Learning by Transduction](https://mlsanity.com/paper/1301.7375/) (2013)
- [A Comprehensive Survey on Source-free Domain Adaptation](https://mlsanity.com/paper/2302.11803/) (2023)
- [Visual Prompt Tuning for Test-time Domain Adaptation](https://mlsanity.com/paper/2210.04831/) (2022)
- [Improving Text-to-Image Consistency via Automatic Prompt Optimization](https://mlsanity.com/paper/2403.17804/) (2024)
- [Source-Free Unsupervised Domain Adaptation: A Survey](https://mlsanity.com/paper/2301.00265/) (2022)
- [SITA: Single Image Test-time Adaptation](https://mlsanity.com/paper/2112.02355/) (2021)
- [Test-time Batch Statistics Calibration for Covariate Shift](https://mlsanity.com/paper/2110.04065/) (2021)
- [MixNorm: Test-Time Adaptation Through Online Normalization Estimation](https://mlsanity.com/paper/2110.11478/) (2021)
- [In Search of Lost Online Test-time Adaptation: A Survey](https://mlsanity.com/paper/2310.20199/) (2023)
- [Meta-Prompting for Automating Zero-shot Visual Recognition with LLMs](https://mlsanity.com/paper/2403.11755/) (2024)
- [Revisiting Realistic Test-Time Training: Sequential Inference and Adaptation by Anchored Clustering Regularized Self-Training](https://mlsanity.com/paper/2303.10856/) (2023)
- [Benchmarking Test-Time Adaptation against Distribution Shifts in Image Classification](https://mlsanity.com/paper/2307.03133/) (2023)
- [On-target Adaptation](https://mlsanity.com/paper/2109.01087/) (2021)
- [Evaluation of Test-Time Adaptation Under Computational Time Constraints](https://mlsanity.com/paper/2304.04795/) (2023)
- [Self-Adaptive Forecasting for Improved Deep Learning on Non-Stationary Time-Series](https://mlsanity.com/paper/2202.02403/) (2022)
- [Robust Fast Adaptation from Adversarially Explicit Task Distribution Generation](https://mlsanity.com/paper/2407.19523/) (2024)

## Built on by (most cited first, 30 of 59)

- [Inner Thinking Transformer: Leveraging Dynamic Depth Scaling to Foster Adaptive Internal Thinking](https://mlsanity.com/paper/2502.13842/) (2025)
- [Visual Instance-aware Prompt Tuning](https://mlsanity.com/paper/2507.07796/) (2025)
- [Prompt-based Adaptation in Large-scale Vision Models: A Survey](https://mlsanity.com/paper/2510.13219/) (2025)
- [SLOT: Sample-specific Language Model Optimization at Test-time](https://mlsanity.com/paper/2505.12392/) (2025)
- [Continuous Self-Improvement of Large Language Models by Test-time Training with Verifier-Driven Sample Selection](https://mlsanity.com/paper/2505.19475/) (2025)
- [Efficient Test-Time Scaling for Small Vision-Language Models](https://mlsanity.com/paper/2510.03574/) (2025)
- [Monitoring Risks in Test-Time Adaptation](https://mlsanity.com/paper/2507.08721/) (2025)
- [CRISP: Object Pose and Shape Estimation with Test-Time Adaptation](https://mlsanity.com/paper/2412.01052/) (2024)
- [Latte: Collaborative Test-Time Adaptation of Vision-Language Models in Federated Learning](https://mlsanity.com/paper/2507.21494/) (2025)
- [The Illusion of Progress? A Critical Look at Test-Time Adaptation for Vision-Language Models](https://mlsanity.com/paper/2506.24000/) (2025)
- [Active Test-time Vision-Language Navigation](https://mlsanity.com/paper/2506.06630/) (2025)
- [Adapting Vision-Language Models Without Labels: A Comprehensive Survey](https://mlsanity.com/paper/2508.05547/) (2025)
- [Noise is an Efficient Learner for Zero-Shot Vision-Language Models](https://mlsanity.com/paper/2502.06019/) (2025)
- [AdaMEM: Test-Time Adaptive Memory for Language Agents](https://mlsanity.com/paper/2606.05684/) (2026)
- [Mint: A Simple Test-Time Adaptation of Vision-Language Models against Common Corruptions](https://mlsanity.com/paper/2510.22127/) (2025)
- [Test-Time Iterative Error Correction for Efficient Diffusion Models](https://mlsanity.com/paper/2511.06250/) (2025)
- [TTT-Parkour: Rapid Test-Time Training for Perceptive Robot Parkour](https://mlsanity.com/paper/2602.02331/) (2026)
- [An Evidence-Based Post-Hoc Adjustment Framework for Anomaly Detection Under Data Contamination](https://mlsanity.com/paper/2510.21296/) (2025)
- [Evolutionary Multi-Task Optimization for LLM-Guided Program Discovery](https://mlsanity.com/paper/2605.22613/) (2026)
- [What Drives Test-Time Adaptation for CLIP? A Controlled Empirical Study from an Update Perspective](https://mlsanity.com/paper/2606.14299/) (2026)
- [A Survey on Self-Improving Test-Time Intelligence: Feedback-Driven Adapting, Learning, and Scaling at Inference](https://mlsanity.com/paper/2609.01679/) (2026)
- [GeneralizeFormer: Layer-Adaptive Model Generation across Test-Time Distribution Shifts](https://mlsanity.com/paper/2502.12195/) (2025)
- [PAID: Pairwise Angular-Invariant Decomposition for Continual Test-Time Adaptation](https://mlsanity.com/paper/2506.02453/) (2025)
- [NeuroTTT: Bridging Pretraining-Downstream Task Misalignment in EEG Foundation Models via Test-Time Training](https://mlsanity.com/paper/2509.26301/) (2025)
- [Memory-Integrated Reconfigurable Adapters: A Unified Framework for Settings with Multiple Tasks](https://mlsanity.com/paper/2512.00940/) (2025)
- [Dance Across Shifts: Forward-Facilitation Continual Test-Time Adaptation through Dynamic Style Bridging](https://mlsanity.com/paper/2605.18608/) (2026)
- [On the Learnability of Test-Time Adaptation: A Recovery Complexity Perspective](https://mlsanity.com/paper/2605.28057/) (2026)
- [Improving Next Tokens via Second-to-Last Predictions with Generate and Refine](https://mlsanity.com/paper/2411.15661/) (2024)
- [EmbodiTTA: Resource-Efficient Test-Time Adaptation for Embodied Visual Systems](https://mlsanity.com/paper/2505.00986/) (2025)
- [Low-Cost Test-Time Adaptation for Robust Video Editing](https://mlsanity.com/paper/2507.21858/) (2025)

## Abstract (arXiv)

Machine learning algorithms have achieved remarkable success across various disciplines, use cases and applications, under the prevailing assumption that training and test samples are drawn from the same distribution. Consequently, these algorithms struggle and become brittle even when samples in the test distribution start to deviate from the ones observed during training. Domain adaptation and domain generalization have been studied extensively as approaches to address distribution shifts across test and train domains, but each has its limitations. Test-time adaptation, a recently emerging learning paradigm, combines the benefits of domain adaptation and domain generalization by training models only on source data and adapting them to target data during test-time inference. In this survey, we provide a comprehensive and systematic review on test-time adaptation, covering more than 400 recent papers. We structure our review by categorizing existing methods into five distinct categories based on what component of the method is adjusted for test-time adaptation: the model, the inference, the normalization, the sample, or the prompt, providing detailed analysis of each. We further discuss the various preparation and adaptation settings for methods within these categories, offering deeper insights into the effective deployment for the evaluation of distribution shifts and their real-world application in understanding images, video and 3D, as well as modalities beyond vision. We close the survey with an outlook on emerging research opportunities for test-time adaptation.