# SPeaR: Test-Time Adaptation with Steering Primitives for Realigning Representations

arXiv: https://arxiv.org/abs/2609.24111 · HTML: https://mlsanity.com/paper/2609.24111/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 35 references that are in the map.
- First posted on arXiv 21 Sep 2026.

## Builds on (most cited first, 25 of 25)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [Similarity of Neural Network Representations Revisited](https://mlsanity.com/paper/1905.00414/) (2019)
- [WILDS: A Benchmark of in-the-Wild Distribution Shifts](https://mlsanity.com/paper/2012.07421/) (2020)
- [AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty](https://mlsanity.com/paper/1912.02781/) (2019)
- [RobustBench: a standardized adversarial robustness benchmark](https://mlsanity.com/paper/2010.09670/) (2020)
- [How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers](https://mlsanity.com/paper/2106.10270/) (2021)
- [Efficient Test-Time Model Adaptation without Forgetting](https://mlsanity.com/paper/2204.02610/) (2022)
- [Improving robustness against common corruptions by covariate shift adaptation](https://mlsanity.com/paper/2006.16971/) (2020)
- [Towards Stable Test-Time Adaptation in Dynamic Wild World](https://mlsanity.com/paper/2302.12400/) (2023)
- [MEMO: Test Time Robustness via Adaptation and Augmentation](https://mlsanity.com/paper/2110.09506/) (2021)
- [A Survey of Unsupervised Deep Domain Adaptation](https://mlsanity.com/paper/1812.02849/) (2018)
- [High-Performance Large-Scale Image Recognition Without Normalization](https://mlsanity.com/paper/2102.06171/) (2021)
- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [Robust Test-Time Adaptation in Dynamic Scenarios](https://mlsanity.com/paper/2303.13899/) (2023)
- [EcoTTA: Memory-Efficient Continual Test-time Adaptation via Self-distilled Regularization](https://mlsanity.com/paper/2303.01904/) (2023)
- [Entropy is not Enough for Test-Time Adaptation: From the Perspective of Disentangled Factors](https://mlsanity.com/paper/2403.07366/) (2024)
- [Test-Time Adaptation to Distribution Shift by Confidence Maximization and Input Transformation](https://mlsanity.com/paper/2106.14999/) (2021)
- [Universal Test-time Adaptation through Weight Ensembling, Diversity Weighting, and Prior Correction](https://mlsanity.com/paper/2306.00650/) (2023)
- [SITA: Single Image Test-time Adaptation](https://mlsanity.com/paper/2112.02355/) (2021)
- [In Search of Lost Online Test-time Adaptation: A Survey](https://mlsanity.com/paper/2310.20199/) (2023)
- [Rapid Network Adaptation: Learning to Adapt Neural Networks Using Test-Time Feedback](https://mlsanity.com/paper/2309.15762/) (2023)

## Abstract (arXiv)

Test-time adaptation (TTA) addresses distribution shift using only unlabeled test data. Existing methods typically adapt pretrained models by updating their parameters, limiting both what is adapted and where adaptation can occur within the network. We instead keep the pretrained network frozen and steer its intermediate representations. We introduce SPeaR (Steering Primitive for Realigning Representations), which inserts lightweight learnable modules at stage boundaries and optimizes them directly from the test stream, requiring neither source data nor supervised warm-up. Each primitive is optimized using a gated objective that reduces uncertainty only when adaptation is beneficial, along with a diversity regularizer to prevent collapse, and a multi-depth anchor to stabilize adaptation. We show that steering early representations is the most effective strategy, and that the same primitive transfers across convolutional and Transformer architectures. Across CIFAR-10-C, CIFAR-100-C, and ImageNet-C, SPeaR consistently matches or outperforms methods that adapt orders of magnitude more parameters, remains robust across a wide range of batch sizes, and preserves source-domain performance during continual adaptation.