# Awaken, Then Scale: Tiny Adaptation for MRI Reconstruction

arXiv: https://arxiv.org/abs/2609.31813 · HTML: https://mlsanity.com/paper/2609.31813/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 30 references that are in the map.
- First posted on arXiv 25 Sep 2026.

## Builds on (most cited first, 20 of 20)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Convex optimization](https://mlsanity.com/paper/2106.01946/) (2021)
- [PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning](https://mlsanity.com/paper/1711.05769/) (2017)
- [SNIP: Single-shot Network Pruning based on Connection Sensitivity](https://mlsanity.com/paper/1810.02340/) (2018)
- [Robust fine-tuning of zero-shot models](https://mlsanity.com/paper/2109.01903/) (2021)
- [Rigging the Lottery: Making All Tickets Winners](https://mlsanity.com/paper/1911.11134/) (2019)
- [fastMRI: An Open Dataset and Benchmarks for Accelerated MRI](https://mlsanity.com/paper/1811.08839/) (2018)
- [Parameter-Efficient Transfer Learning with Diff Pruning](https://mlsanity.com/paper/2012.07463/) (2020)
- [Parameter-Efficient Fine-Tuning without Introducing New Latency](https://mlsanity.com/paper/2305.16742/) (2023)
- [Zero-Shot Self-Supervised Learning for MRI Reconstruction](https://mlsanity.com/paper/2102.07737/) (2021)
- [RoSA: Accurate Parameter-Efficient Fine-Tuning via Robust Adaptation](https://mlsanity.com/paper/2401.04679/) (2024)
- [Test-Time Training Can Close the Natural Distribution Shift Performance Gap in Deep Learning Based Compressed Sensing](https://mlsanity.com/paper/2204.07204/) (2022)
- [Sparse High Rank Adapters](https://mlsanity.com/paper/2406.13175/) (2024)
- [SAFT: Towards Out-of-Distribution Generalization in Fine-Tuning](https://mlsanity.com/paper/2407.03036/) (2024)
- [PAC-Net: A Model Pruning Approach to Inductive Transfer Learning](https://mlsanity.com/paper/2206.05703/) (2022)
- [Continual Domain Adaptation through Pruning-aided Domain-specific Weight Modulation](https://mlsanity.com/paper/2304.07560/) (2023)
- [Pruning Unrolled Networks (PUN) at Initialization for MRI Reconstruction Improves Generalization](https://mlsanity.com/paper/2412.18668/) (2024)
- [FAM: fast adaptive federated meta-learning](https://mlsanity.com/paper/2308.13970/) (2023)
- [D2SA: Dual-Stage Distribution and Slice Adaptation for Efficient Test-Time Adaptation in MRI Reconstruction](https://mlsanity.com/paper/2503.20815/) (2025)

## Abstract (arXiv)

Dormant Awakening (DA) specializes a magnetic resonance imaging (MRI) reconstruction model by fitting a small set of zero weights to one labeled slice. Across fourteen U-shaped convolutional network (U-Net) and vision transformer (ViT) sources, fitting 1,004 or 10,560 weights gives mean peak signal-to-noise ratio (PSNR) gains of .430 and .509 dB. We analyze how scaling the fitted output correction changes evaluation PSNR, then use the calibration correction size to cap changes on new images. The cap bounds changes in root mean squared error (RMSE) relative to the source without an evaluation reference. At 10% adaptation budget, we compare fixed halving and dynamic capping for DA, unrestricted sparse adaptation and low-rank adaptation (LoRA). The controls increase both measured calibration-evaluation correlations across all six tested architecture-adapter settings. Experiments concern one constructed fastMRI-to-M4Raw shift with fixed source checkpoints and participant panels.