The paper introduces DiffPT, a diffusion‑based pretraining method for classifier backbones aimed at improving performance when training data is scarce. Experiments on time‑series, natural image, and medical imaging datasets show that DiffPT outperforms many self‑supervised baselines, especially in low‑data regimes for medical and time‑series tasks. While contrastive pretraining remains superior on CIFAR‑10 and Tiny ImageNet, DiffPT offers a simple and effective alternative across diverse modalities.
arXiv:2607. 05319v1 Announce Type: cross Abstract: We study why diffusion autoencoders can achieve similar image quality while learning substantially different latent structures.
arXiv:2607. 12464v1 Announce Type: cross Abstract: When labeled data are scarce, off-the-shelf diffusion models can augment training sets for few-shot medical image classification, but not all generated samples are equally useful for the downstream task.
The paper explores large‑scale pretraining to enhance deep learning‑based geometric distortion correction for diffusion‑weighted imaging (DWI). By framing the task as image reconstruction, the authors compare a non‑pretrained baseline with self‑supervised and generative pretrained models, finding that the cWDM model yields the best quantitative and qualitative results. When applied to low‑resource, high‑throughput settings in a low‑ and middle‑income country, the pretrained models faced transferability issues, but aligning images to a common standard space improved predictions, indicating that harmonized preprocessing can aid cross‑domain deployment.
arXiv:2607. 03103v1 Announce Type: cross Abstract: Clinical cardiac imaging pipelines currently deploy separate models for each dataset and modality, incurring redundant training costs and precluding knowledge sharing across anatomically related tasks.
arXiv:2610.07002v1 Announce Type: new Abstract: Diffusion models learn semantic representations while generating images. In the Decoupled Diffusion Transformer (DDT), a condition encoder provides fea...
The paper introduces CM-RED, a fast MRI reconstruction method that combines a pretrained consistency model with the regularization by denoising framework. By integrating controlled noise injection into accelerated proximal gradient updates, CM-RED achieves high‑quality reconstructions on fastMRI knee and brain datasets with only four network function evaluations. It consistently outperforms existing diffusion‑ and consistency‑based approaches in quantitative metrics, visual fidelity, and robustness to hyperparameter changes.
Machine learning (ML) has emerged as a promising approach for improving diffusion MRI (dMRI) tractography, a task that remains limited by the intrinsic tension between local diffusion information and...
The paper revisits pixel-space diffusion models, showing that a vanilla diffusion transformer can generate directly in pixel space by swapping velocity prediction for clean image prediction. It introduces MFlow, an adaptive parameterization that interpolates between these two prediction modes based on data representation and model capacity, and demonstrates competitive performance on ImageNet, UCF‑101, and text‑to‑image tasks. Additionally, the authors add ConvRefiner, a lightweight convolutional module trained post‑hoc to restore high‑frequency details while preserving FID.
arXiv:2607. 13043v1 Announce Type: cross Abstract: Deep learning models achieve state-of-the-art image classification but face deployment challenges due to computational costs and energy demands.
The paper presents a systematic comparison of recurrent neural networks and Transformer models for iterative diffusion MRI tractography, focusing on training strategies, input representations, and hyperparameter tuning. It introduces a generation‑validation phase that provides streamline‑level supervision, enabling the models to achieve the best performance reported on the ISMRM2015 challenge dataset. The study also evaluates the effects of missing bundles, noisy training data, and invalid fibers, and demonstrates applicability to in‑vivo data from the Tractoinferno database.
The paper introduces a perceptually regularized diffusion framework for image super‑resolution, adding perceptual‑loss based regularization to the standard diffusion training objective. This approach incorporates prior knowledge to improve training convergence and encourages the recovery of meaningful image features. Experiments on benchmark datasets show enhanced perceptual quality while maintaining competitive distortion metrics.
arXiv:2602.14512v3 Announce Type: replace Abstract: Autoregressive pretraining has been key to the scalability of large language models, yet medical generative foundation models remain predominantly...