PulseAugur
实时 08:11:45

New MRI reconstruction uses discrete latent space and LLM techniques

Researchers have developed a novel method for MRI reconstruction that moves the process into a discrete multi-scale latent space, framing it as autoregressive next-acceleration-scale prediction. This approach leverages discrete priors, similar to those used in visual autoregressive modeling, to restrict solutions to compact sequences of codebook tokens, enabling sharper reconstructions even with extremely sparse measurements. The method also incorporates on-policy privileged information distillation, a technique inspired by large language model post-training, to further enhance reconstruction accuracy. Experiments on the fastMRI benchmark demonstrate improved performance across various sampling patterns under extreme undersampling. AI

影响 Introduces a novel approach to MRI reconstruction by adapting techniques from visual autoregressive modeling and large language models.

排序理由 The cluster contains an academic paper detailing a new method for MRI reconstruction.

在 Hugging Face Daily Papers 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

New MRI reconstruction uses discrete latent space and LLM techniques

报道来源 [2]

  1. Hugging Face Daily Papers TIER_1 English(EN) ·

    Next-Acceleration-Scale Prediction for Autoregressive MRI Reconstruction

    MRI reconstruction is an inherently ill-posed inverse problem, since incomplete measurements admit many plausible solutions. This ambiguity becomes more severe under high acceleration, where pixel-domain continuous predictors tend to average over feasible reconstructions and supp…

  2. arXiv cs.CV TIER_1 English(EN) · Yilmaz Korkmaz, Vishal M. Patel ·

    Next-Acceleration-Scale Prediction for Autoregressive MRI Reconstruction

    arXiv:2605.19354v2 Announce Type: replace-cross Abstract: MRI reconstruction is an inherently ill-posed inverse problem, since incomplete measurements admit many plausible solutions. This ambiguity becomes more severe under high acceleration, where pixel-domain continuous predict…