8 papers
Consistency Models for Fast MRI Reconstruction Using Regularization by Denoising
Merve Gülle, Junno Yun, Yaşar Utku Alçalar +1
Diffusion models (DMs) have emerged as powerful generative priors for MRI reconstruction with promising results. Yet DM-based methods require extensive iterative refinement, limiti…
UDT: Reconciling U-Nets and Diffusion Transformers with Data-Adaptive Token Reduction
Junno Yun, YaÅar Utku Alçalar, Mehmet Akçakaya
Diffusion Transformers (DiTs) have emerged as a core architecture in generative modeling due to their scalability and adaptability to multimodal tasks. DiTs comprise isotropic tran…
PnP-CM: Consistency Models as Plug-and-Play Priors for Inverse Problems
Merve Gülle, Junno Yun, YaÅar Utku Alçalar +1
Diffusion models have found extensive use in solving inverse problems, by sampling from an approximate posterior distribution of data given the measurements. Recently, consistency…
Time-Embedded Algorithm Unrolling for Computational MRI
Junno Yun, YaÅar Utku Alçalar, Mehmet Akçakaya
Algorithm unrolling methods have proven powerful for solving the regularized least squares problem in computational magnetic resonance imaging (MRI). These approaches unfold an ite…
No Alignment Needed for Generation: Learning Linearly Separable Representations in Diffusion Models
Junno Yun, YaÅar Utku Alçalar, Mehmet Akçakaya
Efficient training strategies for large-scale diffusion models have recently emphasized the importance of improving discriminative feature representations in these models. A centra…
Automated Tuning for Diffusion Inverse Problem Solvers without Generative Prior Retraining
YaÅar Utku Alçalar, Junno Yun, Mehmet Akçakaya
Diffusion/score-based models have recently emerged as powerful generative priors for solving inverse problems, including accelerated MRI reconstruction. While their flexibility all…