Publications (21)
FSE Compensated Motion Correction for MRI Using Data Driven Methods
Brett Levac, Sidharth Kumar, Sofia Kardonik +1
Magnetic Resonance Imaging (MRI) is a widely used medical imaging modality boasting great soft tissue contrast without ionizing radiation, but unfortunately suffers from long acqui…
Solving Inverse Problems with Score-Based Generative Priors learned from Noisy Data
Asad Aali, Marius Arvinte, Sidharth Kumar +1
We present SURE-Score: an approach for learning score-based generative models using training samples corrupted by additive Gaussian noise. When a large training set of clean sample…
An untrained deep learning method for reconstructing dynamic magnetic resonance images from accelerated model-based data
Kalina P. Slavkova, Julie C. DiCarlo, Viraj Wadhwa +5
The purpose of this work is to implement physics-based regularization as a stopping condition in tuning an untrained deep neural network for reconstructing MR images from accelerat…
End-to-End Radio Fingerprinting with Neural Networks
Ryan M. Dreifuerst, Andrew Graff, Sidharth Kumar +2
This paper presents a novel method for classifying radio frequency (RF) devices from their transmission signals. Given a collection of signals from identical devices, we accurately…
Optimizing Datalog for the GPU
Yihao Sun, Ahmedur Rahman Shovon, Thomas Gilray +2
Modern Datalog engines (e.g., LogicBlox, Soufflé, ddlog) enable their users to write declarative queries which compute recursive deductions over extensional facts, leaving high-pe…
Configurable and Hierarchical Allreduce
Valentino Guerrini, Ke Fan, Sidharth Kumar
MPI_Allreduce is among the most performance-critical collectives in large-scale scientific computing and distributed machine learning, yet the small- and medium-message regime rema…
Ambient Diffusion Posterior Sampling: Solving Inverse Problems with Diffusion Models Trained on Corrupted Data
Asad Aali, Giannis Daras, Brett Levac +3
We provide a framework for solving inverse problems with diffusion models learned from linearly corrupted data. Firstly, we extend the Ambient Diffusion framework to enable trainin…
Efficient Compression of Structured and Unstructured Volumes via Learned 3D Gaussian Representation
Landon Dyken, Sharmistha Chakrabarti, Nathan Debardeleben +4
Recent work has shown that implicit neural representations (INRs) can be trained to effectively compress structured and unstructured volume data, allowing for direct data querying…
Datalog with First-Class Facts
Thomas Gilray, Arash Sahebolamri, Yihao Sun +3
Datalog is a popular logic programming language for deductive reasoning tasks in a wide array of applications, including business analytics, program analysis, and ontological reaso…
Terascale Query Processing in the Browser: Rethinking GPU Acceleration
Jiaxin Lu, Landon Dyken, Yihao Sun +3
Recursive query computation, central to graph algorithms and relational databases, demands GPU acceleration due to its inherent computational intensity. While substantial prior wor…
Scaling Worst-Case Optimal Datalog to GPUs
Yihao Sun, Kunting Qi, Thomas Gilray +2
Datalog is a declarative logic-programming language used for complex analytic reasoning workloads such as program analysis and graph analytics. Datalog's popularity is due to its u…
Enabling Fast and Accurate Crowdsourced Annotation for Elevation-Aware Flood Extent Mapping
Landon Dyken, Saugat Adhikari, Pravin Poudel +4
Mapping the extent of flood events is a necessary and important aspect of disaster management. In recent years, deep learning methods have evolved as an effective tool to quickly l…
Accelerated Motion Correction with Deep Generative Diffusion Models
Brett Levac, Sidharth Kumar, Ajil Jalal +1
Magnetic Resonance Imaging (MRI) is a powerful medical imaging modality, but unfortunately suffers from long scan times which, aside from increasing operational costs, can lead to…
Speculative Progressive Raycasting for Memory Constrained Isosurface Visualization of Massive Volumes
Will Usher, Landon Dyken, Sidharth Kumar
New web technologies have enabled the deployment of powerful GPU-based computational pipelines that run entirely in the web browser, opening a new frontier for accessible scientifi…
Column-Oriented Datalog on the GPU
Yihao Sun, Sidharth Kumar, Thomas Gilray +1
Datalog is a logic programming language widely used in knowledge representation and reasoning (KRR), program analysis, and social media mining due to its expressiveness and high pe…
Accelerating Stroke MRI with Diffusion Probabilistic Models through Large-Scale Pre-training and Target-Specific Fine-Tuning
Yamin Arefeen, Sidharth Kumar, Steven Warach +2
Purpose: To develop a data-efficient strategy for accelerated MRI reconstruction with Diffusion Probabilistic Generative Models (DPMs) that enables faster scan times in clinical st…
Higher-Order, Data-Parallel Structured Deduction
Thomas Gilray, Arash Sahebolamri, Sidharth Kumar +1
State-of-the-art Datalog engines include expressive features such as ADTs (structured heap values), stratified aggregation and negation, various primitive operations, and the oppor…
Configurable Non-uniform All-to-all Algorithms
Ke Fan, Jens Domke, Seydou Ba +1
MPI_Alltoallv generalizes the uniform all-to-all communication (MPI_Alltoall) by enabling the exchange of data blocks of varied sizes among processes. This function plays a crucial…
Volume Encoding Gaussians: Transfer Function-Agnostic 3D Gaussians for Volume Rendering
Landon Dyken, Andres Sewell, Will Usher +3
Visualizing the large-scale datasets output by HPC resources presents a difficult challenge, as the memory and compute power required become prohibitively expensive for end user sy…
Few-Max: Few-Shot Domain Adaptation for Unsupervised Contrastive Representation Learning
Ali Lotfi Rezaabad, Sidharth Kumar, Sriram Vishwanath +1
Contrastive self-supervised learning methods learn to map data points such as images into non-parametric representation space without requiring labels. While highly successful, cur…
Robust multi-coil MRI reconstruction via self-supervised denoising
Asad Aali, Marius Arvinte, Sidharth Kumar +2
We study the effect of incorporating self-supervised denoising as a pre-processing step for training deep learning (DL) based reconstruction methods on data corrupted by Gaussian n…