On a Foundation Model for Operating Systems

no code implementations • 13 Dec 2023 • Divyanshu Saxena, Nihal Sharma, Donghyun Kim, Rohit Dwivedula, Jiayi Chen, Chenxi Yang, Sriram Ravula, Zichao Hu, Aditya Akella, Sebastian Angel, Joydeep Biswas, Swarat Chaudhuri, Isil Dillig, Alex Dimakis, P. Brighten Godfrey, Daehyeok Kim, Chris Rossbach, Gang Wang

This paper lays down the research agenda for a domain-specific foundation model for operating systems (OSes).

One-Dimensional Deep Image Prior for Curve Fitting of S-Parameters from Electromagnetic Solvers

1 code implementation • 6 Jun 2023 • Sriram Ravula, Varun Gorti, Bo Deng, Swagato Chakraborty, James Pingenot, Bhyrav Mutnury, Doug Wallace, Doug Winterberg, Adam Klivans, Alexandros G. Dimakis

DIP is a technique that optimizes the weights of a randomly-initialized convolutional neural network to fit a signal from noisy or under-determined measurements.

Optimizing Sampling Patterns for Compressed Sensing MRI with Diffusion Generative Models

1 code implementation • 5 Jun 2023 • Sriram Ravula, Brett Levac, Ajil Jalal, Jonathan I. Tamir, Alexandros G. Dimakis

Diffusion-based generative models have been used as powerful priors for magnetic resonance imaging (MRI) reconstruction.

MRI Reconstruction

Inverse Problems Leveraging Pre-trained Contrastive Representations

1 code implementation • NeurIPS 2021 • Sriram Ravula, Georgios Smyrnis, Matt Jordan, Alexandros G. Dimakis

The problem is to recover the representation of an image R(x), if we are only given a corrupted version A(x), for some known forward operator A.

Representation Learning

One-dimensional Deep Image Prior for Time Series Inverse Problems

no code implementations • 18 Apr 2019 • Sriram Ravula, Alexandros G. Dimakis

We extend the Deep Image Prior (DIP) framework to one-dimensional signals.

Denoising Imputation +2