|
Vishesh Kumar
Email /
CV /
Github
"...The aim of science is to make difficult things understandable in a simpler way..." - Paul A.M. Dirac
I'm a PhD student in the Applied Physics Program at Rice University.
I am advised by Ashok Veeraraghavan and Vivek Boominathan, currently focusing on reconstruction algorithms for Compressed Sensing in Photoacoustic Imaging.
My background is in computational math and physics, which I studied at Arizona State, advised by Steve Pressé.
|
Research/Publications
In general, I am interested in building physics-based algorithms for inverse problems; recently, my efforts have focused on imaging and sensing.
|
NEWER: Neural Estimation of Wavelet-Embedded Representations
Vishesh Kumar,
Jingyi Miao,
Shunyao Zhang,
Huan-Cheng Liao,
Kaiyuan Yang,
Lei Li,
Ashok Veeraraghavan,
Vishwanath Saragadam,
and Vivek Boominathan
Asilomar Conference on Signals, Systems, and Computers, 2025(to appear)
An unsupervised method to map diffusion coefficients, along with uncertainties, continuously across 2-D surfaces directly from particle trajectories without data binning.
|
DiffMAP-GP: Continuous 2D diffusion maps from particle trajectories without data binning using Gaussian Processes
Vishesh Kumar,
J. Shepard Bryan IV,
Alex Rojewski,
Carlo Manzo,
and Steve Presse
Biophysical Reports, 2025
An unsupervised method to map diffusion coefficients, along with uncertainties, continuously across 2-D surfaces directly from particle trajectories without data binning.
|
Towards an Efficient, Customizable, and Accessible AI Tutor
Juan Segundo Hevia*,
Facundo Arredondo*,
Vishesh Kumar*,
Innovation and Responsibility in AI-Supported Education Workshop - AAAI, 2025
We propose a novel AI tutoring system that combines a Retrieval-Augmented Generation (RAG) pipeline with a lightweight language model to provide efficient, customizable, and accessible educational support.
|
|