Utkarsh Saxena

Engineering · Purdue University West Lafayette

Early career · publishing since 2018

Advanced Memory and Neural Computing Ferroelectric and Negative Capacitance Devices Advanced Neural Network Applications CCD and CMOS Imaging Sensors Neural dynamics and brain function

Publications

Citations

311

Est. group size

Recurring co-author estimate

Active years

Publishing since 2018

Research summary

AI-generated

Utkarsh Saxena's research spans hardware-efficient machine learning and neuromorphic computing, including work on memory-efficient neural network training, on-chip learning using novel spintronic and analog hardware devices, and efficient visual generation models. Earlier work also touched on applied machine learning tasks like pose estimation and image processing, as well as some early work in molecular physics/nanofluidics. The overall focus is on making neural network training and inference more computationally and energy efficient, often through novel hardware or algorithmic approaches.

Efficient neural network training and inferenceNeuromorphic and spintronic hardware for AIMemory-efficient deep learningComputer vision applicationsAnalog and emerging device-based computing

Publication output has been relatively steady over the last decade at 2-4 papers per year, with a modest increase in the most recent years (2024-2026).

Generated by claude-sonnet-5 from public bibliographic data · Jul 20, 2026

Publication cadence

Publications per year over the last 10 years — averaging 3.0/year recently

Recent publications

OASIS: Online Activation Subspace Learning for Memory-Efficient Training
arXiv (Cornell University) · 2026
OASIS: Online Activation Subspace Learning for Memory-Efficient Training
arXiv (Cornell University) · 2026
DC-DiT: Adaptive Compute and Elastic Inference for Visual Generation via Dynamic Chunking
ArXiv.org · 2026
DC-DiT: Adaptive Compute and Elastic Inference for Visual Generation via Dynamic Chunking
Open MIND · 2026
Real-Time Pose Estimation and Body Language Classification Using Machine Learning
International Journal of Research Publication and Reviews · 2025
Prototype for Integration of colorization and super resolution model using machine learning
2021 Third International Conference on Inventive Research in Computing Applications (ICIRCA) · 2021
On-chip learning in a conventional silicon MOSFET based Analog Hardware\n Neural Network
arXiv (Cornell University) · 2019
On-chip Learning In A Conventional Silicon MOSFET Based Analog Hardware Neural Network
2019
Spontaneous translation of nanodroplet over a heterogeneous surface due to thermal cycles: role of solid–liquid interfacial fluctuations
Molecular Physics · 2019
On-chip learning for domain wall synapse based Fully Connected Neural Network
Journal of Magnetism and Magnetic Materials · 2019
Skyrmionic implementation of Spike Time Dependent Plasticity (STDP) enabled Spiking Neural Network (SNN) under supervised learning scheme
2018
Low-Energy Implementation of Feed-Forward Neural Network With Back-Propagation Algorithm Using a Spin-Orbit Torque Driven Skyrmionic Device
IEEE Transactions on Magnetics · 2018

Publishes in

arXiv (Cornell University)×5
IEEE Transactions on Very Large Scale Integration (VLSI) Systems×2
Journal of Magnetism and Magnetic Materials×1
Scientific Reports×1
Frontiers in Science×1

Similar researchers

By research-topic overlap

Sourjya Roy
Engineering · Purdue University West Lafayette
Indranil Chakraborty
Engineering · Purdue University West Lafayette
Nitin Rathi
Engineering · Purdue University West Lafayette
Timur Ibrayev
Engineering · Purdue University West Lafayette
Can Li
Engineering · Purdue University West Lafayette

This profile was generated automatically from public scholarly data (OpenAlex). Group size and activity levels are estimates derived from co-authorship patterns.

Last updated Jul 20, 2026.

Claim or correct this profile