activity
20192023
most citedAttention-based Image Upsampling

6 citations · 24 across the 15 of their papers we have counts for

collaborators
Showing 2022Show all

6 papers · 1 filter

astro-ph.SR2022★ 3 cited

SuNeRF: Validation of a 3D Global Reconstruction of the Solar Corona Using Simulated EUV Images

Kyriaki-Margarita Bintsi, Robert Jarolim, Benoit Tremblay +8

Extreme Ultraviolet (EUV) light emitted by the Sun impacts satellite operations and communications and affects the habitability of planets. Currently, EUV-observing instruments are…

cs.LG2022★ 4 cited

A Hardware-Aware Framework for Accelerating Neural Architecture Search Across Modalities

Daniel Cummings, Anthony Sarah, Sharath Nittur Sridhar +3

Recent advances in Neural Architecture Search (NAS) such as one-shot NAS offer the ability to extract specialized hardware-aware sub-network configurations from a task-specific sup…

cs.CV2022

A Fast and Efficient Conditional Learning for Tunable Trade-Off between Accuracy and Robustness

Souvik Kundu, Sairam Sundaresan, Massoud Pedram +1

Existing models that achieve state-of-the-art (SOTA) performance on both clean and adversarially-perturbed images rely on convolution operations conditioned with feature-wise linea…

astro-ph.SR2022★ 1 cited

Deep-SWIM: A few-shot learning approach to classify Solar WInd Magnetic field structures

Hala Lamdouar, Sairam Sundaresan, Anna Jungbluth +9

The solar wind consists of charged particles ejected from the Sun into interplanetary space and towards Earth. Understanding the magnetic field of the solar wind is crucial for pre…

cs.AI2022★ 1 cited

A Hardware-Aware System for Accelerating Deep Neural Network Optimization

Anthony Sarah, Daniel Cummings, Sharath Nittur Sridhar +4

Recent advances in Neural Architecture Search (NAS) which extract specialized hardware-aware configurations (a.k.a. "sub-networks") from a hardware-agnostic "super-network" have be…

cs.CL2022★ 1 cited

TrimBERT: Tailoring BERT for Trade-offs

Sharath Nittur Sridhar, Anthony Sarah, Sairam Sundaresan

Models based on BERT have been extremely successful in solving a variety of natural language processing (NLP) tasks. Unfortunately, many of these large models require a great deal…