Ryan Solgi
YOU?
Author Swipe
View article: Activation-Informed Pareto-Guided Low-Rank Compression for Efficient LLM/VLM
Activation-Informed Pareto-Guided Low-Rank Compression for Efficient LLM/VLM Open
Large language models (LLM) and vision-language models (VLM) have achieved state-of-the-art performance, but they impose significant memory and computing challenges in deployment. We present a novel low-rank compression framework to addres…
View article: Do Tensorized Large-Scale Spatiotemporal Dynamic Atmospheric Data Exhibit Low-Rank Properties?
Do Tensorized Large-Scale Spatiotemporal Dynamic Atmospheric Data Exhibit Low-Rank Properties? Open
In this study, we investigate for the first time the low-rank properties of a tensorized large-scale spatio-temporal dynamic atmospheric variable. We focus on the Sentinel-5P tropospheric NO2 product (S5P-TN) over a four-year period in an …
View article: Saten: Sparse Augmented Tensor Networks for Post-Training Compression of Large Language Models
Saten: Sparse Augmented Tensor Networks for Post-Training Compression of Large Language Models Open
The efficient implementation of large language models (LLMs) is crucial for deployment on resource-constrained devices. Low-rank tensor compression techniques, such as tensor-train (TT) networks, have been widely studied for over-parameter…
View article: Retrieval of Missing Remotely Sensed Tropospheric NO2 Data Using Tensor Completion
Retrieval of Missing Remotely Sensed Tropospheric NO2 Data Using Tensor Completion Open
Missing values in remotely sensed satellite data present a significant challenge for accurate analysis and interpretation of environmental data. Factors such as dead pixel values or cloud coverage can lead to significant gaps in datasets, …
View article: Tensor shape search for efficient compression of tensorized data and neural networks
Tensor shape search for efficient compression of tensorized data and neural networks Open
Compressing big data and model parameters via tensor decomposition such as the tensor train (TT) format has gained great success in recent years. The application of tensor compression methods requires the data be high dimensional. However,…
View article: Partial Tensorized Transformers for Natural Language Processing
Partial Tensorized Transformers for Natural Language Processing Open
The transformer architecture has revolutionized Natural Language Processing (NLP) and other machine-learning tasks, due to its unprecedented accuracy. However, their extensive memory and parameter requirements often hinder their practical …
View article: Resolving the Water Crisis: There's a Way, But Is There the Will?
Resolving the Water Crisis: There's a Way, But Is There the Will? Open
In this issue paper, the authors refine the definition of water sustainability to account for temporal dynamics and spatial variability, identify specific challenges that must be resolved in the very near future to avoid catastrophic outco…
View article: Predicting COVID Cases: Effectiveness of the Vaccine
Predicting COVID Cases: Effectiveness of the Vaccine Open
The COVID-19 pandemic has been one of the most devastating events in recent history, resulting in millions of deaths and destruction to the global economy. While vaccines have been developed to slow the spread of the virus and achieve glob…
View article: Tensor Shape Search for Optimum Data Compression
Tensor Shape Search for Optimum Data Compression Open
Various tensor decomposition methods have been proposed for data compression. In real world applications of the tensor decomposition, selecting the tensor shape for the given data poses a challenge and the shape of the tensor may affect th…
View article: Long short-term memory neural network (LSTM-NN) for aquifer level time series forecasting using in-situ piezometric observations
Long short-term memory neural network (LSTM-NN) for aquifer level time series forecasting using in-situ piezometric observations Open
The application of neural networks (NN) in groundwater (GW) level prediction has been shown promising by previous works. Yet, previous works have relied on a variety of inputs, such as air temperature, pumping rates, precipitation, service…