Alert button
Picture for Shreyas Saxena

Shreyas Saxena

Alert button

MediSwift: Efficient Sparse Pre-trained Biomedical Language Models

Mar 01, 2024
Vithursan Thangarasa, Mahmoud Salem, Shreyas Saxena, Kevin Leong, Joel Hestness, Sean Lie

Viaarxiv icon

Sparse Iso-FLOP Transformations for Maximizing Training Efficiency

Mar 25, 2023
Shreyas Saxena, Vithursan Thangarasa, Abhay Gupta, Sean Lie

Figure 1 for Sparse Iso-FLOP Transformations for Maximizing Training Efficiency
Figure 2 for Sparse Iso-FLOP Transformations for Maximizing Training Efficiency
Figure 3 for Sparse Iso-FLOP Transformations for Maximizing Training Efficiency
Figure 4 for Sparse Iso-FLOP Transformations for Maximizing Training Efficiency
Viaarxiv icon

SPDF: Sparse Pre-training and Dense Fine-tuning for Large Language Models

Mar 18, 2023
Vithursan Thangarasa, Abhay Gupta, William Marshall, Tianda Li, Kevin Leong, Dennis DeCoste, Sean Lie, Shreyas Saxena

Figure 1 for SPDF: Sparse Pre-training and Dense Fine-tuning for Large Language Models
Figure 2 for SPDF: Sparse Pre-training and Dense Fine-tuning for Large Language Models
Figure 3 for SPDF: Sparse Pre-training and Dense Fine-tuning for Large Language Models
Figure 4 for SPDF: Sparse Pre-training and Dense Fine-tuning for Large Language Models
Viaarxiv icon

Instance-Level Task Parameters: A Robust Multi-task Weighting Framework

Jun 11, 2021
Pavan Kumar Anasosalu Vasu, Shreyas Saxena, Oncel Tuzel

Figure 1 for Instance-Level Task Parameters: A Robust Multi-task Weighting Framework
Figure 2 for Instance-Level Task Parameters: A Robust Multi-task Weighting Framework
Figure 3 for Instance-Level Task Parameters: A Robust Multi-task Weighting Framework
Figure 4 for Instance-Level Task Parameters: A Robust Multi-task Weighting Framework
Viaarxiv icon

Training With Data Dependent Dynamic Learning Rates

May 27, 2021
Shreyas Saxena, Nidhi Vyas, Dennis DeCoste

Figure 1 for Training With Data Dependent Dynamic Learning Rates
Figure 2 for Training With Data Dependent Dynamic Learning Rates
Figure 3 for Training With Data Dependent Dynamic Learning Rates
Figure 4 for Training With Data Dependent Dynamic Learning Rates
Viaarxiv icon

Dynamic curriculum learning via data parameters for noise robust keyword spotting

Feb 18, 2021
Takuya Higuchi, Shreyas Saxena, Mehrez Souden, Tien Dung Tran, Masood Delfarah, Chandra Dhir

Figure 1 for Dynamic curriculum learning via data parameters for noise robust keyword spotting
Figure 2 for Dynamic curriculum learning via data parameters for noise robust keyword spotting
Figure 3 for Dynamic curriculum learning via data parameters for noise robust keyword spotting
Figure 4 for Dynamic curriculum learning via data parameters for noise robust keyword spotting
Viaarxiv icon

Learning Soft Labels via Meta Learning

Sep 20, 2020
Nidhi Vyas, Shreyas Saxena, Thomas Voice

Figure 1 for Learning Soft Labels via Meta Learning
Figure 2 for Learning Soft Labels via Meta Learning
Figure 3 for Learning Soft Labels via Meta Learning
Figure 4 for Learning Soft Labels via Meta Learning
Viaarxiv icon

Learning Unsupervised Visual Grounding Through Semantic Self-Supervision

Sep 05, 2018
Syed Ashar Javed, Shreyas Saxena, Vineet Gandhi

Figure 1 for Learning Unsupervised Visual Grounding Through Semantic Self-Supervision
Figure 2 for Learning Unsupervised Visual Grounding Through Semantic Self-Supervision
Figure 3 for Learning Unsupervised Visual Grounding Through Semantic Self-Supervision
Figure 4 for Learning Unsupervised Visual Grounding Through Semantic Self-Supervision
Viaarxiv icon

Convolutional Neural Fabrics

Jan 30, 2017
Shreyas Saxena, Jakob Verbeek

Figure 1 for Convolutional Neural Fabrics
Figure 2 for Convolutional Neural Fabrics
Figure 3 for Convolutional Neural Fabrics
Figure 4 for Convolutional Neural Fabrics
Viaarxiv icon