Shreyas Saxena

According to our database, Shreyas Saxena authored at least 14 papers between 2011 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2024

MediSwift: Efficient Sparse Pre-trained Biomedical Language Models.

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

CoRR, 2024

2023

Sparse Iso-FLOP Transformations for Maximizing Training Efficiency.

Shreyas Saxena, Vithursan Thangarasa, Abhay Gupta, Sean Lie

CoRR, 2023

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

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

Proceedings of the Uncertainty in Artificial Intelligence, 2023

2021

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

Pavan Kumar Anasosalu Vasu, Shreyas Saxena, Oncel Tuzel

CoRR, 2021

Training With Data Dependent Dynamic Learning Rates.

Shreyas Saxena, Nidhi Vyas, Dennis DeCoste

CoRR, 2021

Dynamic Curriculum Learning via Data Parameters for Noise Robust Keyword Spotting.

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

Proceedings of the IEEE International Conference on Acoustics, 2021

2020

Learning Soft Labels via Meta Learning.

Nidhi Vyas, Shreyas Saxena, Thomas Voice

CoRR, 2020

2019

Data Parameters: A New Family of Parameters for Learning a Differentiable Curriculum.

Shreyas Saxena, Oncel Tuzel, Dennis DeCoste

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Learning Unsupervised Visual Grounding Through Semantic Self-Supervision.

Syed Ashar Javed, Shreyas Saxena, Vineet Gandhi

Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, 2019

2016

Learning representations for visual recognition. (Apprentissage de représentations pour la reconnaissance visuelle).

Shreyas Saxena

PhD thesis, 2016

Convolutional Neural Fabrics.

Shreyas Saxena, Jakob Verbeek

Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 2016

Heterogeneous Face Recognition with CNNs.

Shreyas Saxena, Jakob Verbeek

Proceedings of the Computer Vision - ECCV 2016 Workshops, 2016

2015

Coordinated Local Metric Learning.

Shreyas Saxena, Jakob Verbeek

Proceedings of the 2015 IEEE International Conference on Computer Vision Workshop, 2015

2011

Significance of Dynamic Content of Gait Present in the Lower Silhouette Region.

Shreyas Saxena

Proceedings of the Biometric Recognition - 6th Chinese Conference, 2011