
Giulia DeSalvo
Giulia DeSalvo has worked at Google Research since 2017. Her research interests are in both theory and applications of machine learning and recently, her primary focus has been on data efficiency of LLM and synthetic data generation. She received her PhD in mathematics from NYU’s Courant Institute of Mathematical Sciences with funding from NSF and received her B.A. in applied mathematics and Italian studies from UC Berkeley with highest honors.
Research Areas
Authored Publications
Sort By
Google
Two-step Active Learning for Instance Segmentation Neural Networks
Ke Yu
Suraj Kothawade
Abdullah Rashwan
Kayhan Batmanghelich
Xiaoqi(Michael) Yin
2023
Firebolt: Weak Supervision Under Weaker Assumptions
Zhaobin Kuang
Chidubem Arachie
Bangyong Liang
Michael Quinn
Bert Huang
Geoffrey Downs
Yang Yang
International Conference on Artificial Intelligence and Statistics 2022
Batch Active Learning at Scale
Anand Rajagopalan
Gui Citovsky
Laz Karydas
NeurIPS 2021
Understanding the Effects of Batching in Online Active Learning
Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics (2020)