About me
I’m an AI researcher and entrepreneur. I have vast experience in implementing state-of-the-art deep learning models for real-world use cases, ranging from computer vision solutions for the energy industry to graph analysis for government law enforcement. I received my masters in Computer Science at Tel-Aviv University advised by Prof. Jonathan Berant, focusing on NLP models’ Robustness. As a Ph.D. candidate at Prof. Berant’s lab, I research remaining gaps in state-of-the-art NLP models and how to solve them to increase trust in the industry and allow productionization of such models to empower everyday users.
I co-founded Demystify-AI where I act as the CTO and lead all research and technological efforts, developing a disruptive explainable AI platform, helping healthcare and financial institutions leverage modern ML techniques in highly regulated environment.
Publications
Efficient Long-Text Understanding with Short-Text Models
Maor Ivgi, Uri Shaham, Jonathan Berant. Published in TACL 2023, will be presented in ACL 2023
Scaling Laws Under the Microscope: Predicting Transformer Performance from Small Scale Experiments
Maor Ivgi, Yair Carmon, Jonathan Berant. Published in Findings of EMNLP 2022
SCROLLS: Standardized CompaRison Over Long Language Sequences
Uri Shaham, Elad Segal, Maor Ivgi, Avia Efrat, Ori Yoran, Adi Haviv, Ankit Gupta, Wenhan Xiong, Mor Geva, Jonathan Berant, Omer Levy. Published in EMNLP 2022
Beyond Importance Scores: Interpreting Tabular ML by Visualizing Feature Semantics
Amirata Ghorbani, Dina Berenbaum, Maor Ivgi, Yuval Dafna and James Zou. Published in MDPI (vol. 13), 2021
Achieving Model Robustness through Discrete Adversarial Training
Maor Ivgi and Jonathan Berant. Published in EMNLP 2021
Scene Graph to Image Generation with Contextualized Object Layout Refinement
Maor Ivgi, Yaniv Benny, Avichai Ben-David, Jonathan Berant, and Lior Wolf. Published in ICIP 2021
Patents
A Machine Learning Model Blind-Spot Detection System and Method
Maor Ivgi and Yuval Dafna. Submission: U.S. Provisional Patent Application No. 63/170,517 f.