Sotabase

Career

· Research Intern, Google Research2025–
· Research Intern, Apple Machine Learning Research2024–
· Graduate Student, MądryLab, MIT2022–
· Research Assistant, Google Research Bangalore2021–
· Predoctoral Researcher, Microsoft Research Bangalore2019–

Publications (10)

The Pitfalls of Simplicity Bias in Neural Networks
Neural Information Processing Systems · 2020
426
cited
Do Input Gradients Highlight Discriminative Features?
Neural Information Processing Systems · 2021
67
cited
ContextCite: Attributing Model Generation to Context
Neural Information Processing Systems · 2024
62
cited
ModelDiff: A Framework for Comparing Learning Algorithms
International Conference on Machine Learning · 2022
34
cited
Decomposing and Editing Predictions by Modeling Model Computation
International Conference on Machine Learning · 2024
25
cited
Growing Attributed Networks through Local Processes
The Web Conference · 2017
6
cited
Number of Connected Components in a Graph: Estimation via Counting Patterns
arXiv.org · 2018
1
cited
Modeling Network Growth under Resource Constraints
arXiv.org · 2017
Sotabase
Harshay Shah | Researcher Profile | Sotabase | Sotabase