Shah, Harshay

12 publications

ICML 2025 Parameters vs FLOPs: Scaling Laws for Optimal Sparsity for Mixture-of-Experts Language Models Samira Abnar, Harshay Shah, Dan Busbridge, Alaaeldin El-Nouby, Joshua M. Susskind, Vimal Thilak

ICLRW 2025 Parameters vs FLOPs: Scaling Laws for Optimal Sparsity for Mixture-of-Experts Language Models Samira Abnar, Harshay Shah, Dan Busbridge, Alaaeldin El-Nouby, Joshua M. Susskind, Vimal Thilak

NeurIPS 2024 ContextCite: Attributing Model Generation to Context Benjamin Cohen-Wang, Harshay Shah, Kristian Georgiev, Aleksander Mądry

ICMLW 2024 ContextCite: Attributing Model Generation to Context Benjamin Cohen-Wang, Harshay Shah, Kristian Georgiev, Aleksander Madry

ICMLW 2024 ContextCite: Attributing Model Generation to Context Benjamin Cohen-Wang, Harshay Shah, Kristian Georgiev, Aleksander Madry

ICML 2024 Decomposing and Editing Predictions by Modeling Model Computation Harshay Shah, Andrew Ilyas, Aleksander Madry

ICMLW 2024 Decomposing and Editing Predictions by Modeling Model Computation Harshay Shah, Andrew Ilyas, Aleksander Madry

NeurIPSW 2024 Decomposing and Editing Predictions by Modeling Model Computation Harshay Shah, Andrew Ilyas, Aleksander Madry

ICML 2023 ModelDiff: A Framework for Comparing Learning Algorithms Harshay Shah, Sung Min Park, Andrew Ilyas, Aleksander Madry

NeurIPSW 2022 A Unified Framework for Comparing Learning Algorithms Harshay Shah, Sung Min Park, Andrew Ilyas, Aleksander Madry

NeurIPS 2021 Do Input Gradients Highlight Discriminative Features? Harshay Shah, Prateek Jain, Praneeth Netrapalli

NeurIPS 2020 The Pitfalls of Simplicity Bias in Neural Networks Harshay Shah, Kaustav Tamuly, Aditi Raghunathan, Prateek Jain, Praneeth Netrapalli