Harshay Shah

harshay's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored a paper 7 months ago

Parameters vs FLOPs: Scaling Laws for Optimal Sparsity for Mixture-of-Experts Language Models

Paper • 2501.12370 • Published Jan 21 • 11

authored 2 papers 12 months ago

ContextCite: Attributing Model Generation to Context

Paper • 2409.00729 • Published Sep 1, 2024 • 14

Decomposing and Editing Predictions by Modeling Model Computation

Paper • 2404.11534 • Published Apr 17, 2024

authored 3 papers over 1 year ago

Do Input Gradients Highlight Discriminative Features?

Paper • 2102.12781 • Published Feb 25, 2021

ModelDiff: A Framework for Comparing Learning Algorithms

Paper • 2211.12491 • Published Nov 22, 2022

The Pitfalls of Simplicity Bias in Neural Networks

Paper • 2006.07710 • Published Jun 13, 2020