Harshay Shah
6 papers · 2020–2025 · 2 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
🌍 Conference Polyglot · Bronze 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (18) 🐣 Hot Topic Early Bird
❓
The Questioner
Venues
Top co-authors
Research topics
Machine Learning
(6)
Artificial Intelligence
(3)
Application Areas
(3)
Core AI · Artificial Intelligence
(3)
Optimization & Theory · Machine Learning
(3)
Deep Learning
(2)
Natural Language Processing
(2)
Core Methods
(2)
Learning Types
(2)
Resources & Methods
(2)
Computer Vision
(1)
Applications
(1)
Core AI · Computer Vision
(1)
Optimization & Theory · Deep Learning
(1)
Techniques
(1)
Keywords
stochastic gradient descent
(1)
adversarial robustness
(1)
data augmentation
(1)
adversarial training
(1)
model interpretability
(1)
sparsity
(1)
distribution shift
(1)
model comparison
(1)
convolution filters
(1)
generative model
(1)
learning algorithm
(1)
adversarial perturbation
(1)
language model
(1)
poisoning attack
(1)
scaling law
(1)
model generalization
(1)
attention head
(1)
retrieval-augmented generation
(1)
simplicity bia
(1)
context attribution
(1)
Papers
Parameters vs FLOPs: Scaling Laws for Optimal Sparsity for Mixture-of-Experts Language Models
ICML 2025
ContextCite: Attributing Model Generation to Context
NeurIPS 2024
Decomposing and Editing Predictions by Modeling Model Computation
ICML 2024
ModelDiff: A Framework for Comparing Learning Algorithms
ICML 2023
Do Input Gradients Highlight Discriminative Features?
NeurIPS 2021
The Pitfalls of Simplicity Bias in Neural Networks
NeurIPS 2020