Marzyeh Ghassemi

papers

589

total citations

papers (13)

Characterizing Generalization under Out-Of-Distribution Shifts in Deep Metric Learning

NEURIPS 2021arXiv

citations

Learning Optimal Predictive Checklists

NEURIPS 2021arXiv

citations

Learning the Wrong Lessons: Syntactic-Domain Spurious Correlations in Language Models

NEURIPS 2025arXiv

citations

Measuring Stochastic Data Complexity with Boltzmann Influence Functions

ICML 2024arXiv

citations

Aggregation Hides Out-of-Distribution Generalization Failures from Spurious Correlations

NEURIPS 2025arXiv

citations

KScope: A Framework for Characterizing the Knowledge Status of Language Models

NEURIPS 2025arXiv

citations

Position: Application-Driven Innovation in Machine Learning

ICML 2024

citations

VisAlign: Dataset for Measuring the Alignment between AI and Humans in Visual Perception

NEURIPS 2023

citations

Marzyeh Ghassemi

papers (13)

Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors

If Influence Functions are the Answer, Then What is the Question?

Asymmetry in Low-Rank Adapters of Foundation Models

Medical Dead-ends and Learning to Identify High-Risk States and Treatments

Vision-Language Models Do Not Understand Negation

Characterizing Generalization under Out-Of-Distribution Shifts in Deep Metric Learning

Learning Optimal Predictive Checklists

Learning the Wrong Lessons: Syntactic-Domain Spurious Correlations in Language Models

Measuring Stochastic Data Complexity with Boltzmann Influence Functions

Aggregation Hides Out-of-Distribution Generalization Failures from Spurious Correlations

KScope: A Framework for Characterizing the Knowledge Status of Language Models

Position: Application-Driven Innovation in Machine Learning

VisAlign: Dataset for Measuring the Alignment between AI and Humans in Visual Perception

papers (13)

Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors

If Influence Functions are the Answer, Then What is the Question?

Asymmetry in Low-Rank Adapters of Foundation Models

Medical Dead-ends and Learning to Identify High-Risk States and Treatments

Vision-Language Models Do Not Understand Negation

Characterizing Generalization under Out-Of-Distribution Shifts in Deep Metric Learning

Learning Optimal Predictive Checklists

Learning the Wrong Lessons: Syntactic-Domain Spurious Correlations in Language Models

Measuring Stochastic Data Complexity with Boltzmann Influence Functions

Aggregation Hides Out-of-Distribution Generalization Failures from Spurious Correlations

KScope: A Framework for Characterizing the Knowledge Status of Language Models

Position: Application-Driven Innovation in Machine Learning

VisAlign: Dataset for Measuring the Alignment between AI and Humans in Visual Perception