Eleanor Wright

Professor of Computer Science

Stanford University, Department of Computer Science

I lead the Machine Intelligence Research Lab, where we explore fundamental questions in artificial intelligence, natural language processing, and machine learning. My work focuses on developing efficient, interpretable, and robust AI systems that can benefit society while maintaining transparency and accountability.

Prior to joining Stanford, I completed my PhD at MIT and held research positions at Google Brain and DeepMind. I am particularly interested in neural architecture search, transfer learning, and the intersection of linguistics and deep learning.

Dr. Eleanor Wright

Research Interests

Neural Architecture Search

Developing automated methods for discovering optimal neural network architectures that balance performance, efficiency, and computational cost.

Interpretable AI

Creating transparent and explainable machine learning models that enable humans to understand, trust, and effectively collaborate with AI systems.

Low-Resource NLP

Advancing natural language processing for underrepresented languages through transfer learning and innovative data augmentation techniques.

Selected Publications

Neural Architecture Search for Efficient Deep Learning Models

Dr. Eleanor Wright, J. Smith, M. Chen

Nature Machine Intelligence, 2024

PDF DOI
View Abstract
We present a novel approach to neural architecture search that reduces computational overhead by 40% while maintaining model accuracy. Our method employs a hierarchical search strategy that progressively refines candidate architectures through multiple stages of evaluation.

Interpretability in Large Language Models: A Comprehensive Survey

Dr. Eleanor Wright, R. Johnson

ACM Computing Surveys, 2023

PDF DOI
View Abstract
This survey examines recent advances in interpretability techniques for large language models, covering attention visualization, feature attribution methods, and mechanistic interpretability approaches. We identify key challenges and promising research directions for the field.

Efficient Transfer Learning for Low-Resource Languages

Dr. Eleanor Wright, K. Patel, L. Anderson

Proceedings of ACL 2023, 2023

PDF DOI
View Abstract
We demonstrate that cross-lingual transfer learning can be significantly improved for low-resource languages through carefully designed pre-training objectives and data augmentation strategies. Our approach achieves state-of-the-art results on five benchmark datasets.

Teaching

CS 6780: Advanced Machine Learning

Spring 2025

Course Description
Graduate-level course covering advanced topics in machine learning including deep learning architectures, optimization algorithms, generalization theory, and recent developments in foundation models. Students will complete a substantial research project.

CS 4780: Introduction to Machine Learning

Fall 2024

Course Description
Undergraduate course introducing fundamental concepts in machine learning. Topics include supervised and unsupervised learning, neural networks, decision trees, ensemble methods, and practical considerations for deploying ML systems.

CS 7880: Natural Language Processing Seminar

Spring 2025

Course Description
Research seminar exploring cutting-edge developments in NLP. Students read and present recent papers, engage in critical discussion, and develop original research ideas. Prerequisites include prior coursework in ML and NLP.

Contact

Get in Touch

Office

Gates Computer Science Building
Room 486
353 Jane Stanford Way
Stanford, CA 94305

Office Hours

Spring 2025: Tuesdays 2:00-4:00 PM

Students are welcome to drop by during office hours or schedule an appointment via email for other times. I'm happy to discuss research opportunities, course material, or career advice.