Khaled Saab

I am currently a PhD candidate at Stanford University in the department of Electrical Engineering.

I received my M.S in Electrical Engineering from Stanford in 2019 and B.S in Computer Engineering from Georgia Tech in 2017.

At Stanford, I am lucky to be advised by Daniel Rubin and Chris Ré.

As a recipient of the Stanford Interdisciplinary Graduate Fellowship, and member of the Center for Research on Foundation Models, my research delves into questions such as surpassing the limitations of Transformers by exploring novel and efficient sequence modeling architectures, along with mitigating model reliance on non-generalizable shortcuts. I am especially motivated by human-centric applications, such as healthcare.

Sequence modeling
Effectively Modeling Time Series with Simple Discrete State Spaces [Code]
Michael Zhang*, Khaled Saab*, Michael Poli, Tri Dao, Karan Goel, and Christopher Ré
International Conference on Learning Representations (ICLR), 2023.
Hungry Hungry Hippos: Towards Language Modeling with State Space Models [Blog] [Code]
Tri Dao*, Dan Fu*, Khaled Saab, Armin Thomas, Atri Rudra, and Christopher Ré
International Conference on Learning Representations (ICLR), 2023 (Spotlight).
Combining Recurrent, Convolutional, and Continuous-time Models with Structured Learned Linear State-Space Layers [Blog] [Code]
Albert Gu, Isys Johnson, Karan Goel, Khaled Saab, Tri Dao, Atri Rudra, and Christopher Ré
Neural Information Processing Systems (NeurIPS), 2021.
Self-Supervised Graph Neural Networks for Improved Electroencephalographic Seizure Analysis [Code] [Video]
Siyi Tang, Jared Dunnmon, Khaled Saab, Xuan Zhang, Qianying Huang, Florian Dubost, Daniel Rubin, and Christopher Lee-Messer
International Conference on Learning Representations (ICLR), 2022.
Spatiotemporal Modeling of Multivariate Signals With Graph Neural Networks and Structured State Space Models [Code]
Siyi Tang, Jared Dunnmon, Liangqiong Qu, Khaled Saab, Tina Baykaner, Christopher Lee-Messer, and Daniel Rubin
Conference on Health, Infernece, and Learning (CHIL), 2023 (Best Paper).
Reliability
Towards Trustworthy Seizure Onset Detection Using Workflow Notes [Code]
Khaled Saab, Siyi Tang, Mohamed Taha, Christopher Lee-Messer, Christopher Ré, and Daniel Rubin
In Submission.
Reducing Reliance on Spurious Features in Medical Image Classification with Spatial Specificity [Code] [Video]
Khaled Saab, Sarah Hooper, Mayee Chen, Michael Zhang, Daniel Rubin, and Christopher Ré
Machine Learning for Healthcare (MLHC), 2022.
Domino: Discovering Systematic Errors with Cross-Modal Embeddings [Code] [Blog] [Video]
Sabri Eyuboglu*, Maya Varma*, Khaled Saab*, Jean-Benoit Delbrouck, Christopher Lee-Messer, Jared Dunnmon, James Zou, and Christopher Ré
International Conference on Learning Representations (ICLR), 2022 (Oral).
ViLMedic: A Framework for Research at the Intersection of Vision and Language in Medical AI [Code]
Jean-Benoit Delbrouck, Khaled Saab, Maya Varma, Sabri Eyuboglu, Pierre Chambon, Jared Alexander Dunnmon, Juan Manuel Zambrano, Akshay Chaudhari, and Curtis Langlotz
Association for Computational Linguistics (ACL) Demo Track, 2022.
Cost-effective data scaling
Observational Supervision for Medical Image Classification Using Gaze Data [Code] [Video]
Khaled Saab, Sarah Hooper, Nimit Sohoni, Jupinder Parmar, Brian Pogatchnik, Sen Wu, Jared Dunnmon, Hongyang Zhang, Daniel Rubin, and Christopher Ré
Medical Image Computing and Computer Assisted Intervention (MICCAI), 2021 (Early Accept).
Weak Supervision as an Efficient Approach for Automated Seizure Detection in Electroencephalography
Khaled Saab, Jared Dunnmon, Christopher Ré, Daniel Rubin, and Christopher Lee-Messer
npj Digital Medicine, 2020.
Cross-Modal Data Programming Enables Rapid Medical Machine Learning [Code]
Jared Dunnmon, Alex Ratner, Khaled Saab, Nishit Khandwala, Matthew Markert, Hersh Sagreiya, Rodger Goldman, Christopher Lee-Messer, Matthew Lungren, Daniel Rubin, and Christopher Ré
Cell Patterns, 2020.
Doubly Weak Supervisioin of Deep Learning Models for Head CT
Khaled Saab, Jared Dunnmon, Roger Goldman, Alex Ratner, Hersh Sagreiya, Christopher Ré, and Daniel Rubin
Medical Image Computing and Computer Assisted Intervention (MICCAI), 2019 (Oral).
Improving Sample Complexity with Observational Supervision
Khaled Saab, Jared Dunnmon, Alex Ratner, Daniel Rubin, and Christopher Ré
ICLR Limited Labeled Data Workshop, 2019 (Spotlight).
Stochastic signal processing
A multivariate adaptive gradient algorithm with reduced tuning efforts
Samer Saab Jr, Khaled Saab, Shashi Phoha, Minghui Zhu, and Asok Ray
Neural Netowrks, 2022.
Shuffled Linear Regression with Erroneous Observations
Samer Saab, Khaled Saab, and Samer Saab Jr.
IEEE Conference on Information Sciences and Systems, 2019.
A Stochastic Newton-Raphson Method with Noisy Function Measurements
Khaled Saab and Samer Saab Jr.
IEEE Signal Processing Letters, 2016.
Application of an Optimal Stochastic Newton-Raphson Technique to Triangulation-Based Localization Systems
Khaled Saab and Samer Saab Jr.
IEEE/ION Position, Location and Navigation Symposium, 2016.
Estimation of Cluster Centroids in Presence of Noisy Observations
Khaled Saab
IEEE MIT Undergraduate Research Technology Conference, 2016.
A Positioning System for Photodiode Device Using Collocated LEDs
Samer Saab Jr. and Khaled Saab
IEEE Photonics Journal, 2016.
Protecting Bare-metal Embedded Systems with Privilege Overlays
Abraham Clements, Naif Almakhdhub, Khaled Saab, Prashast Srivastava, Jinkyu Koo, Saurabh Bagchi, and Mathias Payer
IEEE Symposium on Security and Privacy, 2017.

Personal Life

Tackling challenging problems with an interdisciplinary team is my passion (in a broad sense). But I also love many other activities that are social (chitchatting with friends), physical (martial arts and bodybuilding), and solitary (listening to podcasts, reading, and playing fetch with Mr. Tuck).