Ryan King

Ryan King

Ph.D. student in Computer Science at Texas A&M University, developing multimodal foundation models for healthcare applications. Research focuses on contrastive pretraining, transfer learning, and continual learning for EHR data.

CV

Curriculum Vitae

Education

Ph.D. in Computer Science - Texas A&M University (Expected 2026)
Advisors: Dr. Bobak Mortazavi and Dr. Tianbao Yang
Engineering Graduate Merit Fellowship

B.S. in Computer Science - Texas A&M University (2019-2021)
Summa Cum Laude, Research Honors

B.S. in Civil Engineering - Virginia Military Institute (2011-2015)
Minor in Applied Mathematics

Professional Experience

Graduate Research Assistant, Clinical AI Lab

Texas A&M University | Aug 2021 – Present

  • Led foundational research in masked and contrastive pretraining for clinical data, designing novel architectures for uni-modal and bi-modal settings (EHR and clinical notes). Resulted in multiple first-author publications advancing zero-shot prediction and transfer learning in healthcare.
  • Directed a multidisciplinary team of graduate and undergraduate researchers on projects involving generative modeling of EHRs, multimodal learning with imaging and waveform data, and incorporation of clinical interventions for causal inference in pretraining.
  • Designed lab onboarding infrastructure and maintain two high-performance compute servers; created and published a new student setup guide that improved onboarding efficiency and research productivity.
  • Co-authored two federal research proposals (NSF Smart & Connected Health and NIH NLM R01), contributing sections on pretraining, data infrastructure, and evaluation methodology.

Undergraduate Research Assistant, Bioinformatics Lab

Texas A&M University | Dec 2019 – May 2021

  • Selected for competitive research role to develop methods for batch correction and fusion of scRNA-seq data using statistical and deep learning approaches.
  • Developed and evaluated a domain adaptation technique that reduced batch effects via Maximum Mean Discrepancy minimization, improving model generalization across experiments.
  • Ported deep generative models by translating a TensorFlow Zero-Inflated Negative Binomial Autoencoder (ZINB-AE) into PyTorch, enhancing usability and training stability.

Infantry Officer, United States Army (Active Duty)

1st Armored Division, Fort Bliss | May 2015 – July 2019

  • Led operations and logistics for a 120-soldier infantry company, deploying $80M in equipment across Syria, Iraq, and Kuwait under U.S. Central Command operations.
  • Served as executive officer and advisor to the company commander; mentored and trained junior officers during high-intensity rotations in combat environments.
  • Engineered a custom logistics tracking system integrated with the Army SAP platform, facilitating recovery of $300M in inventory through automated reconciliation processes.
  • Planned and executed adaptive supply chains supporting 4 platoons under dynamic mission objectives, ensuring operational continuity across distributed regions.

Teaching Experience

Instructor of Record, CSCE 421: Machine Learning

Texas A&M University

  • Selected to teach a class of 100 undergraduate students
  • Designed comprehensive curriculum covering Logistic Regression, Support Vector Machines, Decision Trees, Convolutional Neural Networks, Recurrent Neural Networks, and Auto-Encoders
  • Developed lectures, quizzes, homework assignments, projects, and exams to facilitate student learning

Publications

2024

Memory-Efficient Continual Learning with CLIP Models
Ryan King, Gang Li, Bobak J. Mortazavi, Tianbao Yang
NeurIPS 2024 Workshop on Adaptive Foundation Models

An Efficient Contrastive Unimodal Pretraining Method for EHR Time Series Data
Ryan King, Shivesh Kodali, Conrad Kreuger, Tianbao Yang, Bobak Mortazavi
2024 IEEE EMBS International Conference on Biomedical and Health Informatics (BHI)
Acceptance Rate: 25.6%

A Domain Incremental Continual Learning Benchmark for ICU Time Series Model Transportability
Ryan King, Conrad Kreuger, Ethan Vesekla, Tianbao Yang, Bobak Mortazavi
2024 IEEE EMBS International Conference on Biomedical and Health Informatics (BHI)
Acceptance Rate: 25.6%

2023

Multimodal Pretraining of Medical Time Series and Notes
Ryan King, Tianbao Yang, Bobak Mortazavi
Proceedings of the 3rd Machine Learning for Health Symposium (ML4H), PMLR 225:244-255
Acceptance Rate: 28.7%

Collaborative Work

MEDS Decentralized, Extensible Validation (MEDS-DEV) Benchmark: Establishing Reproducibility and Comparability in ML for Health
Matthew B.A. McDermott, Aleksia Kolo, Chao Pang, Edward Choi, Ethan Steinberg, Hyewon Jeong, Jack Gallifant, Jason Alan Fries, Jeffrey N Chiang, Jungwoo Oh, Justin Xu, Kamilė Stankevičiūtė, Kiril Vadimovic Klein, Mikkel Fruelund Odgaard, Nassim Oufattole, Patrick Rockenschaub, Pawel Renc, Robin van de Water, Shalmali Joshi, Simon Austin Lee, Teya Bergamaschi, Tom Pollard, Vincent Jeanselme, Nigam Shah, Michael Wornow, Aparajita Kashyap, Xinzhou Jiang, Yanwei Li, Young Sang Choi, Yuta Kobayashi, Ryan King
Proceedings of the 4th Machine Learning for Health Symposium (ML4H)

Under Review

Guideline-Aware, Language-Conditioned Time-Series Model for Lab Abnormality Prediction in EHRs
Ryan King, Julian Samuel, Sadeer Al-Kindi, Bobak Mortazavi
Proceedings of the 5th Machine Learning for Health Symposium (ML4H)

Privacy Preserving Continual Learning for EHRs using Bimodal Contrastive Pretraining
Barry Liu, Ryan King, Tianbao Yang, Bobak Mortazavi
Proceedings of the 5th Machine Learning for Health Symposium (ML4H)

Honors & Awards

  • Engineering Graduate Merit Fellowship - Texas A&M University
  • University Nomination for Google PhD Fellowship - 2025 Google PhD Fellowship in Health Research
  • Best Reviewer Award - 2024 IEEE EMBS International Conference on Biomedical and Health Informatics
  • Undergraduate Research Honors - Texas A&M University
  • Travel Awards - Multiple conference travel awards

Service & Leadership

  • Young Professionals (YP) Chair for IEEE-EMBS BHI 2025
  • Organized COVID-19 Data Competition for four consecutive years
  • Mentored 25+ junior researchers, including undergraduates and master’s students
  • Reviewer for NeurIPS, ICML, ICLR, ML4H, BHI, JBHI, and Neurocomputing

Open Source Contributions

Skills

Programming Languages: Python, SQL, C, C++, Java, JavaScript, C#, VBA, Scheme

Packages & Frameworks: PyTorch, TensorFlow, PySpark, Lightning, Hydra, Numpy, Pandas, Matplotlib, Sklearn

Course Projects

Optimization - Developed an algorithm to predict individual temperature parameters for contrastive pretraining using distributionally robust optimization

Software Engineering - Project manager/Scrum Master of a team that developed a web application which analyzed the sentiment of user-provided sentences using machine learning to create Spotify playlists

Robotics - Using the Deepmind Lab environment, experimented with Differentiable Neural Architecture Search and Evolutionary Search methods for learning the best model architecture for a policy learning agent

Last updated: September 2024