Mohsen Nayebi

PhD Candidate in Computer Science
University of Kansas

I am a PhD candidate at the University of Kansas, advised by Dr. Zijun Yao. My research focuses on foundation models, graph learning, and language models for relational and temporal data, with applications in healthcare and financial services.

I have held AI research internships at SAP Labs and Capital One.

Mohsen Nayebi

News

Joined SAP Labs as an AI Research PhD Associate Intern

Joined SAP Labs in Palo Alto to research graph, relational, and tabular foundation models for multi-table data.

Industry experience

Three papers accepted to EMNLP 2026 Main Conference

REFINE, ReTA, and RASPER explore LLMs, knowledge graphs, and reinforcement learning for clinical prediction.

Announcement

Returned to Capital One for a second PhD internship

Returned to Capital One’s AI Foundations team in New York as a Principal Data Science Intern, working on graph foundation models and fraud detection.

Industry experience
Earlier news

PhD comprehensive exam at the University of Kansas

Presented my research on representation augmentation for electronic health records through ontologies, knowledge graphs, and large language models.

View exam photo

ATLAS accepted at NeurIPS 2025’s NPGML workshop

ATLAS grew out of my first Capital One internship and studies graph learning for account takeover detection.

Announcement

LINKO accepted at CIKM 2025

LINKO introduces multi-ontology integration for medical concept representation.

Announcement

Joined Capital One’s PhD Data Science Internship Program

Joined Capital One’s AI Foundations team in San Jose as a Principal Data Science Intern, researching graph learning for account takeover detection.

Industry experience

Completed my MS in Computer Science

Celebrating my master’s defense and graduation at the University of Kansas. View photos.

Announcement

Research experience

SAP Labs

Palo Alto, CA

AI Research PhD Associate Intern

Researching graph, relational, and tabular foundation models for multi-table data. Developing parameter-efficient relational adaptation, relational in-context learning, and graph-based retrieval to generalize across datasets and tasks.

Poster presentations · Stanford Data-Centric AI Workshop 2026

  • Spatio-Temporal RDBLearn: Relational Label Signals Beyond Deep Feature Synthesis
    Mohsen Nayebi Kerdabadi, Joe Meyer, Peyman Baghershahi
  • JoeCo: Joint Embedding Compression for Frozen Tabular Foundation Models
    Joe Meyer, Mohsen Nayebi Kerdabadi, Peyman Baghershahi, Afreen Shaikh

AUG 24, 2026 – PRESENT

Capital One

New York, NY

Principal Data Science Intern · AI Foundations

Developed HERMES, a dual-scale relational Graph Transformer combining heterogeneous temporal neighborhoods with ecosystem-level context for consumer identity and fraud detection.

130M+ transactions evaluated. 44.44% relative reduction in customer friction. 24.66% relative improvement in fraud recall.

Accepted · NeurIPS 2026 GDDL Workshop · Paper

JUN – AUG 2026

Capital One

San Jose, CA

Principal Data Science Intern · AI Foundations

Built ATLAS, reframing account takeover detection as directed temporal graph learning. Combined causal message passing, inductive neighbor sampling, and lag-aware supervision on a graph with 100M+ nodes and 1B edges.

+6.38% AUC improvement. >50% less customer friction.

NeurIPS 2025 · NPGML Workshop paper

JUN – AUG 2025

Selected research

Publications

Google Scholar

2026

Dual-Scale Relational Graph Transformers for Ecosystem-Aware Fraud Detection

Mohsen Nayebi Kerdabadi, Xinrou Li, Yao Xiao, Zijun Yao, Xin Sun

NeurIPS 2026 · Geometric Distributional Deep Learning (GDDL) Workshop Accepted

Complementary Evidence Reasoning over Structured and Unstructured Electronic Health Records

Manuscript under review

StealthAlignment: Continual LLM Safety Alignment with Adaptive, Recalibrated Evolutionary Adversarial Pools

Manuscript under review

REFINE: LLM Refinement over Budgeted Text-Attributed Graphs for Personalized Medical Concept Representation

Mohsen Nayebi Kerdabadi, Arya Hadizadeh Moghaddam, Dongjie Wang, Zijun Yao

EMNLP 2026 · Main Conference Accepted

Text-Attributed Knowledge Graph Enrichment with Large Language Models for Medical Concept Representation

Mohsen Nayebi Kerdabadi, Arya Hadizadeh Moghaddam, Chen Chen, Dongjie Wang, Zijun Yao

ACL 2026 · Main Conference

Import What You Need: Learning When and How to Augment EHR Graphs with External Knowledge

Chen Chen, Mohsen Nayebi Kerdabadi, Dongjie Wang, Mei Liu, Zijun Yao

EMNLP 2026 · Main Conference Accepted

RASPER: Reward-Aligned Summarization of Clinical Notes for EHR Outcome Prediction

Arya Hadizadeh Moghaddam, Mohsen Nayebi Kerdabadi, Chen Chen, Dongjie Wang, Zijun Yao

EMNLP 2026 · Main Conference Accepted

RePrompT: Recurrent Prompt Tuning for Integrating Structured EHR Encoders with Large Language Models

Arya Hadizadeh Moghaddam, Drew Ross, Mohsen Nayebi Kerdabadi, Dongjie Wang, Zijun Yao

Findings of ACL 2026

User-Adaptive Meta-Learning for Cold-Start Medication Recommendation with Uncertainty Filtering

Arya Hadizadeh Moghaddam, Mohsen Nayebi Kerdabadi, Dongjie Wang, Mei Liu, Zijun Yao

IEEE ICDE 2026

2025

Multi-Ontology Integration with Dual-Axis Propagation for Medical Concept Representation

Mohsen Nayebi Kerdabadi, Arya Hadizadeh Moghaddam, Dongjie Wang, Zijun Yao

CIKM 2025 · Full Research Paper

Spatio-Temporal Directed Graph Learning for Account Takeover Fraud Detection

Mohsen Nayebi Kerdabadi, William Andrew Byron, Xin Sun, Amirfarrokh Iranitalab

NeurIPS 2025 · NPGML Workshop

Recurrent Neural Networks and Attention Scores for Personalized Prediction and Interpretation of Patient-Reported Outcomes

Jinxiang Hu, Mohsen Nayebi Kerdabadi, Xiaohang Mei, Joseph Cappelleri, Richard Barohn, Zijun Yao

Journal of Biopharmaceutical Statistics

Discovering Time-Aware Hidden Dependencies with Personalized Graphical Structure in Electronic Health Records

Arya Hadizadeh Moghaddam, Mohsen Nayebi Kerdabadi, Bin Liu, Mei Liu, Zijun Yao

ACM Transactions on Knowledge Discovery from Data · Online 2024; issue 2025

2024

Contrastive Learning on Medical Intents for Sequential Prescription Recommendation

Arya Hadizadeh Moghaddam, Mohsen Nayebi Kerdabadi, Mei Liu, Zijun Yao

CIKM 2024 · Full Research Paper

Meta-Learning on Augmented Gene Expression Profiles for Enhanced Lung Cancer Detection

Arya Hadizadeh Moghaddam, Mohsen Nayebi Kerdabadi, Cuncong Zhong, Zijun Yao

AMIA 2024 · Annual Symposium

2023

Contrastive Learning of Temporal Distinctiveness for Survival Analysis in Electronic Health Records

Mohsen Nayebi Kerdabadi, Arya Hadizadeh Moghaddam, Bin Liu, Mei Liu, Zijun Yao

CIKM 2023 · Full Research Paper

Journal article

SurvAttack: Black-Box Attack on Survival Models through Ontology-Informed EHR Perturbation

Mohsen Nayebi Kerdabadi, Arya Hadizadeh Moghaddam, Bin Liu, Mei Liu, Zijun Yao

ACM Transactions on Computing for Healthcare

Talks and posters

Preview of the REFINE poster

REFINE

REFINE: LLM Refinement over Budgeted Text-Attributed Graphs for Personalized Medical Concept Representation

Research poster · PDF
Preview of the MedCo slides

MedCo

Text-Attributed Knowledge Graph Enrichment with Large Language Models for Medical Concept Representation

Talk slides · PDF
Preview of the LINKO slides

LINKO

Multi-Ontology Integration with Dual-Axis Propagation for Medical Concept Representation

Talk slides · PDF
Preview of the OTCSurv slides

OTCSurv

Contrastive Learning of Temporal Distinctiveness for Survival Analysis in Electronic Health Records

Talk slides · PDF
Preview of the SurvAttack poster

SurvAttack

SurvAttack: Black-Box Attack on Survival Models through Ontology-Informed EHR Perturbation

Research poster · PDF

Background

I am a final-year PhD candidate in Computer Science at the University of Kansas.

My research spans knowledge-grounded LLMs, graph and relational foundation models, adaptive retrieval, and temporal representation learning. I study these methods in healthcare and financial applications.

I have been a Research Assistant at KU since January 2023. My industry research includes SAP Labs and Capital One’s AI Foundations team.

LLM–GNN integrationGraph transformersKnowledge graphsReinforcement learningLoRA & prompt tuningPyTorch

Education

2022 – PRESENT

PhD · Computer Science

University of Kansas

2022 – 2024

MS · Computer Science

University of Kansas

2016 – 2021

BS · Mechanical Engineering

Isfahan University of Technology

Research community

Reviewer for NeurIPS, ICLR, KDD, CIKM, SDM, IJCAI, TKDD, and the Journal of Biomedical Informatics.

Teaching at KU includes Data Mining and Advanced Data Science.