Publications
Selected papers, conference proceedings, book chapters, and patents. Authors in bold denote primary contributors. Asterisks (*) mark equal contributions.
Preprints
- Light-FMP: Lightweight Feature and Model Pruning for Enhanced Deep Recommender Systems.preprint arXiv:2605.06441, 2026. arxiv
- Dynamic Scaled Gradient Descent for Stable Fine-Tuning for Classifications.preprint arXiv:2604.27987, 2026. arxiv
2026
- A Locally Agentic AI for 3D Neurosurgical Visualization and Segmentation.extended abstract 2026 North East AI Agents Day, New York, NY, May 2026.
- Quantifying the Predictability of Epidemic Dynamics: An Entropy-Aware Evaluation of Forecasting Models.extended abstract 2026 Northeast Bioengineering Conference (NEBEC 2026), Philadelphia, PA, April 2026.
- Visiting, Following, and Knowledge Sharing: Mining Network-Network Relationships in Crowd-Empowered Open Innovation.to appear Technology & Innovation Journal, 2026.
- Evaluating RAG and Non-RAG Pipelines for Concept Discovery in Environmental Health Ontologies.to appear AMIA Annual Symposium 2026.
- Convergence to Steady State in LLM-Generated Ontological Concepts.to appear Medical Informatics Europe Conference (MIE 2026), Genova, Italy.
2025
- Assessing the Macro and Micro Effects of Random Seeds on Fine-Tuning Large Language Models. IJCNLP-AACL 2025.
- To What Degree Can LLMs Support Medical Informatics Research? Examining the Interplay of Research Support LLMs with LLM Critics. AMIA Annual Symposium 2025.
- Examining Effects of Participant Interaction Network Breadth and Skill Diversity on the Success of Open Innovation. ACM Collective Intelligence Conference 2025 — Poster & Demo Track, La Jolla, CA.
- A Concept Utility Framework for Incremental Ontology Expansion. Multi Conference on Computer Science and Information Systems: e-Health 2025.
- Incorporating Knowledge Sharing in Graph Learning for User Behavior Prediction in Crowd-Empowered Online Communities. ACM ICMR 2025, Chicago.
2024
- When Artificial Intelligence Meets Human Intelligence: Topics and Sentiments about ChatGPT in Online Knowledge Sharing Communities.best paper nom HICSS 58, Hawaii, January 2025.
2023
- Exploring Graph Structure in Graph Neural Networks for Epidemic Forecasting. Temporal Graph Learning Workshop @ NeurIPS 2023, New Orleans.
- A Computable Case Definition for Patients with SARS-CoV2 Testing That Occurred Outside the Hospital. JAMIA Open, 6(3), October 2023. pdf bibtex
- Two-Stage Fine-Tuning for Improved Bias and Variance for Large Pretrained Language Models. ACL 2023, Toronto. pdf bibtex
- Predictive Performance of Multi-Model Ensemble Forecasts of COVID-19 Across European Nations. eLife, 12:e81916, April 2023. pdf
2022
- AI Techniques for Forecasting Epidemic Dynamics: Theory and Practice. In Lidströmer & Eldar (eds), Artificial Intelligence in COVID-19. Springer, Cham. (Book chapter, alphabetical authorship.) pdf
- Enhancing COVID-19 Ensemble Forecasting Model Performance Using Auxiliary Data Sources.best paper IEEE BigData 2022, Osaka, Japan.
- The United States COVID-19 Forecast Hub Dataset. Scientific Data, 9(462), August 2022. pdf
- Ensemble-Based Fine-Tuning Strategy for Temporal Relation Extraction from the Clinical Narrative. Clinical NLP @ NAACL 2022, Seattle. pdf
- Projected Resurgence of COVID-19 in the United States in July–December 2021 Resulting from the Increased Transmissibility of the Delta Variant and Faltering Vaccination. eLife, 11:e73584, 2022. pdf
- CausalGNN: Causal-Based Graph Neural Networks for Spatio-Temporal Epidemic Forecasting.oral AAAI 2022, Vancouver. Acceptance rate: 15%. pdf apx
- Combining Theory and Data Driven Approaches for Epidemic Forecasts. In Knowledge Guided Machine Learning (CRC Press). Book chapter.
2021
- All Models Are Useful: Bayesian Ensembling for Robust High Resolution COVID-19 Forecasting. ACM SIGKDD 2021. pdf
- Modeling of Future COVID-19 Cases, Hospitalizations, and Deaths, by Vaccination Rates and Nonpharmaceutical Intervention Scenarios — United States, April–September 2021. MMWR, 70:719–724, 2021. doi
- Cohorting to Isolate Asymptomatic Spreaders: An Agent-Based Simulation Study on the Mumbai Suburban Railway.oral AAMAS 2021. Acceptance rate: 24.8%.
- Forecasting Influenza Activity Using Machine-Learned Mobility Map. Nature Communications, 12(1):1–12, February 2021.
- Using Mobility Data to Understand and Forecast COVID-19 Dynamics.long talk IJCAI AI4SG 2021. Acceptance rate: 28%. pdf
2020
- Examining Deep Learning Models with Multiple Data Sources for COVID-19 Forecasting. IEEE BigData DSMH Workshop 2020. pdf
- Wisdom of the Ensemble: Improving Consistency of Deep Learning Models. NeurIPS 2020. Acceptance rate: 20.1%. pdf code poster
- Interplay of Global Multi-Scale Human Mobility, Social Distancing, Government Interventions, and COVID-19 Dynamics. medRxiv preprint. pdf
- Cola-GNN: Cross-Location Attention Based Graph Neural Networks for Long-Term ILI Prediction. CIKM 2020. Acceptance rate: 20%. pdf code
- TDEFSI: Theory Guided Deep Learning Based Epidemic Forecasting with Synthetic Information. ACM TSAS, 6(3):1–39, May 2020. IF: 1.69. pdf poster
2019
- DEFSI: Deep Epidemic Forecasting with Synthetic Information. IAAI 2019, Hawaii. Acceptance rate: 35%. pdf
- A Framework for Discovering Health Disparities Among Cohorts in an Influenza Epidemic. World Wide Web Journal, 22(6):2997–3020, November 2019. IF: 2.892. pdf poster
2018
- Social Media Based Simulation Models for Understanding Disease Dynamics. IJCAI 2018, Stockholm. Acceptance rate: 20.5%. pdf
2017 & earlier
- PDGM: Percolation-Based Directed Graph Matching in Social Networks. IEEE ICC 2017, Paris. Acceptance rate: 36.1%. pdf
- Understanding Health Disparities in an Influenza Epidemic. CSSSA 2016, New Mexico. pdf
- The Update Strategies of Global Statistics in Distributed Information Retrieval Systems. CCIR 2012, Jiangxi, China. pdf
Patents
- Method for Reproducibility of Deep Learning Classifiers Using Ensembles. U.S. Patent 11,574,166, issued February 7, 2023. link