NIH/R61EY037504: VisionWay: Accessibility-aware Path Selection for Wayfinding, 09/01/2025-08/31/2027. Role: MPI, $1,235,002, 25%.
What we study
Research
Fundamental advances in trustworthy machine learning, connected to health, accessibility, and society.
01 / Research direction
Large Language Model Safety and Security
We study attacks on large language models and develop defenses that improve safety, alignment, and robustness.
02 / Research direction
Large Language Model Unlearning
We develop methods that help language models forget unwanted or sensitive information while preserving useful knowledge.
03 / Research direction
Large Vision-Language Model for Grounded Spatial Reasoning
We combine vision, language, and segmentation to support spatial reasoning and accessible pedestrian navigation.
04 / Research direction
Vision–Language Models for Medical Image Segmentation
We connect medical images with clinical language to improve segmentation and cross-modal reasoning.
05 / Research direction
On-device machine learning
We build efficient, privacy-aware AI for language and medical imaging on mobile and resource-limited devices.
06 / Research direction
Smart and connected health
We use spatial and temporal IoT data for prediction, representation learning, and anomaly detection in connected health.
07 / Research direction
Fairness-aware decision support system
We design decision-support methods that address sampling, social, and algorithmic biases.
08 / Research direction
Automatic medical imaging interpretation
We combine visual and language features to help AI interpret medical images.
09 / Research direction
Explainable recommender system
We use domain knowledge to make personalized recommendations easier to explain.
10 / Research direction
Spatial-temporal modeling of 4D CNN for fMRI analysis
We develop 4D convolutional models to learn developmental patterns from fMRI data.
11 / Research direction
Context-aware conversational agent
We develop conversational agents that use context and location to generate relevant responses.
Research support
Selected federal funding
NSF/IIS 2504264: Collaborative Research: III: Medium: Advancing Large Language Model Unlearning: Foundations and Applications, 10/01/2025 - 09/30/2029, Total amount: $800,000, Role: PI (33%).
HRSA/5U1QHP53070-02-00 A.G.R.E.E.D. (Applied Gerontology Research and Education to Eliminate Disparities)-GWEP. 07/01/2024 - 06/30/2027, Total amount: $2,000,000, Role Co-I (10%).
NIH/R33HD105610: Severity Predictors Integrating salivary Transcriptomics and proteomics with Multi neural network Intelligence in SARS-CoV2 infection in Children (SPITS MISC), 01/01/2023-12/31/2025. Role: MPI, $1,449,684, 33%.
NSF/ITE 2235225: NSF Convergence Accelerator Track H: Leveraging Human-Centered AI Microtransit to Ameliorate Spatiotemporal Mismatch between Housing and Employment for Persons with Disabilities. 12/15/2022 - 11/30/2023, Total amount: $613,621, Role: co-PI.
NSF/IIS 2211897: Collaborative Research: HCC: Small: Understanding Online-to-Offline Sexual Violence through Data Donation from Users. 10/01/2022-09/30/2026, Total amount: $600,000, Role: PI (33%).
NIH/R61HD105610, “Severity Predictors Integrating salivary Transcriptomics and proteomics with Multineural network Intelligence in SARS-CoV2 infection in Children (SPITS MISC)”, 33% share of $1,433,469, 2021 - 2023, MPI.
NSF/CNS 2043611, “SCC-CIVIC-PG Track A: Leveraging AI-assist Microtransit to Ameliorate Spatiotemporal Mismatch between Housing and Employment.” 25% share of $49,898 (Principal Investigator).
NSF/CCF: S&CC: Promoting a Healthier Urban Community: Prioritization of Risk Factors for the Prevention and Treatment of Pediatric Obesity. 09/01/2016-08/31/2019. 33% share of $200,000 (co-Principal Investigator)
NSF/IIS: S&AS: INT: Autonomous Battery Operating System (ABOS): An Adaptive and Comprehensive Approach to Efficient, Safe, and Secure Battery System Management. 10% share of $1,249,998, 09/01/2017-08/31/2021. (Senior Personnel)
NSF/CCF: EAGER: A novel algorithmic framework for discovering subnetworks from big biological data. 08/15/2014-08/14/2017. (Principal Investigator)
NIH/NLM: R21.A new informatics paradigm for reconstructing signaling pathways in human disease. 09/2009 – 08/2012. (Principal Investigator)
NIH/NCI: R01. Analysis of Epstain-Barr virus type III latency on cellular miRNA gene expression. (co-Investigator)
NSF/CCF: CPATH: A verification based learning model that enriches CS and related undergraduate programs. (co-Principal Investigator)