Project Based Research Courses

ICME Project Based Research Courses

ICME offers several multidisciplinary graduate level courses designed to give students hands-on experience working in teams through real-world project-based research and experiential classroom activities. Students work in dynamic teams with the support of course faculty and mentors, researching preselected topics. The courses expose students to important techniques in computational math and data science as well as to the soft skills necessary for success such as values and ethics, unintended consequences and team building.

Students - ICME Graduate students gain valuable experience and mentorship they would not otherwise find in the classroom while working toward course credit.

Mentors - High quality, committed mentors are key to a project's success as they provide direction, quality data, expertise, and encouragement through weekly meetings.

Faculty - Each project is guided by an ICME Faculty to provide oversight and direction, which offers students and mentors a unique opportunity to work closely with ICME Faculty on valuable research.

Recent Project Videos

Publications

• Enhancing Security in Large Language Models:
  • Development and integration of the Tree of Attacks with Pruning (TAP) method into the PyRIT toolkit. Salma Zainana (ICME)
  • Adversarial Suffix Attack, a novel technique that involves appending meticulously designed suffixes to input sequences in order to influence the output of large language models (LLMs). Naijing Guo (ICME)
  • Students research contributed to the work behind the publication: A Brief Exploration of Data Exfiltration using GCG Suffixes.  
• Congenital Rubella Syndrome Does Not Increase with Introduction of Rubella-Containing Vaccine - Fan Liu (DBDS), Helen Gu (Stats), Xiaoying Shi (Epidemiology); Weian Yin (Stats); Nina Cruz (Stats); Benson Zu (ICME), Maximilian Sabayev (ICME)
• Interpretable Predictive Models to Understand Risk Factors for Maternal and Fetal Outcomes - Tomas M. Bosschieter (ICME), Zifei Xu (ICME)
• Individualized, self-supervised deep learning for blood glucose prediction - Johannes Fuest (Stats)
• Addressing Racial Bias in Facial Emotion Recognition - Alex Fan (Stats), Xingshuo Xiao (ICME)
• Audio-Based Emotion Recognition Using Self-Supervised Learning on an Engineered Feature Space - Peranut Nimitsurachat (ICME)
• TikTok for good: Creating a diverse emotion expression database - Bhavik Shah (ICME)
• Deconvoluting complex correlates of COVID-19 severity with a multi-omic pandemic tracking strategy - Xiran Liu (ICME), Jacob Edelson (DBDS), Douglas Russo (Stats), Justin Wong (Stats), Jessie Lauzon (Aero Astro)
• Combining international survey datasets to identify indicators of stress during the COVID-19 pandemic: A machine learning approach to improve generalization - Eric Yunan Zhao (Stats), Daniel Xia (ICME) 
• Biomedical Data Commons (BMDC) prioritizes B-lymphocyte non-coding genetic variants in Type 1 Diabetes - Pranav Bhardwaj (Stats)
• Predictive Models from Quantum Computer Benchmarks - Karthik Nataraj (ICME)

Thank you to our project mentors

Thank you to our ICME faculty sponsors