Research Opportunities
Our lab offers exciting opportunities for undergraduate and graduate students to engage in cutting-edge research at the intersection of artificial intelligence, machine learning, and scientific discovery. We are committed to fostering a collaborative environment where students can develop their research skills, publish their work, and contribute to advancing the field.
Research Areas in Our Lab
🔬 Multi-fidelity Learning for Semiconductor Innovation
We develop intelligent surrogate modeling frameworks where machine learning agents substitute for computationally intensive simulations. Our work has achieved significant breakthroughs in semiconductor device performance through physics-informed machine learning.
Current Projects:
- Active learning frameworks combining ML models with TCAD simulations
- Physics-informed ML for quantum device design with multi-scale optimization
- Multi-physics simulation workflows for 2DEG density enhancement
Skills You'll Develop:
- Physics-informed neural networks (PINNs)
- Scientific machine learning (SciML)
- Multi-fidelity surrogate modeling
- TCAD simulation tools
🤖 Multi-modal Scientific Discovery
We're pushing the boundaries of how AI systems comprehend and integrate different types of scientific data, from imaging and spectroscopy to electrical measurements.
Current Projects:
- LLAVA-DPO framework for visual-language scientific understanding
- Multi-modal integration for 2D materials characterization
- Graph neural networks with language models (ALIGN4DR system)
Skills You'll Develop:
- Computer vision and multimodal learning
- Large language models (LLMs)
- Graph neural networks
- Scientific data analysis
🎯 Interactive Learning Systems
We develop interactive frameworks that effectively capture and learn from expert preferences and domain insights, providing interpretable decision pathways in scientific discovery.
Current Projects:
- Multi-agent systems for heterogeneous data integration
- Interactive knowledge engineering for materials exploration
- Uncertainty quantification in AI-suggested designs
Skills You'll Develop:
- Reinforcement learning from human feedback (RLHF)
- Active learning methodologies
- Explainable AI (XAI)
- Uncertainty quantification
Interdisciplinary Collaborative Opportunities
🤝 Joint Research with Dean Taskin Kocak
Focus Areas: AI-Powered Energy Efficiency & Intelligent Network Optimization
Dean Taskin Kocak brings extensive expertise in computer networking, IoT systems, and energy-efficient computing. Our collaboration creates unique opportunities at the intersection of AI/ML and network systems.
Collaborative Research Topics:
- AI-Driven Smart Grid Optimization
- Machine learning for energy consumption prediction
- Reinforcement learning for dynamic load balancing
- Multi-agent systems for distributed energy management
- Integration of renewable energy sources using predictive analytics
- Intelligent IoT Network Design
- Deep learning for network traffic prediction and optimization
- Federated learning for privacy-preserving IoT analytics
- Edge computing optimization using lightweight ML models
- Anomaly detection in IoT sensor networks
- Sustainable Computing Systems
- ML-driven power optimization for data centers
- Green computing through intelligent resource allocation
- Energy-aware task scheduling using reinforcement learning
- Carbon footprint reduction through AI-optimized workflows
What Students Gain:
- Experience in both AI/ML and network systems
- Practical skills in IoT deployment and optimization
- Understanding of sustainable computing principles
- Opportunities to publish in both AI and networking venues
🧠 Joint Research with Dr. Soumyashree Sahoo
Focus Areas: AI for Healthcare & Multimodal Health Data Analytics
Dr. Sahoo specializes in ubiquitous computing, deep learning for health monitoring, and data-driven insights for mental health assessment. Our collaboration enables innovative research combining AI4Science methodologies with health informatics.
Collaborative Research Topics:
- Multimodal Health Monitoring Systems
- Integration of smartphone sensing data with clinical assessments
- Physics-informed neural networks for physiological signal processing
- Time-series analysis for depression treatment outcome prediction
- Multi-fidelity modeling combining wearable data and clinical markers
- Explainable AI for Clinical Decision Support
- Interpretable deep learning models for mental health assessment
- Uncertainty quantification in treatment outcome predictions
- Active learning frameworks for personalized treatment recommendations
- Visual-language models for medical imaging and clinical notes integration
- Longitudinal Health Data Analytics
- Sequential prediction models for long-term health outcomes
- Transfer learning across different patient populations
- Missing data imputation using advanced ML techniques (GRU-D, BRITS)
- Domain adaptation for generalizable health prediction models
- Interactive Clinical Intelligence Systems
- Human-in-the-loop systems for clinician-AI collaboration
- Reinforcement learning for adaptive intervention strategies
- Multi-agent systems integrating diverse health data sources
- Real-time feedback mechanisms for treatment monitoring
What Students Gain:
- Experience in healthcare AI applications with real-world impact
- Skills in handling sensitive, privacy-preserving health data
- Understanding of clinical workflows and healthcare challenges
- Opportunities to contribute to mental health technology advancement
- Publication potential in both AI and medical informatics venues
Student Success Stories
🏆 Recent Student Achievements
Kadin Reed - Undergraduate Research Assistant
- Co-authored publication in Materials Science journal on ML-driven materials discovery
- Developed active learning framework for semiconductor optimization
- Presented research at regional AI conference
Toral Banerjee - Graduate Research Assistant
- First author publication in Nature on physics-informed neural networks
- Received Best Student Paper Award at international conference
- Now pursuing PhD at top-tier institution
💡 Our students regularly publish in top-tier venues and present at major conferences. We provide comprehensive mentorship, from research design to paper writing and presentation skills.
What We Offer
✅ Hands-on Research Experience
- Work on cutting-edge AI/ML projects with real-world applications
- Access to high-performance computing resources
- Exposure to state-of-the-art tools and frameworks
✅ Professional Development
- Co-authorship opportunities in high-impact publications
- Conference presentation opportunities
- Grant writing and proposal development experience
- Weekly research seminars and journal clubs
✅ Mentorship & Collaboration
- One-on-one guidance from faculty
- Collaborative environment with peer researchers
- Interdisciplinary research exposure
- Career development support (industry or academia)
✅ Flexibility
- Both full-time (graduate) and part-time (undergraduate) opportunities
- Summer research programs available
- Independent study credits available
- Remote collaboration options for certain projects
Who Should Apply
We welcome students from diverse backgrounds who are:
- Undergraduate Students: Interested in gaining research experience, preparing for graduate school, or exploring AI/ML applications
- Graduate Students: Seeking thesis/dissertation research opportunities in AI for science and engineering
- Computer Science Majors: With interests in machine learning, deep learning, computer vision, or NLP
- Engineering Students: Interested in computational methods and AI applications in their domains
- Data Science Students: Looking to apply analytics and ML to scientific discovery
- Mathematics/Physics Students: Interested in computational approaches to scientific problems
Preferred Qualifications:
- Strong programming skills (Python required; experience with PyTorch/TensorFlow preferred)
- Coursework in machine learning, data structures, or algorithms
- Self-motivated with strong analytical and problem-solving skills
- Good communication skills and ability to work in a team
- (Bonus) Experience with scientific computing, optimization, or domain-specific tools
How to Apply
Interested in joining our research team? Here's how to get started:
- Email Prof. Ron Lin at rongyu.lin@qu.edu
- Include the following:
- Your CV/resume
- Unofficial transcript
- Brief statement of research interests (1 page)
- Indicate your preferred research area and collaboration interest (if any)
- Expected start date and time commitment
- Optional Materials:
- Code samples or GitHub profile
- Relevant coursework projects
- Letters of recommendation (for graduate positions)
📧 Email Subject Line: "Research Opportunity - [Your Name] - [Undergraduate/Graduate]"
Contact Prof. Lin
View Our Publications
Frequently Asked Questions
Q: Can I join if I'm from outside Computer Science?
A: Absolutely! We welcome students from engineering, mathematics, physics, and other quantitative disciplines who are interested in AI/ML applications.
Q: Do I need prior research experience?
A: Not necessarily. We value enthusiasm, dedication, and willingness to learn. We provide training and mentorship to help you develop research skills.
Q: What is the expected time commitment?
A: For undergraduates, 8-12 hours/week during the semester and full-time during summer. For graduate students, research is typically a significant component of your program.
Q: Are these paid positions?
A: We have various funding mechanisms including research assistantships, independent study credits, and summer research fellowships. Discuss options during the application process.
Q: When can I start?
A: We accept applications year-round. Start dates are flexible based on project timelines and your availability.
Q: Can international students apply?
A: Yes! International students are encouraged to apply. We can discuss visa requirements and support during the interview.
Ready to Make an Impact?
Join us in advancing the frontiers of AI-driven scientific discovery
Get Started Today