Funded Projects
The Jurist Center provides research support for the following projects:
2024
-
Enhancing Transparency and Interpretability in Autonomous Driving
(Xin Hu, Zhengming Ding):
For autonomous driving, achieving high performance is paramount, but interpretability is equally crucial in safety-critical domains. This project explores integrating implicit visual-semantic interpretation with explicit human annotation to enhance transparency and interpretability in autonomous driving decision-making.
-
Geographical Adaptation of Language Models
(Xintian Li, Aron Culotta):
This project develops new domain adaptation models that learn location attributes, allowing machine learning classifiers to be transferred to new geographical regions. Applications include analyzing evacuation behaviors during hurricanes and sentiment towards vaccines during the COVID epidemic.
-
Machine Learning to Predict Indirect Call Site Targets for Software Security
(Cristian Garces, Jiang Ming):
This research aims to accurately predict/resolve indirect call site targets in software, addressing a key challenge in security and software verification. The outcome may benefit tasks like malware analysis and program integrity hardening.
-
Computational Epitome Prediction
(Jairui Li, Ramgopal Mettu):
This project develops data-driven models to predict cancer mutations to target for therapy. The research focuses on utilizing GPU computing and sophisticated ML-inspired sampling schemes to achieve real-time speeds in analyzing protein conformational stability.
-
AI-Based Diagnostic Systems for Skin Disease Detection
(Janet Wang, Jihun Hamm):
This project develops equitable and reliable AI-based diagnostic systems for skin diseases, focusing on improving performance and reliability through transfer learning and diffusion generative models.
-
Graph Sampling Distances for Map Merging
(Erfan Hosseini, Carola Wenk):
This project develops algorithms to merge roadmaps of the same city into one overall roadmap. The work leverages graph sampling distances to address the map merging problem, providing a unique geometric lens to this AI/DS challenge.
-
Improving Ride Sharing with Reinforcement Learning
(Tianyi Xu, Zizhan Zheng):
This project investigates predictive reinforcement learning (RL) to enhance ride-sharing. The focus is on ensuring robust learning and decision-making by utilizing predictive information like weather and traffic forecasts.
-
Improving Peer Selection
(Harper Lyon, Nicholas Mattei):
This project develops new algorithms for peer selection in scenarios where agents must choose a subset of themselves for an award or prize, ensuring impartiality and fairness.
2023
-
Graph Neural Networks for Software Security
(Cristian Garces, Jiang Ming):
This project applies deep learning to resolve indirect control flow in software security analysis, translating the problem into a graph's edge prediction problem.
-
Calibrating Deep Learning Models
(Yunbei Zhang, Jihun Hamm):
The student worked on calibrating deep learning models to improve the reliability of predicted confidence outputs, establishing best practices for implementing calibrated models across various domains.
- Publication: Analysis of Task Transferability in Large Pre-trained Classifiers, Workshop on Mathematics of Modern Machine Learning (M3L) at NeurIPS 2023
- Publication: On the Fly Neural Style Smoothing for Risk-Averse Domain Generalization, IEEE/CVF Winter Conference on Applications of Computer Vision 2024
-
Making Human-Like Moral Decisions
(Disa Sariola, Nicholas Mattei):
This project analyzes human subjects' data to guide automated decision-making in ethically constrained environments, aiming to develop AI agents that mimic human behavior in moral decision-making.
-
Forecasting Vaccination Decisions using Social Media
(Xintian Li, Aron Culotta):
This project develops NLP methods to extract vaccination intent from social media and forecasts how intent will evolve during the pandemic.
-
Improving the Efficiency of Large Language Models
(Sofiia Druchyna, Lu Peng):
This project analyzes LLM models running on GPUs, examining trade-offs between resource usage, power consumption, and model accuracy to propose more efficient model architectures.
2022
-
Computational Epitome Prediction
(Avik Bhattacharya, Ramgopal Mettu, Sam Landry):
This project predicts cancer mutations for therapy targeting, enabled by large-scale data collection and predictive model implementation.
-
Understanding Emerging Issues in Public Schools from Online Reviews
(Linsen Li, Aron Culotta, Nicholas Mattei):
This project analyzes online reviews to predict changes in school demographics and test results, offering insights into family decision-making and educational inequities.
-
Robust Reinforcement Learning for Security
(Xiaolin Sun, Zizhan Zheng, Nicholas Mattei):
This project investigates how randomized smoothing can help obtain policies with certified adversarial robustness for reinforcement learning tasks subject to state perturbation attacks.
Faculty Profiles
Our faculty lead projects across a broad array of artificial intelligence topics, including machine learning, multi-agent systems, computer vision, natural language processing, visualization, and ethics. Below is a sample of such projects:
- Learning to Secure Cooperative Multi-Agent Learning Systems: Advanced Attacks and Robust Defenses, Zizhan Zheng
- Fair Recommendation Through Social Choice, Nicholas Mattei
- Mechanisms and Algorithms for Improving Peer Selection, Nicholas Mattei
- Modeling and Learning Ethical Principles for Embedding into Group Decision Support Systems, Nicholas Mattei
- Machine Learning for Advanced Manufacturing, through the Louisiana Materials Design Alliance, Jihun Hamm
- Quantifying Morphologic Phenotypes in Prostate Cancer - Developing Topological Descriptors for Machine Learning Algorithms, Carola Wenk, J. Quincy Brown, Brian Summa
- Scalable, Content-Based, Domain-Agnostic Search of Scientific Data through Concise Topological Representations, Brian Summa
- Scalable Interactive Image Segmentation through Hierarchical, Query-Driven Processing, Brian Summa
- Predicting Real-time Population Behavior during Hurricanes Synthesizing Data from Transportation Systems and Social Media, Aron Culotta
- Quantifying Multifaceted Perception Dynamics in Online Social Networks, Aron Culotta
- Understanding the Relationship between Algorithmic Transparency and Filter Bubbles in Online Media, Aron Culotta
- Reducing Classifier Bias in Social Media Studies of Public Health, Aron Culotta
