Research Areas

Our interdisciplinary research teams work at the intersection of machine learning, computer vision, natural language processing, and ethics to develop AI systems that are more capable, interpretable, and beneficial.

Computer Vision & Perception

Advancing the state-of-the-art in visual understanding, 3D perception, and scene reconstruction.

Current Projects

PhysNav-DG: Explainable AI & Sensor Fusion for NavigationCompleted

A novel system for multimodal embodied navigation using a VLM-based sensor fusion framework.

MD-NEX v2Active

Developing a benchmark and dataset for multimodal embodied navigation.

Natural Language Processing

Developing more capable, interpretable, and efficient language models and dialogue systems.

Current Projects

GenECA: Generalizable Embodied Conversational AgentsActive

A framework for creating multimodal conversational agents that can adapt to different contexts.

Semantic Web for UI Element AnnotationCompleted

Leveraging semantic web technologies to improve automated annotation of UI elements.

AI Ethics & Safety

Ensuring AI systems are developed and deployed responsibly, with a focus on fairness and transparency.

Current Projects

CPS-Guard: Dependability Assurance for AI SystemsCompleted

Multi-role orchestration system for ensuring the safety and reliability of AI in cyber-physical systems.

LDM-Bench: A Comprehensive Benchmark for Demographic-Based Discrimination in Legal AIPlanning

A benchmark for evaluating demographic-based discrimination in legal AI systems.

Applied ML Research

Translating cutting-edge ML research into practical applications that solve real-world problems.

Current Projects

ML for Climate Change MitigationActive

Applying machine learning techniques to optimize energy usage and reduce carbon emissions.

Healthcare Diagnostics with Limited DataPlanning

Developing diagnostic tools that can work effectively with limited training data.

Research Highlights

Explore some of our most impactful recent research projects and publications.

Research Visualization

PhysNav-DG: Robust VLM-Sensor Fusion

A novel framework for combining vision-language models with sensor data for robust navigation in challenging environments.

Read the paper

Research Visualization

GenECA: Multimodal Conversational Agents

A general-purpose framework for creating adaptive multimodal embodied conversational agents with real-time capabilities.

Read the paper

Research Visualization

CPS-Guard: Dependability Assurance

A multi-role orchestration system for ensuring the safety and reliability of AI in cyber-physical systems.

Read the paper