Mitigating hallucination in vision language models for autonomous systems

Autonomous systems such as intelligent vehicles and robotic platforms must reliably perceive their surroundings and reason about complex environments to make safe, informed decisions. Recent advances in Vision-Language Models (VLMs) and Vision-Language-Action (VLA) frameworks combine visual understanding with language-based reasoning, creating unified architectures for perception, interpretation, and decision-making. This integration enables autonomous agents to describe […]

Read More
Canadian Mass Timber Costing Guide

Mass timber – an innovative, wood-based alternative to concrete and steel – is key to building greener cities, but its widespread use in Canada is currently limited by uncertainty over construction costs. Developers and builders lack reliable, standardized data to compare the price of mass timber projects against traditional building methods and materials across different […]

Read More
Implementation of multi-centre clinical trials in orthopaedic trauma

This research internship is offered within the Division of Orthopaedic Surgery under the supervision of Dr. Sheila Sprague, PhD. The program focuses on clinical research aimed at improving outcomes and quality of life for patients with musculoskeletal injuries through multiple ongoing clinical trials, including Beads vs. Vac, FLAP-ATTACK, FASTER-HIP, SWRCT, and studies on pelvic fracture […]

Read More
Data-Driven Disaggregation of HP Loads in Transmission Systems with Limited Data

This project develops AI- and data-driven methods to improve visibility of heat pump (HP) loads in power grids. By disaggregating HP consumption from aggregate smart meter and grid data, it will support accurate demand forecasting, reliable grid operation, and planning for heating electrification in cold climates, contributing to reduced greenhouse gas emissions.

Read More
Commercializing CO2-Derived Clay Polymer for Agricultural Applications

This project between McMaster University and Carbon Upcycling Technologies (CUT) aims to commercialize sustainable agricultural products made from captured CO2. The team will assess markets for sprayable clay–polymer coatings that protect crops from UV damage and clay-based soil conditioners that improve water and nutrient retention. The outcomes will guide pilot partnerships and help CUT scale […]

Read More
Quantum Machine Learning for Computational Drug Discovery

Drug discovery is traditionally slow, costly, and high-risk, with timelines exceeding a decade and expenses reaching billions. This lag is particularly problematic for neglected diseases and cardiovascular conditions, which carry significant global burdens but attract limited research investment. To address this, the project proposes leveraging quantum computing and hybrid quantum-classical algorithms to accelerate drug discovery. […]

Read More
Comparing the performance of UAV-derived statistical models with established mechanistic models to measure microclimatic conditions in open and closed canopy environments

Climate change is reshaping ecosystems, yet regional climate data often overlook the fine-scale temperature patterns that species actually experience. These local variations, or microclimates, are influenced by vegetation, topography, and land cover, and can shield organisms from extreme conditions. This project aims to improve how we model and map microclimates using high-resolution drone imagery. We […]

Read More
AI-Driven Compliance Automation Platform for Cybersecurity and Privacy Standards

Organizations today face increasing difficulty keeping up with cybersecurity and privacy rules such as ISO 27001, SOC 2, GDPR, and Canada’s PIPEDA. Meeting these requirements is often slow, expensive, and prone to human error because compliance checks are still done mostly by hand. To address this, Carleton University and Sabytel Technologies Inc. are working together […]

Read More
Porous Structure Modeling

This project focuses on developing better computer models to predict how recycled concrete can store and transfer heat for use in thermal energy storage (TES) systems. Instead of relying only on expensive and time-consuming experiments, the project will create more accurate and efficient simulation methods that can speed up the design of sustainable energy storage […]

Read More
Exploration of the Use of Artificial Intelligence in Small, Rural Northern Municipality

The proposed project aims to modernize the Township of Terrace Bay’s records and data management systems by integrating AI-powered tools that streamline operations and enhance decision-making. Currently reliant on manual processes and limited digital infrastructure, the municipality faces challenges in organizing, analyzing, and retrieving key service data. This initiative will introduce automated classification systems, predictive […]

Read More
Artificial Intelligence-Driven Predictive Modeling for Canine Pain Assessment and Personalized Analgesic Recommendations

Accurately assessing and managing pain in dogs is one of the most challenging aspects of veterinary medicine because animals cannot verbally communicate their discomfort. Current methods rely heavily on behavioral observations and standardized scoring tools, which are often subjective and prone to inconsistencies. This project aims to address these limitations by developing an AI-powered predictive […]

Read More