This project will create a privacy-preserving AI coding assistant that runs directly on a user’s computer instead of relying on cloud services. Many organizations, such as governments and healthcare providers, cannot use cloud-based AI tools because of data security and confidentiality concerns. The system will automatically detect the user’s hardware (CPU, GPU, memory) and select […]

(1) the main activities of the partner ServiceNow develops a platform for client organizations to manage and automate large-scale processes across various industries. In 2020, ServiceNow acquired Element AI to strengthen its presence in the Artificial Intelligence (AI) research landscape and the Canadian AI ecosystem. This acquisition enabled the development of AI-driven products that improve […]

Les systèmes de simulation en temps réel sont essentiels pour valider la stabilité des réseaux de production et transport d’électricité et la contribution de l’équipement de production électrique à la stablité de tension, de puissance et de fréquence (alternateurs, régulateurs de vitesse, régulateurs de tension et stabilisateurs de puissance). Or, l’interface actuelle utilisée par l’entreprise […]

GenAI-Counselor is an AI-powered genetic counseling assistant developed by Ebovir Biotechnologie Inc. to bridge the gap between complex genetic test results and patient understanding. By combining domain-specific knowledge bases (e.g., ACMG, ClinVar, GeneReviews), report parsing, personalized patient modeling, retrieval-augmented generation (RAG), and large language models (LLMs), the system delivers clear, clinically grounded explanations of genetic […]

This project is designed to provide a baseline dataset for fish processing stations on Southern Vancouver Island. From this dataset, researchers aim to identify broad-scale trends in nearshore marine systems and identify future research needs. Main objectives of the project include monitoring both seal behaviour and fish waste subsidies near these recreational fish processing stations […]

This study focuses on enhancing aviation safety by detecting and analyzing runway incursions—unauthorized entries of aircraft, vehicles, or personnel onto active runways—using high-resolution ADS-B data from Flightradar24 (FR24). Despite existing protocols, such incursions remain a significant threat to air traffic operations. The project aims to develop and validate algorithms capable of identifying critical events, such […]

As multi-agent systems become more complex, improving how Large Language Model (LLM)-based agents work together is increasingly important. This research focuses on creating reusable design patterns and adaptive coordination strategies to boost collaboration and system performance. Blend360 is an AI service provider that builds advanced solutions for clients in sectors like finance, healthcare, and consumer […]

This project aims to make mass timber buildings, a sustainable alternative to concrete and steel, even more reliable. While mass timber is great for the environment, we don’t fully understand how it handles moisture over time, which can affect its durability. Our project will tackle this by using advanced sensors to monitor a new mass […]

Sturgeon Bank is a Wildlife Management Area within the unceded traditional territories of the Coast Salish peoples, and west of the City of Richmond, British Columbia. Sturgeon Bank is primarily comprised of intertidal marsh, mud flats and open water, and provides several ecological and coastal risk mitigation benefits. However, monitoring indicates that Sturgeon Bank’s salt […]

Faulting might be affecting the flow of injected CO2 into the subsurface at the Aquistore Carbon Capture and Storage facility in southeastern Saskatchewan. 3D seismic data indicate that faulting affects the Deadwood Sandstone injection target approximately 100 m to the west of the injection well. The seismic data cannot however image all the structural complexity […]

Knowledge graphs are a means of structuring semantic knowledge that can be used to increase AI reliability. In our applications, Large Language Model (LLM) chatbots are not on their own able to meet 100% accuracy goals for our scenarios, and we use the knowledge graph to reflectively validate answers before presenting them to the user. […]

Ce projet de recherche propose une analyse de la trajectoire de Transition en Commun (TeC), une alliance intersectorielle montréalaise qui concentre ses efforts à la transition socio-écologique. En tant qu’initiative urbaine qui mobilise un large éventail d’acteurs TeC constitue un espace privilégié pour mieux comprendre les modalités d’émergence, de structuration et d’engagement des collectifs dans […]