In response to the escalating demand for clean tech and energy-efficient structures, our project focuses on revolutionizing building data processing for swift decarbonization planning. We tackle the challenge by parsing diverse data from mixed media documents and fine-tuning pre-trained large language models (LLMs) for optimal data query accuracy. Our approach integrates text parsing, tokenization, and […]

This project aims to enhance the work with technical drawings in manufacturing is done by using advanced computer techniques to automatically identify and read text within these drawings. This means turning detailed plans and sketches into digital data quickly and accurately, without manual input. For the partner organization, this innovation promises to greatly speed up […]

“THIS IS A GENERIC TEXT PUT IN PLACE AS THERE WAS NO PROJECT OVERVIEW”

“THIS IS A GENERIC TEXT PUT IN PLACE AS THERE WAS NO PROJECT OVERVIEW”

In recent years, large language models (LLMs) have significantly impacted text-related tasks, including translation, code generation, and answering questions. However, due to their computational demands, these models are typically available only through closed doors-APIs, with opaque operations that obscure data usage. This creates privacy concerns for users who frequently engage with these models, as their […]

This project isto develop a new website which will provide an infrastructure for non-profit admission. The admission professionals will be using this websites to conduct the interviews, in terms of providing them with the guiding question. The use of check boxes and other visual tools, such as radio buttons, text boxes, etc. will help provide […]

This project is meant to develop a Hybrid AI Platform for Streamlining Evaluation (HAIPSE) of applications assisting the partner organization, The NIB Trust Fund, in processing the two categories of funding applications. The NIB Trust Fund supports education programs of the First Nation and Métis individuals and organizations aimed at healing, reconciliation, and knowledge building. […]

Generating synthetic data is important for a number of machine learning problems at Mastercard especially in the areas of additional data generation for imbalanced problems, data sharing etc. The data is mostly tabular in nature and a number of techniques exist for generating tabular data in the literature. However most of these techniques do not […]

Careful operational planning is essential for making agriculture autonomous and sustainable. The movements of agricultural equipment in the farm can be optimized to increase productivity and reduce costs and greenhouse gas (GHG) emissions. The aim of this project is to develop and productize advanced optimization algorithms to determine the best end-to-end machine routes, positions of […]

Le numérique est désormais omniprésent dans nos activités quotidiennes. Nombreuses de nos actions sont numérisées, analysées et assistées par un ordinateur. Or, nous produisons de plus en plus de logiciels et les bugs (ou souvent les défauts de spécification) sont largement sous-estimés. La tendance en effet et à produire des mises à jour (parfois quotidiennes, souvent hebdomadaires) plutôt […]

This project develops and benchmarks novel offline training algorithms for AI navigation in gaming environments. As such, it is intended to be a self-contained project. Traditional video game navigation heavily relies on navigation meshes (navmeshes) for pathfinding. Navmeshes offer a simplified representation of complex environments but face limitations in portraying nuanced navigation abilities, such as […]

Meeting the climate change timetable of emission reductions entails significant investment in the current building stock. Knowing what should be done to improve the efficiency of and reduce emissions from these buildings needs easily accessible and user-friendly tools. We propose delivery of such a tool. We aim to produce a portal that allows a wide […]