Ontology matching (OM) plays a key role in enabling data interoperability and knowledge sharing, but it remains challenging due to the need for large training datasets and limited vocabulary processing in machine learning approaches. Recently, methods based on Large Language Model (LLMs) have shown great promise in OM, particularly through the use of a retrieve-then-prompt pipeline. In this approach, relevant target entities are first retrieved and then used to prompt the LLM to predict the final matches. Despite their potential, these systems still present limited performance and high computational overhead. To address these issues, we introduce MILA, a novel approach that embeds a retrieve-identify-prompt pipeline within a prioritized depth-first search (PDFS) strategy. This approach efficiently identifies a large number of semantic correspondences with high accuracy, limiting LLM requests to only the most borderline cases. We evaluated MILA using the biomedical challenge proposed in the 2023 and 2024 editions of the Ontology Alignment Evaluation Initiative. Our method achieved the highest F-Measure in four of the five unsupervised tasks, outperforming state-of-the-art OM systems by up to 17%. It also performed better than or comparable to the leading supervised OM systems. MILA further exhibited task-agnostic performance, remaining stable across all tasks and settings, while significantly reducing LLM requests. These findings highlight that high-performance LLM-based OM can be achieved through a combination of programmed (PDFS), learned (embedding vectors), and prompting-based heuristics, without the need of domain-specific heuristics or fine-tuning.

In contrast to single-skill tasks, long-horizon tasks play a crucial role in our daily life, e.g., a pouring task requires a proper concatenation of reaching, grasping and pouring subtasks. As an efficient solution for transferring human skills to robots, imitation learning has achieved great progress over the last two decades. However, when learning long-horizon visuomotor skills, imitation learning often demands a large amount of semantically segmented demonstrations. Moreover, the performance of imitation learning could be susceptible to external perturbation and visual occlusion. In this paper, we exploit dynamical movement primitives and meta-learning to provide a new framework for imitation learning, called Meta-Imitation Learning with Adaptive Dynamical Primitives (MiLa). MiLa allows for learning unsegmented long-horizon demonstrations and adapting to unseen tasks with a single demonstration. MiLa can also resist external disturbances and visual occlusion during task execution. Real-world robotic experiments demonstrate the superiority of MiLa, irrespective of visual occlusion and random perturbations on robots.

Montreal, March 20, 2023 – Mila – Quebec Artificial Intelligence Institute and the United Nations Educational, Scientific and Cultural Organization (UNESCO) today unveiled at Mila a joint book on the urgent need for a better governance of artificial intelligence (AI) in the face of unprecedented technological change. The book, Missing Links in AI Governance, includes 18 articles on AI governance written by academics, civil society representatives, innovators and policy makers at a time when technological revolutions provide new scientific, economic and social opportunities while raising ethical questions and posing regulatory challenges. The book explores themes such as the influence of AI on indigenous and LGBTI communities, the necessary inclusion of Southern countries in global governance or the use of AI to support innovation for socially beneficial purposes. It maps out possible solutions to foster an AI development that is ethical, inclusive, and respectful of human rights. The authors also warn against the use of AI in potentially harmful contexts like autonomous weapons or the manipulation of digital content for social destabilization, deplore the increasing centralization of decision-making power in the development of AI systems and biases embedded in them, and the lack of transparency and accountability in the industry.

Reinforcement learning (RL) is an area of machine learning that focuses on training intelligent agents using related experiences so they can learn to solve decision making tasks, such as playing video games, flying stratospheric balloons, and designing hardware chips. Due to the generality of RL, the prevalent trend in RL research is to develop agents that can efficiently learn tabula rasa, that is, from scratch without using previously learned knowledge about the problem. However, in practice, tabula rasa RL systems are typically the exception rather than the norm for solving large-scale RL problems. Large-scale RL systems, such as OpenAI Five, which achieves human-level performance on Dota 2, undergo multiple design changes (e.g., algorithmic or architectural changes) during their developmental cycle. This modification process can last months and necessitates incorporating such changes without re-training from scratch, which would be prohibitively expensive.

Founded by Professor Yoshua Bengio of the Université de Montréal, Mila rallies researchers specializing in the field of artificial intelligence. Recognized globally for its significant contributions to deep learning, Mila has distinguished itself in the areas of natural language processing, object recognition and generative models. In addition to its academic training and fundamental research focus, Mila's mission is to contribute to Quebec and Canada's economic development through technology transfer and business innovation. As part of Mila's Applied Machine Learning Research team, the candidate will manage a team of researchers working with industrial partners to build machine learning-based proofs of concept. The projects selected by the team cover a wide range of domains, are in general highly challenging at the scientific level and can lead to publications.

MONTREAL, March 16, 2021 /CNW/ - Amgen announced today that it has entered into a multi-year partnership with Mila – Quebec Artificial Intelligence Institute. One of the world's leading biotechnology companies, Amgen uses cutting-edge science and technology to discover and develop innovative therapeutics, and AI is currently deployed in several of its R&D and manufacturing activities. This new partnership will permit Amgen to expand its knowledge of AI and deep learning by interacting and engaging with experts in Mila's unique ecosystem, both virtually and (eventually) on the Mila campus in Montreal. This announcement was made during Effervescence 2021, an international virtual gathering of scientists, entrepreneurs and industry professionals from the life sciences and health technology sectors in the presence of the Quebec Minister of Economy and Innovation, Pierre Fitzgibbon. "We are very happy to have signed this partnership with Mila," said Philip Tagari, Amgen's Vice President of Research, Therapeutic Discovery.

This week our reviews cross several categories: first up, Andrew Tarantola drove the VW ID.4 EV around the Bay Area to see how Volkswagen fared with a compact SUV. Meanwhile, Nicole Lee found a lot to like about Mila's smart air purifier, which has several themed filters and modes that can be customized. Billy Steele listened to Bose's new Sport Open Earbuds, which are designed to sit just outside the ear to allow for better awareness of one's surroundings. And in a quest for better home security, Devindra Hardawar installed Arlo's Video Doorbell and Pro 3 cameras around his home to check out what the system could do. Nicole also considered several smart lights and clocks to see which deserves a spot on your nightstand, and I tested four smart white noise makers designed to be used in a nursery. After driving the VW ID.4 EV, Andrew Tarantola concluded that it's a solid first attempt at a practical electric car from the German automaker.

Quebec Artificial Intelligence Institute (Mila) and IBM have teamed up to accelerate artificial intelligence (AI) and machine learning research using open-source technology. Mila and IBM have been collaborating since early 2020 on a project that is meant to make a key component of AI, known as hyperparameter optimization, more accessible. The organizations claim that this would improve machine learning model performances and pinpoint within the'black box' of AI where models need work. "A collaboration with…IBM is a great opportunity to accelerate the development of an open-source solution…initiated at Mila." – Yoshua Bengio, Mila The two organizations are looking to integrate the Quebec institute's open-source software, Oríon, with IBM's Watson Machine Learning Accelerator, an AI model training and inference tool that the tech giant offers to businesses. The overall goal, they claim, is to "improve the development, deployment, and ongoing management of complex AI and deep learning models, as well as to make tools more accessible to a larger base of scientists, engineers, and developers through automation."

The number of artificial intelligence (AI) researchers in Canada's private sector is proportionally higher than that of other countries, according to Montreal-based Element AI's 2020 Global AI Talent Report. The report found that Canada has 367 AI researchers, making it second only to the US. The Global AI Talent Report measured the size of the available talent pool in the AI industry through self-reported data on social media and demand via the monthly total job postings for the same role up to August 2020. The goal of the report is to assess the most current global patterns for the worldwide AI talent pool. The report tracked 477,956 people worldwide working in the AI industry, of which 61 percent worked in productization, 38 percent in engineering, and a mere one percent in research.

Yoshua Bengio is recognized as one of the world's leading experts in artificial intelligence and a pioneer in deep learning. Since 1993, he has been a professor in the Department of Computer Science and Operational Research at the Université de Montréal. He is the founder and scientific director of Mila, the Quebec Institute of Artificial Intelligence, the world's largest university-based research group in deep learning. He is a member of the NeurIPS board and co-founder and general chair for the ICLR conference, as well as program director of the CIFAR program on Learning in Machines and Brains and is Fellow of the same institution. In 2018, Yoshua Bengio ranked as the computer scientist with the most new citations, worldwide, thanks to his many publications.