Description
The competition aims to bridge the knowledge gap between computer and AI scientists and energy experts by providing a risk-based energy resource management framework where CI experts can test their metaheuristic algorithms and evaluate their efficacy in real-world problems beyond the typical benchmark CI problems.

Contact:
José Almeida, GECAD, LASI, Polytechnic of Porto (jorga[at]isep.ipp.pt)

Competition link
Here is the competition link: Click Here

Description
Join our exciting competition where your creativity meets cutting-edge AI! We're challenging participants to harness the power of large language models to design next-generation evolutionary algorithms. Dive into this innovative space, showcase your skills, and help shape the future of optimization technology.

Contact:
Adam Viktorin, Tomas Bata University in Zlin, Czech Republic (aviktorin[at]utb.cz)

Competition link
Here is the competition link: Click Here

Description
This is an energy consumption forecast competition that uses real smart building data to assess the quality of novel data preprocessing techniques and forecasting models. One year of real data will be made available for the participants.

Contact:
Luis Gomes, GECAD, LASI, Polytechnic of Porto (Lfg[at]isep.ipp.pt)

Competition link
Here is the competition link: Click Here

Description
In autonomous drone racing, the drone must navigate through a series of gates in an unknown environment fully autonomously, minimizing time while avoiding collisions and relying solely on onboard sensors. The first challenge involves designing intelligent controllers to navigate the drone through a sequence of gates at high speed. The second challenge seeks to create gate detection methods that can accurately estimate the location of gates in a sequence of images under various illumination conditions.

Contact:
Asst. Prof. Andriy Sarabakha, Aarhus University, Denmark (andriy[at]ece.au.dk)

Competition link
Here is the competition link: Click Here

Description
This student competition focuses on developing Explainable AI (XAI) models for predicting drug responses from cancer genomic data, addressing the challenge of AI’s "black-box" nature in clinical settings. The goal is to improve transparency, making AI decisions more interpretable for clinicians. By bridging AI research and clinical practice, the competition aims to enhance trust and outcomes in personalized cancer medicine.

Contact:
Dr. Arvind Mer University of Ottawa, Canada (amer@uottawa.ca)

Competition link
Here is the competition link: Click Here