A bio-inspired metaheuristic algorithm that mimics the soaring behavior of Andean Condors to solve complex optimization problems in manufacturing, continuous domains, and beyond.
What if algorithms could design themselves? AutoMH uses reinforcement learning to automatically create evolutionary metaheuristic algorithms that adapt and improve—sometimes outperforming human-designed solutions.
Helping conservation planners make data-driven decisions about where to establish protected areas to maximize biodiversity preservation with limited resources.
Evolutionary algorithms mimic natural selection to solve complex optimization problems. This ongoing research explores novel operators, hybrid approaches, and applications across diverse domains—from engineering design to machine learning optimization.
Can AI language models solve complex optimization problems? Exploring whether GPT and other transformers can generate constraint programming models that tackle real-world challenges.