Dense Associative Memories are high storage capacity variants of the Hopfield networks that are capable of storing a large number of memory patterns in the weights of the network of a given size.

Time series forecasting has played a pivotal role across various industries, including finance, transportation, energy, healthcare, and climate.

Extracting scientific understanding from particle-physics experiments requires solving diverse learning problems with high precision and good data efficiency. We propose the Lorentz Geometric Algebra Transformer (L-GA Tr), a new multipurpose architecture for high-energy physics.

Finding fast and accurate approaches to solving Schrödinger equations is a central challenge in quantum chemistry, with far-reaching implications for material science and pharmaceutical development. The ability to solve this equation precisely would unlock a plethora of properties inherent to the microscopic systems being studied.

This heterogeneous nature presents challenges for a single model to accurately generate genomic sequences.