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.

A major obstacle to the advancements of machine learning models in marine science, particularly in sonar imagery analysis, is the scarcity of AI-ready datasets. While there have been efforts to make AI-ready sonar image dataset publicly available, they suffer from limitations in terms of environment setting and scale.

We further extend Kaleidoscope to critic ensembles in the context of actor-critic algorithms, which could help improve value estimations.

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

This work presents Depth Anything V2 .