Make any backbone architecture Lorentz-equivariant with minimal computational cost, with applications in high-energy physics

DynaMix, a novel pre-trained foundation model for zero-shot inference of dynamical systems, outperforms time series foundation models in terms of long-term statistical properties, forecasts, and inference times.

We introduce a structure-based generative model for sampling protein conformations efficiently and eliminate the need for pre-training and evolutionary information.