Computing properties of molecular systems rely on estimating expectations of the (unnormalized) Boltzmann distribution. Molecular dynamics (MD) is a broadly adopted technique to approximate such quantities. However, stable simulations rely on tiny integration time steps (10^(−15)s), whereas convergence of some moments, e.g., binding free energy or rates, might rely on sampling processes on time scales as long as 10^(−1)s, and these simulations must be repeated for every molecular system independently. We recently proposed Implicit Transfer Operator (ITO) Learning [1], a framework to learn surrogates of the simulation process with multiple time resolutions. Our initial work shows that ITO models can simulate challenging molecular systems, such as fast-folding proteins, with time steps at least six orders of magnitude larger than traditional molecular dynamics [1]. We implement ITO models using denoising diffusion probabilistic models with bespoke SE(3) equivariant architectures. While the ITO architecture, in principle, allows for training general models that work for all molecules, current datasets have been missing. This deficiency limits current ITO models to be molecule specific and their application potential in drug and material design. We aim to generate a dataset and train the first-ever transferable ITO models. Such a model would open up tremendous potential for applications and lower the computational needs to study the properties of molecules. Our group has experience with ITO models and transferable generative models for molecules. Simon Olsson (PI) and Mathias Schreiner (joining as a postdoc) initially proposed and implemented the ITO framework. Simon Olsson and Juan Viguera Diez (Ph.D. student) have previous experience with transferable generative models for molecular structures [2]. We have implemented a project pilot showing promising preliminary results [3]. This figure compares the histograms of internal coordinates between a transferable ITO model (blue) and an MD trajectory (orange) for an unseen molecule, showing remarkable agreement. [1] Mathias Schreiner, Ole Winther and Simon Olsson. Implicit Transfer Operator Learning: Multiple Time-Resolution Surrogates for Molecular Dynamics. Advances in Neural Information Processing Systems 36 [2] Viguera Diez J, Romeo Atance S, Engkvist O, Mercado R, Olsson S. A transferable Boltzmann generator for small-molecules conformers. ELLIS Workshop AI4Molecules https://cloud.ml.jku.at/s/sKtfdFpoTp9F7sJ [3] Viguera Diez J, Romeo Atance S, Engkvist O, Olsson S. Generation of conformational ensembles of small molecules via Surrogate Model-Assisted Molecular Dynamics. In press...Machine Learning: Science and Technology