Improved accuracy for the Deep Learning-aided many-body dispersion (DNN-MBD) correction to DFT. DNN-MBDQ goes beyond dipole including quadrupole polarizability (Q) terms via a generalized Random Phase Approximation (RPA) formalism. @PierPoier@jppiquem
https://t.co/bhph1BTBqC
#compchem Just out in #jpclett@JPhysChem (#OpenAccess ) : Generalized Many-Body Dispersion Correction through Random-phase Approximation for Chemically Accurate DFT. Introducing the DNN-MBDQ model including quadrupole corrections. Great work by @PierPoier https://t.co/mEW9kbzSU4
#compchem🚨#preprint🚨:Force-Field-Enhanced Neural Network Interactions: from Local Equivariant Embedding to Atom-in-Molecule properties & long-range effects. Great work by @Thomas__Ple introducing the hybrid physically-driven #machinelearning FENNIX model https://t.co/W8o1DcItec
#compchem Excited to share our new #preprint. Pushing the accuracy of Deep Learning-aided many-body dispersion correction for Density Functional Theory: inclusion of quadrupole polarizabilities through Random Phase Approximation. Stellar work by @PierPoier https://t.co/Sj5Ah0OQuK
New website for Tinker-HP @TINKERtoolsMD. It will accumulate new ressources including tutorials, an extended manual and various publications of interest. Check it out!! #compchem#HPC#supercomputing#neuralnetworks https://t.co/7po25shXrZ
Please RT. #compchem We are looking for an experienced #HPC engineer to work on various GPU optimizations of the Tinker-HP software @TINKERtoolsMD. Please contact me if interested. This position is funded by @ERC_Research (project ERC EMC2) and oriented towards exascale computing
@PierPoier@jppiquem propose a new many-body dispersion correction for density functional theory. Thanks to neural networks, the density-free framework is shown to be highly accurate, transferable & applicable beyond electronic structure theory #compchem
https://t.co/VgrCo1JcgO