MOFFlow: Flow Matching for MOF Structure Prediction
A Riemannian flow matching framework for generating Metal-Organic Framework structures by treating building blocks as …
Molecular Modeling
Notes on 3D molecular representations, conformer generation, and neural network potentials. Covers geometric deep learning approaches for molecules.
DenoiseVAE: Adaptive Noise for Molecular Pre-training
Liu et al.'s ICLR 2025 paper introducing DenoiseVAE, which learns adaptive, atom-specific noise for better molecular …
Beyond Atoms: 3D Space Modeling for Molecular Pretraining
Lu et al. introduce SpaceFormer, a Transformer that models entire 3D molecular space (not just atoms) for superior …
Dark Side of Forces: Non-Conservative ML Force Models
Bigi et al. critique non-conservative force models in ML potentials, showing their simulation failures and proposing …
Efficient DFT Hamiltonian Prediction via Adaptive Sparsity
Luo et al. introduce SPHNet, using adaptive sparsity to dramatically improve SE(3)-equivariant Hamiltonian prediction …
Learning Smooth Interatomic Potentials with eSEN
Fu et al. propose energy conservation as a key MLIP diagnostic and introduce eSEN, bridging test accuracy and real …