activity
20232026
most citedEnergy-conserving equivariant GNN for elasticity of lattice architected metamaterials

1 citations · 1 across the 2 of their papers we have counts for

collaborators

5 papers

physics.chem-ph2026

Fine-tuning MLIP foundation models: strategies for accuracy and transferability

Tamás Lajos Tompa, Eszter Varga-Umbrich, Ilyes Batatia +3

Adapting machine-learned interatomic potential (MLIP) foundation models to specialised tasks through fine-tuning is an increasingly important practice, yet systematic guidance on w…

cs.LG20241 cited

Energy-conserving equivariant GNN for elasticity of lattice architected metamaterials

Ivan Grega, Ilyes Batatia, Gábor Csányi +2

Lattices are architected metamaterials whose properties strongly depend on their geometrical design. The analogy between lattices and graphs enables the use of graph neural network…

physics.chem-ph2024

A foundation model for atomistic materials chemistry

Ilyes Batatia, Philipp Benner, Yuan Chiang +85

Atomistic simulations of matter, especially those that leverage first-principles (ab initio) electronic structure theory, provide a microscopic view of the world, underpinning much…

physics.chem-ph2023

MACE-OFF: Transferable Short Range Machine Learning Force Fields for Organic Molecules

Dávid Péter Kovács, J. Harry Moore, Nicholas J. Browning +8

Classical empirical force fields have dominated biomolecular simulation for over 50 years. Although widely used in drug discovery, crystal structure prediction, and biomolecular dy…

stat.ML2023

Equivariant Matrix Function Neural Networks

Ilyes Batatia, Lars L. Schaaf, Huajie Chen +3

Graph Neural Networks (GNNs), especially message-passing neural networks (MPNNs), have emerged as powerful architectures for learning on graphs in diverse applications. However, MP…