Material Science AI Comparison Hub

Reference Surfaces

Top Papers

• From Evaluation to Design: Using Potential Energy Surface Smoothness Metrics to Guide Machine Learning Interatomic Potential Architectures(6.0)

  Develop a robust MLIP evaluation tool to reduce errors in interatomic potential modeling while optimizing model design efficiency.

• MatRIS: Toward Reliable and Efficient Pretrained Machine Learning Interaction Potentials(5.0)

  Introducing MatRIS, an efficient invariant MLIP with attention-based modeling for scalable and expressive material simulations.