Large MLIPs deliver marginal accuracy gains over lightweight models while sacrificing orders of magnitude in throughput and scalability, making lightweight models the practical Pareto-optimal choice.
Accuracy–efficiency Pareto trade-off across the 23 benchmarked MLIPs
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cond-mat.mtrl-sci 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Are Machine Learning Interatomic Potentials Truly Practical? A Benchmark of 23 Mainstream Models
Large MLIPs deliver marginal accuracy gains over lightweight models while sacrificing orders of magnitude in throughput and scalability, making lightweight models the practical Pareto-optimal choice.