Benchmarking long-range ML interatomic potentials on SrTiO3 defect energetics
rbhar90 · x · 2026-10-03
An arXiv paper (2610.00794) benchmarks three long-range machine learning interatomic potentials — MACE-POLAR, MACE-LES and LOREM — against a short-range MACE baseline on capturing long-range Coulombic interactions.
- Most MLIPs remain semilocal and neglect long-range electrostatics; systematic benchmarks on realistic systems were scarce
- Evaluation progresses from synthetic point-charge systems to first-principles data on SrTiO3, where Sr–O Schottky vacancy pairs make long-range charge interactions central
- The authors also study oxygen vacancy migration barriers, isolating how models learn electrostatics from competing DFT energy contributions like dielectric screening and exchange-correlation
More from Research
- Symbolic supervision gives video models equal reasoning at ~1/30 the compute, Rubik's Cube study finds — niloofar_mire · 2026-10-03
- Sony AI open-sources PAVAS, a physics-aware video-to-audio model accepted as CVPR 2026 Oral — mittu1204 · 2026-10-03
- Maryland RCT: GPT-4o tutor offering left students 4 points lower, 15% used it — lmoroney · 2026-10-03
- OpenAI paper: simulating deployment predicts LLM safety before release — JacquesThibs · 2026-10-03
- PyTorch Helion DSL integrated into vLLM beats CUTLASS and DeepGEMM with 10%+ throughput gains — PyTorch · 2026-10-03
- Neural memory as an unbounded 2D lattice: writes and reads through a tiny 3x3 bump — CFGeek · 2026-10-03