Pretrained atomic potential screens 1,620 combos to stabilize one-atom-thick metals
bravo_abad · x · 2026-11-12
Bagheri and Koskinen used MatterSim, a pretrained machine-learning interatomic potential, to fold the environment into the search itself: screening metal layers sandwiched between protective sheets. Of 1,620 metal–substrate combinations, 331 passed dynamical-stability and structural filters, with selected candidates verified by quantum calculations. The substrates changed which structures survive; results are computational candidates awaiting experiments. Lesson: if a material only works in the right environment, make that environment part of the search space.
More from Research
- SGLang Megakernel Pushes Muse Spark to 1,109 tok/s, 2.1x Over Baseline — hsu_byron · 2026-11-12
- ArcGrav: a cross-model Agent Control Language to cut token overhead — ArchitecturalGravity · 2026-11-12
- Open-source dual-arm robot solves tangram puzzles with 90 demos, ~60% success — DanGrover · 2026-11-12
- FutureHouse's deslopper trains Kosmos to write indistinguishably from human experts — proteinrosh · 2026-11-12
- Fleuret amplifies debate: AI can't slash wet-lab experiments in unmapped biology — francoisfleuret · 2026-11-12
- Recursive bets on open-endedness: agents running massive parallel experiments like scientist communities — agihouse_org · 2026-11-12