Proceedings of the National Academy of Sciences · 30 October 2026 · From issue 60
In-context learning as a retraining-free paradigm for constitutive modeling
In simulations and lab tests, one trained model predicted stress in materials it had never seen.
Lingfeng Li, Zhuoyuan Li et al.
Integrity screen: passed (3 checks) Checked 1 November 2026. Read the source
The plain-language reading of this paper is in the full issue, for subscribers.
Read the full issue