An adaptive fine-tuning workflow for foundation-model MLIPs enables efficient CSP in the CaFeNi ternary, reproducing the low-pressure hull and predicting a new phase Ca6FeNi stable above 100 GPa.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cond-mat.mtrl-sci 3years
2026 3roles
background 1polarities
background 1representative citing papers
Machine learning models, especially certain deep neural networks, can predict lattice thermal conductivity with useful accuracy across different generalization tests while being orders of magnitude faster than first-principles calculations.
Hybrid two-stage optimization framework uses AI for peak/density tasks and physics constraints for robust PXRD crystal structure solving on complex or low-quality cases.
citing papers explorer
-
Adaptive fine-tuning of foundation models for crystal structure prediction: Discovery of high-pressure phases in the CaFeNi system
An adaptive fine-tuning workflow for foundation-model MLIPs enables efficient CSP in the CaFeNi ternary, reproducing the low-pressure hull and predicting a new phase Ca6FeNi stable above 100 GPa.
-
Fast and Accurate Prediction of Lattice Thermal Conductivity via Machine Learning Surrogates
Machine learning models, especially certain deep neural networks, can predict lattice thermal conductivity with useful accuracy across different generalization tests while being orders of magnitude faster than first-principles calculations.
-
Ab-initio Crystal Structure Determination from Powder X-Ray Diffraction
Hybrid two-stage optimization framework uses AI for peak/density tasks and physics constraints for robust PXRD crystal structure solving on complex or low-quality cases.