Kangming Li
YOU?
Author Swipe
View article: Exploring the Frontiers of kNN Noisy Feature Detection and Recovery for Self-Driving Labs
Exploring the Frontiers of kNN Noisy Feature Detection and Recovery for Self-Driving Labs Open
Self-driving laboratories (SDLs) have shown promise to accelerate materials discovery by integrating machine learning with automated experimental platforms. However, errors in the capture of input parameters may corrupt the features used t…
View article: Accurate and efficient predictions of keyhole dynamics in laser materials processing using machine learning-aided simulations
Accurate and efficient predictions of keyhole dynamics in laser materials processing using machine learning-aided simulations Open
View article: Exploring the role of the atherogenic index of plasma as a mediator between body roundness Index and cardiovascular events in older adults: a NHANES-based study
Exploring the role of the atherogenic index of plasma as a mediator between body roundness Index and cardiovascular events in older adults: a NHANES-based study Open
Background The rising incidence of cardiovascular diseases (CVD) in the elderly highlights the need for effective preventive strategies. Recent studies suggest that obesity, through metabolic factors, contributes to the development of CVD.…
View article: LLM4Mat-bench: benchmarking large language models for materials property prediction
LLM4Mat-bench: benchmarking large language models for materials property prediction Open
Large language models (LLMs) are increasingly being used in materials science. However, little attention has been given to benchmarking and standardized evaluation for LLM-based materials property prediction, which hinders progress. We pre…
View article: Probing out-of-distribution generalization in machine learning for materials
Probing out-of-distribution generalization in machine learning for materials Open
Scientific machine learning (ML) aims to develop generalizable models, yet assessments of generalizability often rely on heuristics. Here, we demonstrate in the materials science setting that heuristic evaluations lead to biased conclusion…
View article: Evaluating the performance and robustness of LLMs in materials science Q&A and property predictions
Evaluating the performance and robustness of LLMs in materials science Q&A and property predictions Open
We evaluate LLM performance and robustness for materials science Q&A and property prediction. Prompt sensitivity and mode collapse reveal reliability concerns, providing informed skepticism and guiding more cautious adoption in scientific …
View article: Bayesian assessment of commonly used equivalent circuit models for corrosion analysis in electrochemical impedance spectroscopy
Bayesian assessment of commonly used equivalent circuit models for corrosion analysis in electrochemical impedance spectroscopy Open
Electrochemical Impedance Spectroscopy (EIS) is a crucial technique for assessing corrosion of metallic materials. The analysis of EIS hinges on the selection of an appropriate equivalent circuit model (ECM) that accurately characterizes t…
View article: LLM4Mat-Bench: Benchmarking Large Language Models for Materials Property Prediction
LLM4Mat-Bench: Benchmarking Large Language Models for Materials Property Prediction Open
Large language models (LLMs) are increasingly being used in materials science. However, little attention has been given to benchmarking and standardized evaluation for LLM-based materials property prediction, which hinders progress. We pre…
View article: Prediction of in-hospital mortality risk for patients with acute ST-elevation myocardial infarction after primary PCI based on predictors selected by GRACE score and two feature selection methods
Prediction of in-hospital mortality risk for patients with acute ST-elevation myocardial infarction after primary PCI based on predictors selected by GRACE score and two feature selection methods Open
Introduction Accurate in-hospital mortality prediction following percutaneous coronary intervention (PCI) is crucial for clinical decision-making. Machine Learning (ML) and Data Mining methods have shown promise in improving medical progno…
View article: Evaluating the Performance and Robustness of LLMs in Materials Science Q&A and Property Predictions
Evaluating the Performance and Robustness of LLMs in Materials Science Q&A and Property Predictions Open
Large Language Models (LLMs) have the potential to revolutionize scientific research, yet their robustness and reliability in domain-specific applications remain insufficiently explored. In this study, we evaluate the performance and robus…
View article: Vacancy formation free energy in concentrated alloys: Equilibrium vs. random sampling
Vacancy formation free energy in concentrated alloys: Equilibrium vs. random sampling Open
View article: An Assessment of Commonly Used Equivalent Circuit Models for Corrosion Analysis: A Bayesian Approach to Electrochemical Impedance Spectroscopy
An Assessment of Commonly Used Equivalent Circuit Models for Corrosion Analysis: A Bayesian Approach to Electrochemical Impedance Spectroscopy Open
Electrochemical Impedance Spectroscopy (EIS) is a crucial technique for assessing corrosion of a metallic materials. The analysis of EIS hinges on the selection of an appropriate equivalent circuit model (ECM) that accurately characterizes…
View article: Towards accurate thermodynamics from random energy sampling
Towards accurate thermodynamics from random energy sampling Open
International audience
View article: Probing out-of-distribution generalization in machine learning for materials
Probing out-of-distribution generalization in machine learning for materials Open
Scientific machine learning (ML) endeavors to develop generalizable models with broad applicability. However, the assessment of generalizability is often based on heuristics. Here, we demonstrate in the materials science setting that heuri…
View article: Development and trends in research on hypertension and atrial fibrillation: A bibliometric analysis from 2003 to 2022
Development and trends in research on hypertension and atrial fibrillation: A bibliometric analysis from 2003 to 2022 Open
Background: This study aimed to comprehensively analyze research related to hypertension and atrial fibrillation, 2 common cardiovascular diseases with significant global public health implications, using bibliometric methods from 2003 to …
View article: JARVIS-Leaderboard: a large scale benchmark of materials design methods
JARVIS-Leaderboard: a large scale benchmark of materials design methods Open
View article: Accurate and efficient predictions of keyhole dynamics in laser materials processing using machine learning-aided simulations
Accurate and efficient predictions of keyhole dynamics in laser materials processing using machine learning-aided simulations Open
The keyhole phenomenon has been widely observed in laser materials processing, including laser welding, remelting, cladding, drilling, and additive manufacturing. Keyhole-induced defects, primarily pores, dramatically affect the performanc…
View article: Publisher Correction: Exploiting redundancy in large materials datasets for efficient machine learning with less data
Publisher Correction: Exploiting redundancy in large materials datasets for efficient machine learning with less data Open
View article: A reproducibility study of atomistic line graph neural networks for materials property prediction
A reproducibility study of atomistic line graph neural networks for materials property prediction Open
ALIGNN performance on 29 regression tasks can be generally well reproduced with minor disparity due to stochasticity.
View article: Performance Optimization of Support Vector Machine with Adversarial Grasshopper Optimization for Heart Disease Diagnosis and Feature Selection
Performance Optimization of Support Vector Machine with Adversarial Grasshopper Optimization for Heart Disease Diagnosis and Feature Selection Open
View article: Efficient first principles based modeling <i>via</i> machine learning: from simple representations to high entropy materials
Efficient first principles based modeling <i>via</i> machine learning: from simple representations to high entropy materials Open
Generalization performance of machine learning models: (upper panel) generalization from small ordered to large disordered structures (SQS); (lower panel) generalization from low-order to high-order systems.
View article: Exploiting redundancy in large materials datasets for efficient machine learning with less data
Exploiting redundancy in large materials datasets for efficient machine learning with less data Open
Extensive efforts to gather materials data have largely overlooked potential data redundancy. In this study, we present evidence of a significant degree of redundancy across multiple large datasets for various material properties, by revea…
View article: Myocardial Perfusion in ST-Segment Elevation Myocardial Infarction Patients After Percutaneous Coronary Intervention: Influencing Factors and Intervention Strategies
Myocardial Perfusion in ST-Segment Elevation Myocardial Infarction Patients After Percutaneous Coronary Intervention: Influencing Factors and Intervention Strategies Open
View article: Editors’ Choice—AutoEIS: Automated Bayesian Model Selection and Analysis for Electrochemical Impedance Spectroscopy
Editors’ Choice—AutoEIS: Automated Bayesian Model Selection and Analysis for Electrochemical Impedance Spectroscopy Open
Electrochemical Impedance Spectroscopy (EIS) is a powerful tool for electrochemical analysis; however, its data can be challenging to interpret. Here, we introduce a new open-source tool named AutoEIS that assists EIS analysis by automatic…
View article: JARVIS-Leaderboard: A Large Scale Benchmark of Materials Design Methods
JARVIS-Leaderboard: A Large Scale Benchmark of Materials Design Methods Open
Lack of rigorous reproducibility and validation are major hurdles for scientific development across many fields. Materials science in particular encompasses a variety of experimental and theoretical approaches that require careful benchmar…
View article: Materials Datasets with 273 compositional and structural features extracted from Matminer
Materials Datasets with 273 compositional and structural features extracted from Matminer Open
Materials Datasets with 273 compositional and structural features extracted from Matminer. Materials datasets are retrieved using the python package jarvis-tools.
View article: Materials Datasets with 273 compositional and structural features extracted from Matminer
Materials Datasets with 273 compositional and structural features extracted from Matminer Open
Materials Datasets with 273 compositional and structural features extracted from Matminer. Materials datasets are retrieved using the python package jarvis-tools.
View article: AutoEIS: automated Bayesian model selection and analysis for electrochemical impedance spectroscopy
AutoEIS: automated Bayesian model selection and analysis for electrochemical impedance spectroscopy Open
Electrochemical Impedance Spectroscopy (EIS) is a powerful tool for electrochemical analysis; however, its data can be challenging to interpret. Here, we introduce a new open-source tool named AutoEIS that assists EIS analysis by automatic…
View article: On the redundancy in large material datasets: efficient and robust learning with less data
On the redundancy in large material datasets: efficient and robust learning with less data Open
Extensive efforts to gather materials data have largely overlooked potential data redundancy. In this study, we present evidence of a significant degree of redundancy across multiple large datasets for various material properties, by revea…
View article: A critical examination of robustness and generalizability of machine learning prediction of materials properties
A critical examination of robustness and generalizability of machine learning prediction of materials properties Open
Recent advances in machine learning (ML) have led to substantial performance improvement in material database benchmarks, but an excellent benchmark score may not imply good generalization performance. Here we show that ML models trained o…