Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,341 papers · 148 categories

Trend · papers per month

count% of corpus
0.3%0.5%0.8%0.1% · Sep 201719922001200920182026
3 results for “electronegativity”
Catalyst design using actively learned machine with non-ab initio input features towards CO2 reduction reactionscond-mat.mtrl-sci

New method uses machine learning to predict CO2 reduction catalysts without expensive ab initio calculations.

problem Predicting catalytic activity for CO2 reduction reactions using computationally expensive ab initio methods.
method Combining muffin-tin orbital theory descriptors with machine learning (ANN and KRR) for large-scale screening.
result Predicted CO adsorption energy with 0.05 eV mean absolute deviation, significantly improved over previous methods.
CO2 reductioncatalyst designmachine learningactive learningelectronegativity
2017-09-14abs ↗pdf ↗
Generative adversarial networks (GAN) based efficient sampling of chemical space for inverse design of inorganic materialscs.LG

MatGAN uses GAN to efficiently generate new inorganic materials.

problem Efficiently searching the vast chemical design space for new materials.
method Generative adversarial network (GAN) trained on ICSD materials database.
result 92.53% novelty and 84.5% chemically valid samples generated.
GANmaterials designinverse designchemical spaceinorganic materials
2019-11-12abs ↗pdf ↗