Materials AI and Scientific Language Models

Placeholder. Replace this page with a verified account of the research program.

Motivation

[Placeholder] This direction is about reading and using the literature on cement, inorganic glasses, and materials for extreme environments. Replace this paragraph with a sourced problem statement.

Questions

Methods

[Placeholder] Summarize methods here. Do not add unpublished numbers or claims.

Selected publications

LLaMat: A family of large language models for materials research with insights into model adaptability in continued pre-training

Zaki M, Ahlawat D, Mishra V, Singh S, Bihani V, Grover H, Mishra B, Miret S, Mausam M, Krishnan NMA

Nature Machine Intelligence, 2026 Feb 27; 1–14 · 2026 · Journal article · Featured

Evaluating large language model agents for automation of atomic force microscopy

Mandal I, Soni J, Zaki M, Smedskjaer MM, Wondraczek K, Wondraczek L, Gosvami NN, Krishnan NMA

Nature Communications, 2025 Oct 14; 16(1): 9104 · 2025 · Journal article

MatSKRAFT: A framework for large-scale materials knowledge extraction from scientific tables

Hira K, Zaki M, Krishnan NMA, Mausam M

arXiv preprint arXiv:2509.10448, 2025 Sep 12 · 2025 · Preprint

Artificial intelligence for information extraction from cement literature

Zaki M, Bharadwaj K, Goyal R, Jayadeva J, Krishnan NMA

Binding Materials for Sustainable Construction, Woodhead Publishing, pp. 819–832 · 2025 · Book chapter

LLaMaT: Large Language Model for Materials Science

Mishra V, Singh S, Zaki M, Grover HS, Miret S, Mausam, Krishnan NMA

AI4MAT Workshop, BOKU Vienna, Accepted, July 2024 · 2024 · Conference paper

MaScQA: Investigating Materials Science Knowledge of Large Language Models

Zaki M, Jayadeva J, Mausam M, Anoop Krishnan NM

Digital Discovery · 2024 · Journal article · Featured

Reconstructing materials tetrahedron: Challenges in materials information extraction

Hira K, Zaki M, Sheth D, Krishnan N, others

Digital Discovery, special issue on AI4MAT NeurIPS-2023, Accepted, 2024 · 2024 · Journal article

Glassomics: An omics approach toward understanding glasses through modeling, simulations, and artificial intelligence

Zaki M, Jan A, Krishnan NMA, Mauro JC

MRS Bulletin · 2023 · Journal article · Featured

Cementron: Machine learning the alite and belite phases in cement clinker from optical images

Zaki M, Sharma S, Gurjar SK, Goyal R, Krishnan NA, others

Construction and Building Materials, 397: 132425 · 2023 · Journal article · Featured

DiSCoMaT: Distantly supervised composition extraction from tables in materials science articles

Gupta T, Zaki M, Khatsuriya D, Hira K, Krishnan NMA, Mausam M

Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 13465–13483, Toronto, Canada · 2023 · Conference paper · Featured

Natural language processing-guided meta-analysis and structure factor database extraction from glass literature

Zaki M, Namireddy SR, Pittie T, et al.

Journal of Non-Crystalline Solids: X, 15: 100103 · 2022 · Journal article

MatSciBERT: A materials domain language model for text mining and information extraction

Gupta T, Zaki M, Krishnan NMA, Mausam M

npj Computational Materials, 8(1): 102 · 2022 · Journal article · Featured

Extracting processing and testing parameters from materials science literature for improved property prediction of glasses

Zaki M, Jayadeva, Krishnan NMA

Chemical Engineering and Processing - Process Intensification, 180: 108607 · 2022 · Journal article

Artificial intelligence and machine learning in glass science and technology: 21 challenges for the 21st century

Ravinder, Venugopal V, Bishnoi S, … Zaki M, … et al.

International Journal of Applied Glass Science, 12(3): 277–292 · 2021 · Journal article

Looking through glass: Knowledge discovery from materials science literature using natural language processing

Venugopal V, Sahoo S, Zaki M, Agarwal M, Gosvami NN, Krishnan NMA

Patterns, 2(7): 100290 · 2021 · Journal article · Featured

Software and datasets

No verified software or datasets are listed for this direction yet.

Collaborators

No verified collaborators are listed for this direction yet.