arXiv subjects

Kamal Choudhary

Publications and source records attributed to Kamal Choudhary.

At least 19 recordsLinked to original sources

arXiv2026

ALIGNN 2.0: A Unified Line-Graph Neural Network Framework for Materials Screening, Force Fields, Inverse Design, Spectroscopy, and Microscopy

Graph neural networks are central to materials property prediction and machine-learning interatomic potentials, yet their reliance on specialized graph libraries hampers portability and reproducibility, and property and force-field models have historically required separate graph pipelines. We present ALIGNN 2.0, a dependency-free, pure-PyTorch reimplementation of the Atomistic Line Graph Neural Network, with the line graph and its batching built from scratch, running on current-generation accelerators and unifying scalar, spectral, tensorial, per-atom, and force-field prediction behind a single graph, a combination that to our knowledge no existing framework provides. Comparing radius and k-nearest-neighbor (kNN) graphs, the wider kNN graph is more accurate for properties while the smoothly varying radius graph is required for energy-conserving molecular dynamics. On the JARVIS-Leaderboard, ALIGNN 2.0 leads on 26 of 30 single-property benchmarks against the original ALIGNN, with large gains for piezoelectric and dielectric maxima, exfoliation energy, moduli, and superconducting Tc. The LAMMPS- and OpenMM-compatible ALIGNN-FF matches leading universal potentials on the Matbench-Discovery and CHIPS-FF benchmarks at a small fraction of their parameters while scaling to hundred-thousand-atom cells. We further use ALIGNN 2.0 as the denoiser in a conditional crystal-diffusion model, where explicit line-graph message passing consistently lowers structural denoising loss. We also show, as work in progress, that an independently diffused, redundant bond-angle state is learnable but does not uniformly improve reconstruction or combine additively with the line graph. Finally, from a single relaxed structure the same framework reconstructs infrared, Raman, optical-dielectric, and neutron spectra in agreement with experiment and DFT, and drives frozen-phonon electron-microscopy image simulation.

cond-mat.mtrl-sci↗

arXiv2026

Hybrid DiffractGPT-Rietveld Refinement Framework for Automated X-ray Diffraction Analysis

X-ray diffraction (XRD) is fundamental to structural materials characterization, yet transforming a raw powder pattern into a refined crystal structure still demands considerable domain expertise. We present AGAPI-XRD, a hybrid framework integrating DiffractGPT generative structure prediction, database pattern matching against JARVIS-DFT and COD, and automated Rietveld refinement and ALIGNN-FF relaxation through a unified API at https://atomgpt.org/xrd. First, we used the AGAPI-XRD pipeline to evaluate the crystal structure of a variety of minerals in the RRUFF database that were experimentally characterized using powder x-ray diffraction. Next, we benchmarked the lattice parameter prediction fidelity of the AGAPI-XRD pipeline using a subset of the Alexandria PBE-hull dataset and the subset of RRUFF minerals that have known lattice parameters. AGAPI-XRD returns valid lattice parameters for 79.7\% of the RRUFF benchmark minerals and for 94.8--98.1\% of the Alexandria subset, while identifying a candidate structure for 93.8\% of RRUFF minerals. For this benchmark, pattern matching delivers the highest accuracy for known phases, while DiffractGPT extends structure generation to complex materials absent from existing databases. Together, AGAPI-XRD advances accessible, end-to-end automated crystal structure determination from powder XRD data.

cond-mat.mtrl-sci↗

arXiv2026

AtomBench: A Benchmarking Framework for Generative Crystal Reconstruction Models in Conventional Superconductors

A key question in benchmarking generative crystal reconstruction models is how the amount and type of crystallographic information provided to a generative model affects its ability to reconstruct atomic structures. Yet such comparisons often overlook the fact that models receive unequal information about the target during reconstruction, thereby confounding architectural conclusions. We present AtomBench, an extensible, model-agnostic framework for comparing generative models on a well-defined crystal reconstruction task (rather than \textit{de novo} generation), which we here apply to conventional superconductors. We train and evaluate four models, AtomGPT, CDVAE, FlowMM, and MatterGen, on the JARVIS Supercon-3D and Alexandria DS-A/B datasets, grouping them by the information each accesses at inference. Reconstruction fidelity is measured by the Kullback-Leibler divergence (KLD) and mean absolute error (MAE) of lattice parameters and the root-mean-squared displacement (RMSD) of atomic coordinates. We further introduce the continuous corrected RMSD (ccRMSD), a continuous measure of local geometric fidelity defined for every structure in the test set. MatterGen achieves the best atomic-coordinate reconstruction, followed by AtomGPT, while CDVAE reconstructs lattices most accurately, and FlowMM is the least accurate but fastest overall. We find that conditioning on critical temperature T$_c$ does not consistently improve fidelity. We also release AtomBench as an open-source Python package that reproduces all reported reconstruction metrics, figures, and tables from one or more benchmark files and supports direct submission to the JARVIS-Leaderboard. Any inverse model emitting crystal reconstructions can be benchmarked with \texttt{atombench}, and we encourage community use. https://github.com/atomgptlab/atombench

cs.LG↗

arXiv2026

AGAPI-Agents: An Open-Access Agentic AI Platform for Accelerated Materials Design on AtomGPT.org

Agentic AI systems increasingly connect large language models (LLMs) to external scientific tools, yet whether and when tool access improves prediction accuracy remains uncharacterized. We present AGAPI (AtomGPT.org API), an open access platform integrating eight open-source LLMs with 18 REST endpoints (28 agent tools, 50 web apps) spanning materials databases, force fields, tight-binding band structures, X-ray diffraction, and protein structure. A three-evaluation residual decomposition on JARVIS-Leaderboard electronic-structure test sets separates agent pipeline fidelity from inherited density functional theory (DFT) functional bias. For bulk modulus and bandgap the agent reproduces JARVIS-DFT entries to numerical precision, so the experimental-reference degradation is functional bias, not agentic malfunction. On memorization-resistant test sets (57 defective supercells, 60 hypothetical compositions), tool-augmented mean absolute error (MAE) is below 0.005 eV versus 1.25 to 1.86 eV tool-free, confirming tools are indispensable where parametric knowledge is unavailable. We further demonstrate autonomous multi-step workflows including 10-operation defect-engineering pipelines. AGAPI is available at https://github.com/atomgptlab/agapi.

cs.AI↗

arXiv2026

BatteryMat: a hierarchical machine-learning and DFT framework for average-voltage screening of lithium-ion cathode materials

Density functional theory (DFT) predicts cathode voltages accurately but does not scale to the combinatorial chemical spaces of modern materials databases, while pure machine-learning surrogates are fast but cannot guarantee thermodynamic consistency. We introduce BatteryMat, a three-tier framework that promotes single-pass average-voltage prediction with the Atomistic Line Graph Neural Network (ALIGNN) as the primary screening signal across JARVIS-DFT, then validates survivors with ALIGNN-FF force-field delithiation profiles and automated PBE+U or optB88-vdW+U supercell DFT. The exchange-correlation functional is selected automatically by spacegroup, and the lithium metal reference is recomputed in the same plane-wave basis as the cathode runs, removing a systematic offset of about 1 V present in tabulated values. Trained on 7,610 ALIGNN-FF delithiation voltages, the ALIGNN predictor reproduces the force-field labels with a mean absolute error of 0.17 V and a coefficient of determination of 0.94; this measures distillation fidelity to the force-field protocol, not agreement with DFT or experiment. On four commercial chemistries (LiFePO4, LiMnPO4, LiMn2O4, LiCoO2) the DFT tier reproduces the experimental average voltage to within 0.3 V and the theoretical volumetric capacity to within 5%; a fifth, non-stoichiometric layered entry is carried as an edge case. The pipeline prioritises, rather than generates, existing structures: it ranks the lithium-containing JARVIS-DFT pool into 71 candidates and a scan of about 4.49 million Alexandria structures into 213, all surrogate-level leads awaiting DFT validation rather than confirmed cathodes. BatteryMat is available at https://github.com/atomgptlab/batterymat with a demo at https://atomgpt.org/battery.

cond-mat.mtrl-sci↗

arXiv2026

Hallucination Detector: A hybrid LLM and Semantic Scholar tool calling for detecting hallucination in scientific literature on AtomGPT.org

Large language models are now commonly used as partners in scientific writing, and this shift has brought a subtler type of failure: made-up references. Fabricated authors, bogus DOIs, wrongly assigned identifiers, and citations that merge elements from multiple genuine articles are now being inserted into manuscripts at a volume that traditional peer review was never meant to handle. Recent audits reveal that such references have already slipped through the review process and made their way into the published literature, including leading journals and conferences. Automated verification that operates at the speed and scale of modern content production has therefore become a necessary safeguard rather than a convenience. This work presents and evaluates the AtomGPT reference checker (https://atomgpt.org/hallucination_detector), an open, web-accessible tool that verifies citations against the scholarly literature by combining large-language-model field extraction with structured retrieval from Semantic Scholar. For each reference, the tool extracts the bibliographic fields, retrieves the closest matching real papers, and scores the agreement across title, authorship, and venue to produce a graded judgment of whether a citation is trustworthy, partially supported, or likely fabricated. We benchmark the tool against an externally curated set of confirmed hallucinated citations from accepted NeurIPS 2025 papers and find that it reliably flags the great majority of them.

cs.DL↗

arXiv2026

SlaKoNet-VQD: A universal Slater-Koster tight-binding Hamiltonian for variational quantum band-structure calculations on near-term hardware

Variational quantum algorithms such as VQE and VQD are promising for near-term electronic structure calculations, but for periodic solids their reach is limited by the cost of building a faithful second-quantized Hamiltonian, typically via DFT plus Wannierization or hand-fit tight-binding parameters. SlaKoNet addresses this by combining deep learning with the Slater-Koster tight-binding formalism to fit hopping and overlap parameters across 65 elements, enabling deterministic Hamiltonian construction for any crystal built from these elements. Here we couple a SlaKoNet model trained on JARVIS-TBmBJ with a Qiskit-based VQD algorithm, replacing costly Hamiltonian construction with a universal neural Hamiltonian generator. The resulting SlaKoNet-VQD workflow is structure-agnostic, differentiable, and suited to high-throughput bandstructure screening. We benchmark on silicon, recovering the full eight-band structure along the standard k-path with mean absolute deviation of 1.78 meV from exact diagonalization on a 3-qubit simulator, and extend to five conventional superconductors (Al, Ta, Nb, V, ZrN) with similar accuracy. We demonstrate execution on IBM Quantum hardware for a k-point ground-state calculation on aluminum (MAE ~0.37 eV). We further promote the Hamiltonian to a correlated Hubbard model solved via dynamical mean-field theory, recovering weakening correlations across group-5 metals and strong quasiparticle renormalization in La2CuO4, identifying the impurity problem as a natural quantum solver target. This pipeline enables high-throughput VQA benchmarking across the periodic table and gradient-based ansatz-Hamiltonian co-optimization for materials discovery. Web app: https://atomgpt.org/quantum.

cond-mat.mtrl-sci↗

arXiv2026

Mesh Graph Neural Network Framework for Accelerating Finite Element Simulation for Arbitrary Geometries

Finite element analysis (FEA) is essential for structural design but remains computationally expensive, particularly when evaluating multiple design iterations or load scenarios. Machine learning surrogate models offer a promising alternative, yet most approaches struggle with a critical limitation: generalizing across varying geometries. This work presents a mesh graph network (MGN) for predicting von Mises stress fields in 2D structural components with arbitrary hole geometries. Unlike traditional machine learning approaches that use absolute node coordinates as features, the proposed model builds on existing MGN frameworks that encode node types (e.g., fixed boundary, free surface, hole edge), relative edge features (distance between neighbors), and global features (applied load). This architecture is inherently translation- and rotation-invariant, enabling generalization to unseen geometries without retraining. The MGN was trained on 11 plate geometries under 20 load conditions and evaluated on 7 unseen geometries and 3 unseen loads. In the most favorable case, the model achieves $R^2 \geq 0.97$ on an unseen geometry and unseen load, compared to $R^2 \approx 0.01$--$0.86$ for conventional models (Random Forest, Gradient Boosting , K-Nearest Neighbors) trained on identical data. However, even in less favorable cases, the MGN model still outperforms conventional models. This work extends the mesh-based simulation framework of Pfaff et al. (arXiv:2010.03409) to structural mechanics, demonstrating that graph neural networks can serve as efficient surrogates for finite element analysis across varying geometries.

cs.LG↗

arXiv2026

RamanGPT: Bidirectional Mapping Between Crystal Structures and Raman Spectra with Graph Neural Networks and Generative Transformers

Raman spectroscopy is one of the most accessible vibrational probes in materials laboratories, but its forward problem (structure to spectrum) is bottlenecked by the cost of density functional perturbation theory, and its inverse problem (spectrum to structure) typically relies on retrieval against curated references. We introduce RamanGPT, a deep-learning framework that addresses both directions for crystalline inorganic materials. The forward model, an Atomistic Line Graph Neural Network (ALIGNN), is trained on the 5{,}099-material Computational Raman Database and predicts 200-bin spectra over 50-1000~cm$^{-1}$ with 42.5\% having a cosine similarity greater than or equal to 0.354 suggesting qualitative features of the target spectrum. The model also shows some qualitative agreement with the approximate features and appearance of similar relative intensity of the modes to an experimental measurement of metallic 1T VSe$_{2}$, a system absent from the training set. The inverse model fine-tunes a large language model via Quantized Low-Rank Adaptation on Raman-plus-formula prompts, recovering lattice parameters with mean absolute errors of 1.14-2.16~Å and reduced-formula consistency of 86.8\% on 508 held-out materials. A cosine-similarity matcher and an inverse$\rightarrow$relax$\rightarrow$forward consistency loop are deployed at https://atomgpt.org/raman.

cond-mat.mtrl-sci↗

arXiv2026

AI-ready design of realistic 2D materials and interfaces with Mat3ra-2D

Artificial intelligence (AI) and machine learning (ML) models in materials science are predominantly trained on ideal bulk crystals, limiting their transferability to real-world applications where surfaces, interfaces, and defects dominate. We present Mat3ra-2D, an open-source framework for the rapid design of realistic two-dimensional materials and related structures, including slabs and heterogeneous interfaces, with support for disorder and defect-driven complexity. The approach combines: (1) well-defined standards for storing and exchanging materials data with a modular implementation of core concepts and (2) transformation workflows expressed as configuration-builder pipelines that preserve provenance and metadata. We implement typical structure generation tasks, such as constructing orientation-specific slabs or strain-matching interfaces, in reusable Jupyter notebooks that serve as both interactive documentation and templates for reproducible runs. To lower the barrier to adoption, we design the examples to run in any web browser and demonstrate how to incorporate these developments into a web application. Mat3ra-2D enables systematic creation and organization of realistic 2D- and interface-aware datasets for AI/ML-ready applications.

cond-mat.mtrl-sci↗

arXiv2026

From Photons to Electrons: Accelerated Materials Discovery via Random Libraries and Automated Scanning Transmission Electron Microscopy

The real-world implementation of materials prediction algorithms remains limited by persistent characterization bottlenecks in materials discovery, where photon-based probe techniques (e.g., XRD or Raman) impose long acquisition times and access latencies, restricting exploration to quasi-ternary composition spaces typically realized as compositional libraries. Here, we argue that a paradigm shift from photon- to electron-based characterization can realign materials characterization with modern high-throughput synthesis. We formulate cost functions and exploration strategies for STEM-based chemical and structural characterization and use Monte Carlo simulations to show that random chemical libraries, where compositionally distinct regions are co-located within a single specimen and interrogated in situ by electron spectroscopies, can sample high-dimensional composition and phase spaces with orders-of-magnitude greater effective coverage than conventional spread-library/X-ray approaches. We further demonstrate autonomous discovery on a laboratory STEM platform, where ML-based autotuning and scripted control enable iterative region selection and characterization without human intervention. Finally, we outline extensions to labeled or position-encoded libraries that preserve compositional and processing metadata, enabling joint exploration of composition and process spaces. Together, these results establish electron-based, ML-enabled STEM as a scalable pathway toward combinatorially rich materials discovery.

cond-mat.mtrl-sci↗

arXiv2026

Effect of Exchange-Correlation Functionals on Schottky Barriers at Si/Metal Interfaces

Accurate prediction of Schottky barrier heights (SBHs) at metal-semiconductor (M-SC) interfaces is essential for understanding and optimizing charge injection in electronic and optoelectronic devices. However, first-principles calculations of SBHs remain challenging due to the combined difficulties of semiconductor bandgap underestimation, metal Fermi level placement, lattice-mismatch, relative geometric alignment and electrostatic potential alignment across heterogeneous interfaces. In this work, we present a systematic and physically grounded assessment of computational strategies for SBH prediction using Si(111)/Metal (Al, Cu, Ag, Au) interfaces as representative test cases. We evaluate multiple exchange-correlation (XC) treatments, in combination with three distinct bulk reference protocols: relaxed bulk, relaxed bulk with spin-orbit coupling, and strained bulk references consistent with the interface geometry. By benchmarking against experimental data, we demonstrate that structural and electrostatic consistency between interface and bulk reference calculations is the dominant factor governing SBH accuracy. We show that mixed hybrid-semilocal approaches combined with strained reference protocols yield uniformly positive and significantly improved SBHs, achieving near-experimental accuracy while maintaining a favorable balance between computational cost and predictive performance. Our results establish a clear and transferable methodology for reliable Schottky barrier prediction and provide practical guidance for large-scale screening and interface engineering.

cond-mat.mtrl-sci↗

arXiv2026

M-CODE: Materials Categorization via Ontology, Dimensionality and Evolution

The rapid advancement of artificial intelligence in materials science requires data standards and data management practices that can capture the complexity of real-world structures, including surfaces, interfaces, defects, and dimensionality reduction. We present M-CODE - Materials Categorization via Ontology, Dimensionality and Evolution - a compact categorization system that links materials-science-specific terminology to a set of reusable concepts as building blocks and provenance-aware transformations. M-CODE classifies structures by dimensionality, structural complexity (from pristine to compound pristine, defective, and processed), and variants that capture common structure creation and evolution approaches. A practical implementation of the categorization is provided in an open-source codebase that includes JSON schemas, examples, and Python and TypeScript types/interfaces, designed to support reproducible dataset generation, validation, and community contributions.

cond-mat.mtrl-sci↗

arXiv2025

Machine Learning for Predicting Magnetization from X-ray Diffraction of Iron Oxide Nanoparticles Using Simple Physics-Based Data Generation

Automation and high-throughput characterization and synthesis for material development are becoming increasingly common; these approaches require machine learning (ML) tools to assess material properties, ideally based on a single measurement. Here, ML models are developed to predict magnetization from X-ray diffraction (XRD) for iron oxide nanoparticles. Our approach is to first develop a set of simulated data that links modulated XRD, based on a crystallographic information file (CIF), to a simple magnetic model to determine magnetization at a given magnetic field, thereby enabling us to train Random Forest and Gradient Boosting regression models on a large amount of simulated data. The models are validated by synthesizing iron oxide nanoparticles and measuring their crystal structure via XRD and room-temperature magnetization curves. In doing so, we can fine-tune both the training hyperparameters and the optimal size of the simulated datasets used to train the models. Through this optimization, the best models can achieve an $R^2$ greater than 0.9 for five experimental samples, used for tuning, for predicting the max magnetization (at 2.8 T) of the measurement. Lastly, we demonstrate reasonable predictions on the full magnetization vs. magnetic field curve, showing that the RF model excels at predicting the high magnetic field values, which is key for determining the success of an iron oxide nanoparticle synthesis for applications like magnetic particle imaging (MPI), thermal magnetic particle imaging (T-MPI), and hyperthermia.

cond-mat.mtrl-sci↗

arXiv2025

CHIPS-TB: Evaluating Tight-Binding Models For Metals, Semiconductors, and Insulators

As semiconductor technologies continue to scale down to the nanoscale, the efficient prediction of material properties becomes increasingly critical. The tight-binding (TB) method is a widely used semi-empirical approach that offers a computationally tractable alternative to Density Functional Theory (DFT) for large-scale electronic structure calculations. However, conventional TB models often suffer from limited transferability and lack standardized benchmarking protocols. In this study, we introduce a computational framework (CHIPS-TB) for evaluating and comparing tight-binding parameterizations across diverse material systems relevant to semiconductor design, focusing on properties such as electronic bandgaps, band structures, and bulk modulus. We assess model parameterizations including Density Functional Tight-Binding (DFTB)-based MatSci, PBC, PTBP, SlaKoNet and TB3PY against OptB88vdW, TBmBJ-DFT and experimental reference data from the JARVIS-DFT database for 50+ materials pertinent to semiconductor applications. The CHIPS-TB code will be made publicly available on GitHub and benchmarks will be available on JARVIS-Leaderboard.

cond-mat.mtrl-sci↗

arXiv2025

Accelerated prediction of dielectric functions in solar cell materials with graph neural networks

We present an atomistic line graph neural network (ALIGNN) model for predicting dielectric functions directly from crystal structures. Trained on $\sim$7000 dielectric functions from the JARVIS-DFT database computed with a meta-GGA exchange-correlation functional, the model accurately reproduces spectral features, including peak intensities and overall line shapes, while enabling efficient high-throughput screening. Applied to the recently developed Alexandria materials database, containing over four hundred thousand insulating materials, we uncover a clear elemental trend, with vanadium emerging as a strong indicator of materials with high-spectroscopic limited maximum efficiency (SLME). In particular, vanadium-based perovskite materials show a substantially higher fraction of high-SLME compounds compared to the database average, underscoring their promise for optoelectronic applications.

cond-mat.mtrl-sci↗

arXiv2025

DiffractGPT: Atomic Structure Determination from X-ray Diffraction Patterns using Generative Pre-trained Transformer

Crystal structure determination from powder diffraction patterns is a complex challenge in materials science, often requiring extensive expertise and computational resources. This study introduces DiffractGPT, a generative pre-trained transformer model designed to predict atomic structures directly from X-ray diffraction (XRD) patterns. By capturing the intricate relationships between diffraction patterns and crystal structures, DiffractGPT enables fast and accurate inverse design. Trained on thousands of atomic structures and their simulated XRD patterns from the JARVIS-DFT dataset, we evaluate the model across three scenarios: (1) without chemical information, (2) with a list of elements, and (3) with an explicit chemical formula. The results demonstrate that incorporating chemical information significantly enhances prediction accuracy. Additionally, the training process is straightforward and fast, bridging gaps between computational, data science, and experimental communities. This work represents a significant advancement in automating crystal structure determination, offering a robust tool for data-driven materials discovery and design.

cond-mat.mtrl-sci↗

arXiv2025

The JARVIS Infrastructure is All You Need for Materials Design

The Joint Automated Repository for Various Integrated Simulations (JARVIS) is a unified platform for multiscale, multimodal, forward, and inverse materials design. It integrates diverse theoretical and experimental approaches, including density functional theory, quantum Monte Carlo, tight-binding, classical force fields, machine learning, microscopy, diffraction, and cryogenics, across a wide range of materials. Emphasizing open access and reproducibility, JARVIS provides datasets, tools, benchmarks, and web applications that are widely adopted by the materials community. By bridging computation and experiment, JARVIS accelerates both fundamental research and real-world materials innovation.

cond-mat.mtrl-sci↗