activity
20242026
collaborators

9 papers

cond-mat.mtrl-sci2026

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

Frank M. Abel, Jaehyung Lee, Charles R. Campbell +1

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 densit…

cond-mat.mtrl-sci2026

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

Vsevolod Biryukov, Kamal Choudhary, Timur Bazhirov

Artificial intelligence (AI) and machine learning (ML) models in materials science are predominantly trained on ideal bulk crystals, limiting their transferability to real-world ap…

cond-mat.mtrl-sci2026

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

Boris Slautin, Kamyar Barakati, Utkarsh Pratiush +10

The real-world implementation of materials prediction algorithms remains limited by persistent characterization bottlenecks in materials discovery, where photon-based probe techniq…

cond-mat.mtrl-sci2025

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

In Jun Park, Kamal Choudhary

As semiconductor technologies continue to scale down to the nanoscale, the efficient prediction of material properties becomes increasingly critical. The tight-binding (TB) method…

cond-mat.mtrl-sci2025

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

Kamal Choudhary

Crystal structure determination from powder diffraction patterns is a complex challenge in materials science, often requiring extensive expertise and computational resources. This…

cond-mat.mtrl-sci2025

Lean CNNs for mapping electron charge density fields to material properties

Pranoy Ray, Kamal Choudhury, Surya R. Kalidindi

This work introduces a lean CNN (convolutional neural network) framework, with a drastically reduced number of fittable parameters (<81K) compared to the benchmarks in current lite…