Abhijeet Gangan

Research

Open-source projects

  • a2c_ase - ASE-friendly implementation of the amorphous-to-crystalline (a2c) workflow.
  • lammps-jax - LAMMPS plugin for running JAX force fields with jax.export and a PJRT runtime.
  • aoti_mlip - PyTorch AOTInductor for universal machine-learned interatomic potentials.
  • mace-eqx - Standalone Equinox implementation of MACE using cuequivariance_jax.
  • torch_matfunc - PyTorch matrix functions: matrix exponential with its Fréchet derivative and an analytical 3×3 matrix logarithm.
  • ase-jax - Minimal ASE calculators backed by JAX and JAX-MD energy functions.

Maintainer

  • jax-md - Differentiable, hardware-accelerated molecular dynamics in JAX.
  • torch-sim - Torch-native, batchable atomistic simulation.

Recent publications

  1. M. J. Gawkowski, N. Artrith, S. Bonfanti, A. S. Gangan, H. H. Heenen, J. Kioseoglou, I. Lončarić, H. Myneni, J. Riebesell, M. Rossi, M. Rupp, J. Schmidt, S. Sharma, B. X. Shi, A. Wadowski, L. Hörmann, and V. Kapil, Dyna-Mat: End-to-End Benchmarking of Foundation Machine Learning Interatomic Potentials in Finite-Temperature Ensembles (2026). arXiv:2607.03433
  2. T. Koker, A. Gangan, M. Kotak, J. Marian, and T. Smidt, PFT: Phonon Fine-tuning for Machine Learned Interatomic Potentials, in International Conference on Machine Learning (ICML) (2026). arXiv:2601.07742
  3. S. Pathrudkar, S. Taylor, A. Keripale, A. S. Gangan, P. Thiagarajan, S. Agarwal, J. Marian, S. Ghosh, and A. S. Banerjee, Electronic Structure Prediction of Medium and High Entropy Alloys Across Composition Space, npj Comput. Mater. (2025). doi:10.1038/s41524-025-01856-3
  4. O. Cohen, J. Riebesell, R. Goodall, A. Kolluru, S. Falletta, J. Krause, J. Colindres, G. Ceder, and A. S. Gangan, TorchSim: An Efficient Atomistic Simulation Engine in PyTorch, AI Sci. 1, 025003 (2025). doi:10.1088/3050-287x/ae1799, arXiv:2508.06628
  5. S. Hossain, P. Thiagarajan, S. Pathrudkar, S. Taylor, A. S. Gangan, A. S. Banerjee, and S. Ghosh, Surprisingly High Redundancy in Electronic Structure Data (2025). arXiv:2507.09001