Manasa Kaniselvan — accepted AI-conference papers

2026

Enhancing Diffusion-Based Sampling with Molecular Collective Variables

Juno Nam, Bálint Máté, Artur P. Toshev, Manasa Kaniselvan, Rafael Gomez-Bombarelli, Ricky T. Q. Chen +3

ICLR 2026poster

Diffusion-based samplers learn to sample complex, high-dimensional distributions using energies or log densities alone, without training data. Yet, they remain impractical for molecular sampling because they are often slower than molecular dynamics and miss thermodynamically relevant modes. Inspired…

Cited by 0 Source ↗code ↗Scholar ↗

2026

Learning from the Electronic Structure of Molecules across the Periodic Table

Manasa Kaniselvan, Benjamin Kurt Miller, Meng Gao, Juno Nam, Daniel S. Levine

ICLR 2026poster

Machine-Learned Interatomic Potentials (MLIPs) require vast amounts of atomic structure data to learn forces and energies, and their performance continues to improve with training set size. Meanwhile, the even greater quantities of accompanying data in the Hamiltonian matrix $\mathbf{H}$ behind thes…

Cited by 0 Source ↗Scholar ↗

2025

Learning the Electronic Hamiltonian of Large Atomic Structures

Chen Hao Xia, Manasa Kaniselvan, Alexandros Nikolaos Ziogas, Marko Mladenović, Rayen Mahjoub, Alexander Maeder +1

ICML 2025poster

Graph neural networks (GNNs) have shown promise in learning the ground-state electronic properties of materials, subverting *ab initio* density functional theory (DFT) calculations when the underlying lattices can be represented as small and/or repeatable unit cells (i.e., molecules and periodic cry…

Cited by 0 Source ↗PDF ↗Scholar ↗