Research
Current Projects
A snapshot of my ongoing research directions.
Permutation-Equivariant Molecules
Building symmetry-aware surrogate models that respect permutation structure, remain scale-invariant, and provide robust and reliable predictions for strongly correlated molecular systems.
Inductive Bias of Quantum Circuits
Studying how the spectral inductive bias of parameterized quantum circuits can be leveraged for complex machine learning tasks and shapes trainability, expressivity, and generalization.
Reinforcement Learning for Error Correction
Developing reinforcement learning agents that adaptively reweight quantum error-correction decoding graphs, improving logical error rates under realistic drift noise in surface-code systems.
Published Projects
Published work and preprints.
2026
-
Learning pole structures of hadronic states using predictive uncertainty estimationPhys. Rev. D, Mar 2026 -
2025
-
Discovering emergent connections in quantum physics research via dynamic word embeddingsMachine Learning: Science and Technology, Feb 2025 -
Learning density functionals from noisy quantum dataMachine Learning: Science and Technology, Feb 2025
2024
-
Explainable representation learning of small quantum statesMachine Learning: Science and Technology, Jan 2024 -
