Papers
Publications
Papers, preprints, and research threads across AI, physics, chemistry, and adjacent curiosities ✦
Selected Publications
Towards Scalable One-Step Generative Modeling for Autoregressive Dynamical System Forecasting
Under Review...
First autoregressive one-step generative model for dynamical systems.
MENO: MeanFlow-Enhanced Neural Operators for Dynamical Systems
Under Review...
One-step generative modelling for multiscale fluid dynamics with neural operators.
Uni-Flow: a unified autoregressive-diffusion model for complex multiscale flows
Under Review...
Generative modelling for complex multiscale fluid dynamics.
2026
Understanding Galaxy Morphology Evolution Through Cosmic Time via Redshift Conditioned Diffusion Models
University of Cambridge, Department of Physics
Survey of generative models for astrophysical image synthesis.
Accelerating Redshift-Conditioned Galaxy Image Synthesis with One-step Generative Modeling
Under Review...
One-step generative modelling for astrophysical image synthesis.
Towards Scalable One-Step Generative Modeling for Autoregressive Dynamical System Forecasting
Under Review...
First autoregressive one-step generative model for dynamical systems.
Physical Fidelity Reconstruction via Improved Consistency-Distilled Flow Matching for Dynamical Systems
Under Review...
Distilled one-step generative fidelity reconstruction for physical systems.
MENO: MeanFlow-Enhanced Neural Operators for Dynamical Systems
Under Review...
One-step generative modelling for multiscale fluid dynamics with neural operators.
Uni-Flow: a unified autoregressive-diffusion model for complex multiscale flows
Under Review...
Generative modelling for complex multiscale fluid dynamics.
2025
Equivariant U-shaped Neural Operators for the Cahn-Hilliard Phase-field Model
Under Review...
Equivariant operator learning for phase-field modelling.
Investigating Atomic and Molecular Systems in Ultra-strong Magnetic Fields Using Neural Network Variational Monte Carlo
Imperial College London, Department of Physics
Neural network ansatz for VMC in strong magnetic fields.