3 papers
cond-mat.mtrl-sci2025
Flow Matching for Accelerated Simulation of Atomic Transport in Crystalline Materials
Juno Nam, Sulin Liu, Gavin Winter +3
Atomic transport underpins the performance of materials in technologies such as energy storage and electronics, yet its simulation remains computationally demanding. In particular,…
cs.LG2025
Think While You Generate: Discrete Diffusion with Planned Denoising
Sulin Liu, Juno Nam, Andrew Campbell +4
Discrete diffusion has achieved state-of-the-art performance, outperforming or approaching autoregressive models on standard benchmarks. In this work, we introduce Discrete Diffusi…
cs.LG2024
Generative Marginalization Models
Sulin Liu, Peter J. Ramadge, Ryan P. Adams
We introduce marginalization models (MAMs), a new family of generative models for high-dimensional discrete data. They offer scalable and flexible generative modeling by explicitly…