Postdoc, Los Alamos National Laboratory
2 papers at NeurIPS 2025
We introduce a challenging benchmark to evaluate LLMs' mathematical reasoning and code-writing abilities, finding that specialized models like o1-mini outperform earlier ones but still struggle overall.
This paper presents Discrete Spatial Diffusion, a generative model for discrete-state data that ensures mass conservation, enabling applications in scientific domains like materials science, also demonstrating results on popular image benchmarks.
