Diffusion Tree Sampling for Inference Time Adaptation of Crystal Generative Models

Published
Source
arXiv
Paper number
1467
Field
Machine Learning
arXiv ID
2611.17462

Key points

  • The authors applied DTS to crystal generation by treating the denoising trajectory of diffusion models as a Monte Carlo tree search tree steering toward a reward-tilted distribution.
  • When using conditional generative models as search proposals, importance weights correct for double tilting and preserve the target distribution.
  • The multi-objective extension MO-DTS keeps per-objective value estimates and samples a preference each traversal, so a single tree samples the whole Pareto front.
  • In MatterGen experiments at matched compute, the number of stable structures rose from a baseline of 868 up to 1432, with the stability rate rising from 68.4% to 75.7%.
  • In DiffCSP experiments, the stability rate kept increasing as the compute budget grew from 105 to 107 NFEs, showing inference-time scaling.
  • As a limitation, the method relies on pretrained predictors for reward evaluation, and experimental synthesis validation remains a separate step.

Paper links

External research summaries. These are not HDATF publications or measured product results.

Read original (opens in a new tab)