cd /news/machine-learning/diffusion-tree-sampling-for-inferenc… · home › topics › machine-learning › article
[ARTICLE · art-170321] src=arxiv.org ↗ pub= topic=machine-learning verified=true sentiment=↑ positive

Diffusion Tree Sampling for Inference Time Adaptation of Crystal Generative Models

A new arXiv paper (2611.17462v1) introduces two extensions to Diffusion Tree Sampling (DTS), a Monte Carlo tree search procedure over the denoising trajectory, for adapting crystal generative models at inference time without fine-tuning. The authors show how to use existing property-conditional generative models, such as models fine-tuned for classifier-free guidance, as guided proposals inside DTS without distorting the target distribution, and extend DTS to multi-objective sampling so a single search produces samples spanning an entire Pareto front. Applied to de novo crystal generation, the DTS-based adaptation improved crystal stability across models, generated crystals in rare space groups or with high bulk modulus using pretrained conditional models, and produced crystals along a Pareto front of high dielectric constant and high bandgap materials, all without modifying the underlying models.

by read1 min views1 publishedNov 16, 2026

arXiv:2611.17462v1 Announce Type: new Abstract: Diffusion-based generative models have become strong priors over plausible crystal structures, but turning that prior into promising candidates requires steering toward several conflicting properties at once. Fine-tuning is expensive and produces a new model for every new objective, while differentiable guidance is not applicable to many real-world tasks. We instead adapt these generative models at inference time using Diffusion Tree Sampling (DTS), a Monte Carlo tree search procedure over the denoising trajectory. We make two technical contributions on top of DTS that are particularly relevant for AI-for-science applications. First, we show how to use existing property-conditional generative models (e.g., models fine-tuned for classifier-free guidance) as guided proposals inside DTS, without distorting the target distribution. Second, we extend DTS to multi-objective sampling, so that a single search produces samples spanning an entire Pareto front. We instantiate both adaptations on de novo crystal generation: improving the stability of crystals generated by different models, using pretrained conditional models to generate crystals belonging to rare space groups or with high bulk modulus, and generating crystals along a Pareto front of high dielectric constant and high bandgap materials. Across these tasks, DTS-based inference-time adaptation successfully improves model outputs without modifying the models themselves.

── more in #machine-learning 4 stories · sorted by recency
── more on @diffusion tree sampling 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/diffusion-tree-sampl…] indexed:0 read:1min 2026-11-16 · —