{"slug": "diffusion-tree-sampling-for-inference-time-adaptation-of-crystal-generative", "title": "Diffusion Tree Sampling for Inference Time Adaptation of Crystal Generative Models", "summary": "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.", "body_md": "arXiv:2611.17462v1 Announce Type: new \nAbstract: 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.", "url": "https://wpnews.pro/news/diffusion-tree-sampling-for-inference-time-adaptation-of-crystal-generative", "canonical_source": "https://arxiv.org/abs/2611.17462", "published_at": "2026-11-16 05:00:00+00:00", "updated_at": "2026-11-16 05:24:01.833662+00:00", "lang": "en", "topics": ["machine-learning", "ai-research", "generative-ai", "artificial-intelligence"], "entities": ["Diffusion Tree Sampling", "arXiv", "Monte Carlo tree search", "classifier-free guidance"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/diffusion-tree-sampling-for-inference-time-adaptation-of-crystal-generative", "markdown": "https://wpnews.pro/news/diffusion-tree-sampling-for-inference-time-adaptation-of-crystal-generative.md", "text": "https://wpnews.pro/news/diffusion-tree-sampling-for-inference-time-adaptation-of-crystal-generative.txt", "jsonld": "https://wpnews.pro/news/diffusion-tree-sampling-for-inference-time-adaptation-of-crystal-generative.jsonld"}}