Papers/2611.17462
🧪 Test?View on arXiv

Diffusion Tree Sampling for Inference Time Adaptation of Crystal Generative Models

Not provided in the abstract

generative modelsMonte Carlomulti-objective optimizationAI-for-science
2611.17462
Builder Relevance
70%
19h ago

Abstract

The paper presents a method for adapting diffusion-based generative models at inference time to generate crystal structures with conflicting properties.

Reality Card

Core Claim

The introduction of Diffusion Tree Sampling (DTS) allows for effective inference-time adaptation of generative models to produce diverse crystal structures without modifying the models themselves.

Method / Result

DTS successfully generates samples spanning an entire Pareto front for multiple objectives.

Limitations

The paper does not provide specific details on the reproducibility of the results or the datasets used.

Paper to code

Verified implementation resources so builders can test the paper’s claims instead of stopping at the abstract.

No verified implementation link has been attached yet. AIBuzzHub will keep this panel separate from unverified search results.
← Back to all papers