DiffGA: Steering Frozen Diffusion Models for Materials Design via Evolutionary Search

arXiv:2610.14999 · cond-mat.mtrl-sci, cs.LG · Submitted 2026-10-10 · Read on arXiv

cond-mat.mtrl-sci, cs.LG

Submitted: 2026-10-10

Updated: 2026-10-10

Terminology

• Diffusion Model — 1× in this paper · explained in 9 episodes
• Diffusion Models — 1× in this paper · explained in 6 episodes
• Steering — 1× in this paper · explained in 2 episodes

Sources

• Scaling Autoregressive Multi-Modal Models: Pretraining and Instruction Tuning
• Muse: Text-To-Image Generation via Masked Generative Transformers
• SymbolicAI: A framework for logic-based approaches combining generative models and solvers
• GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation
• Scalable Diffusion for Materials Generation
• Inference-Time Alignment of Diffusion Models via Evolutionary Algorithms
• Diffusion-based Evolutionary Optimization for 3D Multi-Objective Molecular Generation
• MatterSim: A Deep Learning Atomistic Model Across Elements, Temperatures and Pressures
• UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
• Accelerating inverse materials design using generative diffusion models with reinforcement learning
• Open Materials Generation with Inference-Time Reinforcement Learning
• Surrogate-Gated Generation and Foundation-Model Embeddings for Bayesian Materials Design

Related papers

• Mode-selective electron-phonon coupling drives charge density waves in the kagome metals YRu 3 Si 2 and LaRu 3 Si 2
• Restoring the Surface Magnetic Gap in MnBi 2 Te 4
• ATLAS: A Foundation Neural Sampler for Amorphous Materials
• A Generalizable Machine Learning Framework for Half-Heusler Thermoelectrics
• Nonlinear dynamics in magnonic Fabry-P' e rot resonators: Low-power neuron-like activation and transmission suppression
• AES-Debye: an Accurate, Efficient, and Scalable Engine for Debye Scattering Calculations