Towards Automated Discovery: A Review of Generative Models, Multimodal Learning and Closed-Loop Workflows in Inverse Materials Design

• URL: http://arxiv.org/abs/2606.02507v1
• Date: Mon, 01 Jun 2026 17:20:55 GMT
• Title: Towards Automated Discovery: A Review of Generative Models, Multimodal Learning and Closed-Loop Workflows in Inverse Materials Design
• Abstract summary: We review advances in generative crystal structure modeling, multimodal learning, and closed-loop design pipelines for crystalline solids.<n>We discuss how multimodal learning fuses diverse materials modalities, including crystal structures, thermodynamic, electronic information, microscopy, spectroscopy, processing context, and scientific text.<n>We highlight recurring failure modes, such as surrogate exploitation, diversity collapse, distribution shift, and the stability-synthesizability gap.
• Score: 0.528869303898094
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Inverse materials design is shifting materials discovery from forward prediction to targeted proposal of candidates that satisfy objectives under physical constraints. Here, we review recent advances in generative crystal structure modeling, multimodal learning, and closed-loop design pipelines for crystalline solids. We survey how modern generators learn chemical-structural priors from large databases to enable controllable sampling of periodic structures, and compare leading model classes including variational autoencoders, normalizing flows, autoregressive formulations, and diffusion models. Particular attention is given to how feasibility constraints and physical priors are enforced across the workflow, through representation choices, training objectives, sampling-time guidance, and post-generation screening and relaxation. We also discuss how multimodal learning fuses diverse materials modalities, including crystal structures, thermodynamic, electronic information, microscopy, spectroscopy, processing context, and scientific text, to construct a more universal, transferable representation of chemical space. In addition, diverse inverse-design strategies are examined, particularly those that integrate conditional generation with latent optimization, Bayesian optimization, reinforcement learning, and active learning. Finally, we highlight recurring failure modes, such as surrogate exploitation, diversity collapse, distribution shift, and the stability-synthesizability gap, and outline discovery-grade evaluation practices based on staged reporting of validity, novelty, uniqueness, stability, and cost.

Related papers

• Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and Recipes [57.55143519213221]
  We provide empirical clarity through a systematic exploration of multimodal pretraining.<n>Our experiments on both synthetic and large-scale real-world datasets yield four key insights into the physics of multimodal pretraining.
  arXiv  Detail & Related papers  (2026-08-05T16:09:25Z)
• A Systematic Survey and Benchmark of Deep Learning for Molecular Property Prediction in the Foundation Model Era [57.5440098776759]
  Molecular property prediction integrates quantum chemistry, cheminformatics, and deep learning to connect molecular structure with biological behavior.<n>This survey traces four complementary paradigms, including Quantum, Descriptor Machine Learning, Geometric Deep Learning, and Foundation Models.<n> Benchmark analyses integrate evidence from both widely used datasets and datasets reflecting industry perspectives.
  arXiv  Detail & Related papers  (2026-04-17T15:16:33Z)
• Finetuning-Free Diffusion Model with Adaptive Constraint Guidance for Inorganic Crystal Structure Generation [7.4621033210394545]
  We propose a generative machine learning framework based on diffusion models with adaptive constraint guidance.<n>Our approach has been tested and validated on several classical examples of inorganic families of compounds.
  arXiv  Detail & Related papers  (2026-04-14T23:25:54Z)
• Generative Modeling in Protein Design: Neural Representations, Conditional Generation, and Evaluation Standards [3.8025175740783026]
  Generative modeling has become a central paradigm in protein research.<n>This survey aims to accelerate the transition from predictive modeling to reliable, function-driven protein engineering.
  arXiv  Detail & Related papers  (2026-03-27T13:02:16Z)
• Towards Agentic Intelligence for Materials Science [73.4576385477731]
  This survey advances a unique pipeline-centric view that spans from corpus curation and pretraining to goal-conditioned agents interfacing with simulation and experimental platforms.<n>To bridge communities and establish a shared frame of reference, we first present an integrated lens that aligns terminology, evaluation, and workflow stages across AI and materials science.
  arXiv  Detail & Related papers  (2026-01-29T23:48:43Z)
• Generative models for crystalline materials [5.856518802859891]
  This review analyzes the current state of generative modeling for crystal structure prediction and textitde novo generation.<n>It examines crystal representations, outlines the generative models used to design crystal structures, and evaluates their respective strengths and limitations.<n>Ultimately, this work aims to inform both experimental scientists looking to adapt suitable ML models to their specific circumstances and ML specialists seeking to understand the unique challenges related to inverse materials design and discovery.
  arXiv  Detail & Related papers  (2025-11-27T17:42:10Z)
• Guiding Generative Models to Uncover Diverse and Novel Crystals via Reinforcement Learning [13.437119411600499]
  We introduce a reinforcement learning framework that guides latent denoising diffusion models toward diverse, yet thermodynamically viable crystalline compounds.<n>Our approach integrates group relative policy optimisation with verifiable, multi-objective rewards that jointly balance creativity, stability, and diversity.<n>This approach establishes a modular foundation for controllable AI-driven inverse design that addresses the novelty-validity trade-off across scientific discovery applications of generative models.
  arXiv  Detail & Related papers  (2025-11-10T14:48:49Z)
• Efficient Regression-Based Training of Normalizing Flows for Boltzmann Generators [85.25962679349551]
  Boltzmann Generators (BGs) offer efficient sampling and likelihoods, but their training via maximum likelihood is often unstable and computationally challenging.<n>We propose Regression Training of Normalizing Flows (RegFlow), a novel and scalable-based training objective that bypasses the numerical instability and computational challenge of conventional maximum likelihood training.
  arXiv  Detail & Related papers  (2025-06-01T20:32:27Z)
• Autoregressive regularized score-based diffusion models for multi-scenarios fluid flow prediction [0.0]
  We propose a conditional score-based diffusion model for multi-scenarios fluid flow prediction.<n>Our model integrates an energy constraint rooted in the statistical properties of turbulent flows.<n>It achieves accurate results across multiple scenarios while preserving key physical and statistical properties.
  arXiv  Detail & Related papers  (2025-05-30T02:37:05Z)
• Will Pre-Training Ever End? A First Step Toward Next-Generation Foundation MLLMs via Self-Improving Systematic Cognition [89.50068130832635]
  Self-Improving cognition (SIcog) is a self-learning framework for constructing next-generation foundation MLLMs by multimodal knowledge.<n>We propose Chain-of-Description for step-by-step visual understanding and integrate structured Chain-of-Thought (CoT) reasoning to support in-depth multimodal reasoning.<n>Experiments demonstrate SIcog's effectiveness in developing MLLMs with enhanced multimodal cognition.
  arXiv  Detail & Related papers  (2025-03-16T00:25:13Z)
• Scalable Diffusion for Materials Generation [99.71001883652211]
  We develop a unified crystal representation that can represent any crystal structure (UniMat) UniMat can generate high fidelity crystal structures from larger and more complex chemical systems. We propose additional metrics for evaluating generative models of materials.
  arXiv  Detail & Related papers  (2023-10-18T15:49:39Z)
• Geometric Deep Learning for Structure-Based Drug Design: A Survey [83.87489798671155]
  Structure-based drug design (SBDD) leverages the three-dimensional geometry of proteins to identify potential drug candidates. Recent advancements in geometric deep learning, which effectively integrate and process 3D geometric data, have significantly propelled the field forward.
  arXiv  Detail & Related papers  (2023-06-20T14:21:58Z)
• Latent Traversals in Generative Models as Potential Flows [113.4232528843775]
  We propose to model latent structures with a learned dynamic potential landscape. Inspired by physics, optimal transport, and neuroscience, these potential landscapes are learned as physically realistic partial differential equations. Our method achieves both more qualitatively and quantitatively disentangled trajectories than state-of-the-art baselines.
  arXiv  Detail & Related papers  (2023-04-25T15:53:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.