Periodic Materials Generation using Text-Guided Joint Diffusion Model

• URL: http://arxiv.org/abs/2503.00522v1
• Date: Sat, 01 Mar 2025 14:56:44 GMT
• Title: Periodic Materials Generation using Text-Guided Joint Diffusion Model
• Authors: Kishalay Das, Subhojyoti Khastagir, Pawan Goyal, Seung-Cheol Lee, Satadeep Bhattacharjee, Niloy Ganguly,
• Abstract summary: TGDMat is a novel text-guided diffusion model designed for 3D periodic material generation.<n>Our approach integrates global structural knowledge through textual descriptions at each denoising step.<n>Our experiments reveal that TGDMat outperforms existing baseline methods by a good margin.
• Score: 23.137596469096824
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Equivariant diffusion models have emerged as the prevailing approach for generating novel crystal materials due to their ability to leverage the physical symmetries of periodic material structures. However, current models do not effectively learn the joint distribution of atom types, fractional coordinates, and lattice structure of the crystal material in a cohesive end-to-end diffusion framework. Also, none of these models work under realistic setups, where users specify the desired characteristics that the generated structures must match. In this work, we introduce TGDMat, a novel text-guided diffusion model designed for 3D periodic material generation. Our approach integrates global structural knowledge through textual descriptions at each denoising step while jointly generating atom coordinates, types, and lattice structure using a periodic-E(3)-equivariant graph neural network (GNN). Extensive experiments using popular datasets on benchmark tasks reveal that TGDMat outperforms existing baseline methods by a good margin. Notably, for the structure prediction task, with just one generated sample, TGDMat outperforms all baseline models, highlighting the importance of text-guided diffusion. Further, in the generation task, TGDMat surpasses all baselines and their text-fusion variants, showcasing the effectiveness of the joint diffusion paradigm. Additionally, incorporating textual knowledge reduces overall training and sampling computational overhead while enhancing generative performance when utilizing real-world textual prompts from experts.

Related papers

• GeodesicNVS: Probability Density Geodesic Flow Matching for Novel View Synthesis [54.39598154430305]
  We propose a Data-to-Data Flow Matching framework that learns deterministic transformations directly between paired views.<n>PDG-FM constrains flow trajectories using geodesic interpolants derived from probability density metrics of pretrained diffusion models.<n>These results highlight the advantages of incorporating data-dependent geometric regularization into deterministic flow matching for consistent novel view generation.
  arXiv  Detail & Related papers  (2026-03-01T09:30:11Z)
• TabDLM: Free-Form Tabular Data Generation via Joint Numerical-Language Diffusion [45.45604062258755]
  Real-world datasets increasingly contain free-form text fields alongside structured numerical and categorical attributes.<n>Existing approaches fall into two categories: diffusion-based methods and LLM-based methods.<n>We propose TabDLM, a unified framework for free-form tabular data generation via a joint numerical-language diffusion model.
  arXiv  Detail & Related papers  (2026-02-26T03:41:49Z)
• Edit2Perceive: Image Editing Diffusion Models Are Strong Dense Perceivers [55.15722080205737]
  Edit2Perceive is a unified diffusion framework that adapts editing models for depth, normal, and matting.<n>Our single-step deterministic inference yields up to faster runtime while training on relatively small datasets.
  arXiv  Detail & Related papers  (2025-11-24T01:13:51Z)
• GeoGNN: Quantifying and Mitigating Semantic Drift in Text-Attributed Graphs [59.61242815508687]
  Graph neural networks (GNNs) on text--attributed graphs (TAGs) encode node texts using pretrained language models (PLMs) and propagate these embeddings through linear neighborhood aggregation.<n>This work introduces a local PCA-based metric that measures the degree of semantic drift and provides the first quantitative framework to analyze how different aggregation mechanisms affect manifold structure.
  arXiv  Detail & Related papers  (2025-11-12T06:48:43Z)
• GNN-CNN: An Efficient Hybrid Model of Convolutional and Graph Neural Networks for Text Representation [0.0]
  This study introduces a novel model architecture that combines Graph Neural Networks (GNNs) and Convolutional Neural Networks (CNNs)<n>The model processes compact batches of character-level inputs without requiring padding or truncation.<n>It captures local contextual patterns using CNNs, expands local receptive fields via lattice-based graph structures, and employs small-world graphs to aggregate document-level information.
  arXiv  Detail & Related papers  (2025-07-10T04:13:53Z)
• Statistical learning of structure-property relationships for transport in porous media, using hybrid AI modeling [0.0]
  The 3D microstructure of porous media significantly impacts the resulting macroscopic properties, including effective diffusivity or permeability. quantitative structure-property relationships are crucial for further optimizing the performance of porous media. The present paper uses 90,000 virtually generated 3D microstructures of porous media derived from literature. The paper extends these findings by applying a hybrid AI framework to this data set.
  arXiv  Detail & Related papers  (2025-03-27T14:46:40Z)
• Unifying Text Semantics and Graph Structures for Temporal Text-attributed Graphs with Large Language Models [19.710059031046377]
  Temporal graph neural networks (TGNNs) have shown remarkable performance in temporal graph modeling. We present textbfCross, a novel framework that seamlessly extends existing TGNNs for TTAG modeling.
  arXiv  Detail & Related papers  (2025-03-18T16:50:10Z)
• Causal Discovery from Data Assisted by Large Language Models [50.193740129296245]
  It is essential to integrate experimental data with prior domain knowledge for knowledge driven discovery. Here we demonstrate this approach by combining high-resolution scanning transmission electron microscopy (STEM) data with insights derived from large language models (LLMs) By fine-tuning ChatGPT on domain-specific literature, we construct adjacency matrices for Directed Acyclic Graphs (DAGs) that map the causal relationships between structural, chemical, and polarization degrees of freedom in Sm-doped BiFeO3 (SmBFO)
  arXiv  Detail & Related papers  (2025-03-18T02:14:49Z)
• CAST: Cross Attention based multimodal fusion of Structure and Text for materials property prediction [5.623295547221969]
  Cross-attention-based model integrates graph representations with textual descriptions of materials.<n>CAST outperforms existing baseline models across four key material properties.<n>This study underscores the potential of multimodal learning frameworks for developing more accurate and globally informed predictive models in materials science.
  arXiv  Detail & Related papers  (2025-02-06T02:29:39Z)
• Open Materials Generation with Stochastic Interpolants [14.939468363546384]
  We introduce Open Materials Generation (OMG), a unifying framework for the generative design and discovery of crystalline materials.<n>OMG employs inorganic interpolants (SI) to bridge an arbitrary base distribution to the target distribution of crystals.<n>We benchmark OMG's performance on two tasks: Crystal Structure Prediction (CSP) for specified compositions, and 'de novo' generation (DNG) aimed at discovering stable, novel, and unique structures.
  arXiv  Detail & Related papers  (2025-02-04T18:56:47Z)
• DeFoG: Discrete Flow Matching for Graph Generation [45.037260759871124]
  We propose DeFoG, a novel framework using discrete flow matching for graph generation. DeFoG employs a flow-based approach that features an efficient linear noising process and a flexible denoising process. We show that DeFoG achieves state-of-the-art results on synthetic and molecular datasets.
  arXiv  Detail & Related papers  (2024-10-05T18:52:54Z)
• ComboStoc: Combinatorial Stochasticity for Diffusion Generative Models [65.82630283336051]
  We show that the space spanned by the combination of dimensions and attributes is insufficiently sampled by existing training scheme of diffusion generative models. We present a simple fix to this problem by constructing processes that fully exploit the structures, hence the name ComboStoc.
  arXiv  Detail & Related papers  (2024-05-22T15:23:10Z)
• Compositional Abilities Emerge Multiplicatively: Exploring Diffusion Models on a Synthetic Task [20.749514363389878]
  We study compositional generalization in conditional diffusion models in a synthetic setting. We find that the order in which the ability to generate samples emerges is governed by the structure of the underlying data-generating process. Our study lays a foundation for understanding capabilities and compositionality in generative models from a data-centric perspective.
  arXiv  Detail & Related papers  (2023-10-13T18:00:59Z)
• 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)
• Reduce, Reuse, Recycle: Compositional Generation with Energy-Based Diffusion Models and MCMC [102.64648158034568]
  diffusion models have quickly become the prevailing approach to generative modeling in many domains. We propose an energy-based parameterization of diffusion models which enables the use of new compositional operators. We find these samplers lead to notable improvements in compositional generation across a wide set of problems.
  arXiv  Detail & Related papers  (2023-02-22T18:48:46Z)
• DIFFormer: Scalable (Graph) Transformers Induced by Energy Constrained Diffusion [66.21290235237808]
  We introduce an energy constrained diffusion model which encodes a batch of instances from a dataset into evolutionary states. We provide rigorous theory that implies closed-form optimal estimates for the pairwise diffusion strength among arbitrary instance pairs. Experiments highlight the wide applicability of our model as a general-purpose encoder backbone with superior performance in various tasks.
  arXiv  Detail & Related papers  (2023-01-23T15:18:54Z)
• Structure-based Drug Design with Equivariant Diffusion Models [40.73626627266543]
  We present DiffSBDD, an SE(3)-equivariant diffusion model that generates novel conditioned on protein pockets. Our in silico experiments demonstrate that DiffSBDD captures the statistics of the ground truth data effectively. These results support the assumption that diffusion models represent the complex distribution of structural data more accurately than previous methods.
  arXiv  Detail & Related papers  (2022-10-24T15:51:21Z)
• Model Criticism for Long-Form Text Generation [113.13900836015122]
  We apply a statistical tool, model criticism in latent space, to evaluate the high-level structure of generated text. We perform experiments on three representative aspects of high-level discourse -- coherence, coreference, and topicality. We find that transformer-based language models are able to capture topical structures but have a harder time maintaining structural coherence or modeling coreference.
  arXiv  Detail & Related papers  (2022-10-16T04:35:58Z)
• Improving Compositional Generalization with Self-Training for Data-to-Text Generation [36.973617793800315]
  We study the compositional generalization of current generation models in data-to-text tasks. By simulating structural shifts in the compositional Weather dataset, we show that T5 models fail to generalize to unseen structures. We propose an approach based on self-training using finetuned BLEURT for pseudo-response selection.
  arXiv  Detail & Related papers  (2021-10-16T04:26:56Z)

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.