MetaGen: A DSL, Database, and Benchmark for VLM-Assisted Metamaterial Generation

• URL: http://arxiv.org/abs/2508.17568v1
• Date: Mon, 25 Aug 2025 00:36:07 GMT
• Title: MetaGen: A DSL, Database, and Benchmark for VLM-Assisted Metamaterial Generation
• Authors: Liane Makatura, Benjamin Jones, Siyuan Bian, Wojciech Matusik,
• Abstract summary: Metamaterials are micro-architected structures whose geometry imparts highlytrivial properties.<n>Yet their design is difficult because of geometric complexity and a non-trivial mapping from architecture to behaviour.<n>We address these challenges with three complementary contributions.
• Score: 25.181982772360612
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Metamaterials are micro-architected structures whose geometry imparts highly tunable-often counter-intuitive-bulk properties. Yet their design is difficult because of geometric complexity and a non-trivial mapping from architecture to behaviour. We address these challenges with three complementary contributions. (i) MetaDSL: a compact, semantically rich domain-specific language that captures diverse metamaterial designs in a form that is both human-readable and machine-parsable. (ii) MetaDB: a curated repository of more than 150,000 parameterized MetaDSL programs together with their derivatives-three-dimensional geometry, multi-view renderings, and simulated elastic properties. (iii) MetaBench: benchmark suites that test three core capabilities of vision-language metamaterial assistants-structure reconstruction, property-driven inverse design, and performance prediction. We establish baselines by fine-tuning state-of-the-art vision-language models and deploy an omni-model within an interactive, CAD-like interface. Case studies show that our framework provides a strong first step toward integrated design and understanding of structure-representation-property relationships.

Related papers

• PoseGAM: Robust Unseen Object Pose Estimation via Geometry-Aware Multi-View Reasoning [49.66437612420291]
  PoseGAM is a geometry-aware multi-view framework that directly predicts object pose from a query image and multiple template images.<n>We construct a large-scale synthetic dataset containing more than 190k objects under diverse environmental conditions.
  arXiv  Detail & Related papers  (2025-12-11T17:29:25Z)
• MoRE: 3D Visual Geometry Reconstruction Meets Mixture-of-Experts [50.37005070020306]
  MoRE is a dense 3D visual foundation model based on a Mixture-of-Experts (MoE) architecture.<n>MoRE incorporates a confidence-based depth refinement module that stabilizes and refines geometric estimation.<n>It integrates dense semantic features with globally aligned 3D backbone representations for high-fidelity surface normal prediction.
  arXiv  Detail & Related papers  (2025-10-31T06:54:27Z)
• Toward a Robust and Generalizable Metamaterial Foundation Model [3.0049721990828084]
  We introduce the Metamaterial Foundation Model (MetaFO), a Bayesian transformer-based foundation model inspired by large language models.<n>By treating metamaterials as an operator that maps material properties to structural responses, MetaFO uncovers intricate structure-property relationships.<n>This scalable and generalizable framework marks a paradigm shift in AI-driven metamaterial discovery, paving the way for next-generation innovations.
  arXiv  Detail & Related papers  (2025-07-03T08:48:36Z)
• GIQ: Benchmarking 3D Geometric Reasoning of Vision Foundation Models with Simulated and Real Polyhedra [33.53387523266523]
  We introduce GIQ, a benchmark specifically designed to evaluate the geometric reasoning capabilities of vision and vision-language foundation models.<n> GIQ comprises synthetic and real-world images of 224 diverse polyhedra.
  arXiv  Detail & Related papers  (2025-06-09T20:11:21Z)
• Spatial Understanding from Videos: Structured Prompts Meet Simulation Data [79.52833996220059]
  We present a unified framework for enhancing 3D spatial reasoning in pre-trained vision-language models without modifying their architecture.<n>This framework combines SpatialMind, a structured prompting strategy that decomposes complex scenes and questions into interpretable reasoning steps, with ScanForgeQA, a scalable question-answering dataset built from diverse 3D simulation scenes.
  arXiv  Detail & Related papers  (2025-06-04T07:36:33Z)
• MetamatBench: Integrating Heterogeneous Data, Computational Tools, and Visual Interface for Metamaterial Discovery [35.74367505796871]
  We introduce a unified framework, named MetamatBench, that operates on three levels.<n>At the data level, we integrate and standardize 5 heterogeneous, multi-modal metamaterial datasets.<n>The ML level provides a comprehensive toolkit that adapts 17 state-of-the-art ML methods for metamaterial discovery.<n>The user level features a visual-interactive interface that bridges the gap between complex ML techniques and non-ML researchers.
  arXiv  Detail & Related papers  (2025-05-08T19:23:59Z)
• ArtGS: Building Interactable Replicas of Complex Articulated Objects via Gaussian Splatting [66.29782808719301]
  Building articulated objects is a key challenge in computer vision.<n>Existing methods often fail to effectively integrate information across different object states.<n>We introduce ArtGS, a novel approach that leverages 3D Gaussians as a flexible and efficient representation.
  arXiv  Detail & Related papers  (2025-02-26T10:25:32Z)
• 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)
• Multi-objective Generative Design of Three-Dimensional Composite Materials [12.258353990252312]
  We report a Wasserstein generative adversarial network (MDWGAN) to implement inverse designs of 3D composite structures. Our framework is capable of tuning the properties of the generated composites in multiple aspects, while keeping the selected features of different kinds of structures.
  arXiv  Detail & Related papers  (2023-02-26T17:45:44Z)
• How to See Hidden Patterns in Metamaterials with Interpretable Machine Learning [82.67551367327634]
  We develop a new interpretable, multi-resolution machine learning framework for finding patterns in the unit-cells of materials. Specifically, we propose two new interpretable representations of metamaterials, called shape-frequency features and unit-cell templates.
  arXiv  Detail & Related papers  (2021-11-10T21:19:02Z)
• Deep Generative Modeling for Mechanistic-based Learning and Design of Metamaterial Systems [20.659457956055366]
  We propose a novel data-driven metamaterial design framework based on deep generative modeling. We show in this study that the latent space of VAE provides a distance metric to measure shape similarity. We demonstrate our framework by designing both functionally graded and heterogeneous metamaterial systems.
  arXiv  Detail & Related papers  (2020-06-27T03:56:55Z)
• Revealing the Invisible with Model and Data Shrinking for Composite-database Micro-expression Recognition [49.463864096615254]
  We analyze the influence of learning complexity, including the input complexity and model complexity. We propose a recurrent convolutional network (RCN) to explore the shallower-architecture and lower-resolution input data. We develop three parameter-free modules to integrate with RCN without increasing any learnable parameters.
  arXiv  Detail & Related papers  (2020-06-17T06:19:24Z)

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.