LEIA: Learned Environment for Interactive Architected Materials

arXiv 2026 56.9 method, benchmark, application

TLDR

LEIA is a world model for interactive simulation of architected materials, enabling real-time deformation and stress field prediction.

Reasoning

The paper introduces a novel world model for physical engineering, addressing complex material behaviors with a benchmark and design search application. However, it lacks real-world experimental validation and focuses on simulated data.

Read-first score

Read-first score 56.9, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 45.

Recency 6%

100

Uses a gentle age decay so recent papers surface without erasing older foundations. 2026

Citation impact 18%

82.1

Uses OpenAlex-shaped citation metadata as a bibliometric attention signal, separate from paper quality. citation_normalized_percentile=0.82066467

Methodology quality 18%

Screens visible abstract and analysis fields for experiment, dataset, baseline, metric, and limitation evidence. markers=baseline,benchmark,result

Topical relevance 29%

64.3

Uses existing LLM keyword relevance scores normalized to 0-100. world model,world simulator,generative world model,interactive world model,video world model,world dynamics prediction,model-based reinforcement learning world model

Reproducibility 18%

Screens links and visible text for paper, code, dataset, artifact, and repository signals. pdf=True; code=False; dataset=False; markers=none

Citation velocity 12%

Citation velocity estimates citations per publication-year to reduce old-paper bias. velocity=0.00

Field roles

FoundationFrontierBridgeMethodology anchor

Rank sensitivity

Stability: volatile; rank range: 334.

Keyword Scores

world model

interactive world model

world simulator

generative world model

world dynamics prediction

video world model

model-based reinforcement learning world model

Deep Analysis

Innovations

LEIA: a world model for interactive exploration of architected materials, enabling real-time deformation and stress field observation under user-specified boundary conditions.
MicroPlate: a benchmark of architected plates covering two microstructure modeling regimes (explicit 3D geometry and homogeneous plate with internal degrees of freedom).
Autoregressive generation of responses to user loading on large three-dimensional unstructured meshes.
Surrogate-guided candidate generation and ranking for de novo design of architected materials, validated by finite element ground truth.

Methodology

LEIA is a world model that handles large three-dimensional unstructured meshes and generates autoregressive responses to user-specified loading. It is assessed using the MicroPlate benchmark, which spans two regimes of microstructure modeling: architected lattices with explicit 3D geometry and a homogeneous plate with implicit internal degrees of freedom. Four baseline methods are compared across both regimes.

Key Results

LEIA enables efficient candidate generation and ranking for fast surrogate-guided search for de novo designs of architected materials, with stress-accurate candidate ranking validated by finite element ground truth.

Resources

Paper