concept
active
concept:diffusion-models-for-materialsDiffusion Models for Materials
Class of generative models adapted for molecular and materials design; MatterGen is an example.
Neighborhood — ranked by edge-count
Concepts (1)
concept
- Materials Discoveryassociated_withDomain of applying generative models to find novel materials with targeted properties (e.g., semiconductors with specific bandgaps).
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Generative models that reverse a noising process, mentioned in quasi-simulator table.
- A model explaining zebra stripes and other animal coat patterns, showing how roughness arises from interaction of regular processes with surface geometry.
- Computational models of crystal growth that produce rough overall symmetry but fail to explain the detailed identical sub-symmetries on snowflake arms
- Prior work on fixed-point convergence in deep networks, foundational to understanding looped model dynamics
- Large pretrained models used as backbones across tasks; their universality motivates the convergence hypothesis
- Making a land model in modelling clay at 1:200 scale to feel slopes and landforms accurately.
- Neural network models demonstrating how organized functional relationships emerge via unsupervised learning; basis for evolutionary connectionism analogy.