Materials Discovery

Domain of applying generative models to find novel materials with targeted properties (e.g., semiconductors with specific bandgaps).

Neighborhood — ranked by edge-count

method

Self-Correcting Search
about
Technique using internal model representations as feedback loops to steer diffusion-based materials generation toward target properties.

artifact

MatterGen
about
Diffusion model for materials generation; baseline system achieving 6.5% success rate on bandgap-targeted candidates.

concept

Diffusion Models for Materials
associated_with
Class of generative models adapted for molecular and materials design; MatterGen is an example.

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

Discoveryconcept0.814
Drug discoveryconcept0.796
Application domain suggested for the method, involving generation of drug candidates.
possibility of discoveryconcept0.780
Another outcome proportional to environmental variables in the theory.
Mathematical Discoveryconcept0.779
Discovery of geometric/topological truths (e.g., neusis construction) that go beyond current AI capabilities, as discussed by Sloman.
Physical Materials, Shapes, and Phenomenaconcept0.769
Natural Building Materialsmethod0.727
Use of locally available, untreated wood, rock, and plant material in restoration structures (principle 7).
Materials, shapes, smells, electricity, magnetism, gravity, gases, fluids, sounds, music, motion, chemical reactions, fire, people, animals, plants, words, concepts, and ideasconcept0.705
The enumerated categories of environmental variables that children engage with and that drive creativity and discovery.
Agential Materialconcept0.698
The view that biological substrates have intrinsic competencies, computational abilities, and homeodynamic setpoints, not merely passive matter.