method
active
method:self-correcting-search

Self-Correcting Search

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

Neighborhood — ranked by edge-count

Findings (1)

finding

Concepts (8)

concept
  • Manifold Steering
    associated_with
    Central framework: steering neural networks by intervening along the curved manifold where a concept lives, rather than in straight lines through activation space.
  • Framework of using internal-state representations to control or steer generative models; conceptually parallel to manifold steering in language models.
  • General approach of using interpretability feedback to steer model generation.
  • Domain of applying generative models to find novel materials with targeted properties (e.g., semiconductors with specific bandgaps).
  • Mechanism of using internal activations or representations to create corrective feedback during generation.
  • Specific materials discovery task: generating semiconductor candidates with desired electronic bandgap using conditioned diffusion.
  • Target output of the materials discovery process: candidate semiconductor materials.
  • Desired electronic bandgap for semiconductor candidates.

Artifacts (1)

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

Related by similarity (8)

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.