concept
active
concept:manifold-steering

Manifold Steering

Central framework: steering neural networks by intervening along the curved manifold where a concept lives, rather than in straight lines through activation space.

Neighborhood — ranked by edge-count

Thinkers (1)

thinker
  • Wurgaft
    studies
    Researcher whose manifold steering concept is referenced as the same conceptual move underlying self-correcting search.

Frameworks (2)

framework
  • The set of geometric properties that appear in all living structure: levels of scale, strong centers, boundaries, echoes, gradients, deep interlock and ambiguity, local symmetries, roughness, inner calm, not separateness, and others.
  • The overarching theoretical framework proposed in the paper, asserting that steering interventions should be aligned with the geometric structure of the model's representation manifold.

Communities (1)

community

Claims (1)

claim

Methods (6)

method
  • linear steering
    contradictsextends
    Typical approach that adds a scaled steering vector to representations; the paper argues this is mismatched with actual representation geometry.
  • Self-Correcting Search
    associated_with
    Technique using internal model representations as feedback loops to steer diffusion-based materials generation toward target properties.
  • Method to fit a manifold M_h to neural representations in activation space.
  • Method to fit a manifold M_y to output probability distributions.
  • The procedure of fitting a one-dimensional manifold (path) to clusters in activation or behavior space to capture the geometric structure of a concept.
  • The general experimental approach of intervening along geometrically-defined paths rather than single-point or linear-direction interventions

Concepts (18)

concept

Findings (2)

finding

Venues (1)

venue
  • Publication venue for Wurgaft et al. manifold steering paper.

Events (1)

event
  • Coordinated release of three papers (Geiger manifesto, Feucht Geometric Calculator, Wurgaft Manifold Steering) establishing neural geometry framework.

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.