Manifold Steering (Wurgaft)

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

• Manifold Steeringconcept0.841
  Central framework: steering neural networks by intervening along the curved manifold where a concept lives, rather than in straight lines through activation space.
• Manifold steering for neural network controlconcept0.758
• Manifold geometry provides a practical steering blueprint in an image-action model predicting car position on a hill, extending results across modalities.finding0.749
  Cross-modality result from the full paper demonstrating that representation-behavior geometry alignment is not limited to language models.
• Self-correcting search employs the same conceptual move as Wurgaft's manifold steering, applied to chemistry instead of LMsclaim0.747
  Interpretive assertion that the internal-state feedback mechanism mirrors manifold steering from prior work.
• Steering along manifolds provides better control than linear steering when the concept geometry is non-linear.claim0.745
  The central thesis of the paper, motivating the shift from linear to geometry-aware manifold steering.
• Manifold-respecting steering produces smooth natural behavioral trajectories while linear steering teleports between non-adjacent concepts.claim0.743
• Manifold steering demonstrates bidirectional geometry-behavior link in a video world model on tasks with geometry corresponding to physical dynamicsfinding0.740
  Extension of manifold steering validation to video world models and physical dynamics tasks, demonstrating cross-modal generality
• Manifold-aware steering is non-trivial IP requiring geometric analysis, not a system-prompt implementation.claim0.734