Manifold steering along activation geometry induces behavioral trajectories matching the natural manifold of outputs, while linear steering produces off-manifold unnatural behaviors.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
Defines an injective carryless pairing map on naturals using disjoint Zeckendorf index bands separated by an x-derived delimiter, with Rocq-mechanized correctness.
Post-selection with DL or FBF after multi-objective GP search improves test-set performance over AIC/BIC baselines on noisy synthetic and real regression tasks, while using DL directly as fitness often causes premature convergence to overly simple models.
citing papers explorer
-
Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior
Manifold steering along activation geometry induces behavioral trajectories matching the natural manifold of outputs, while linear steering produces off-manifold unnatural behaviors.
-
Carryless Pairing: Additive Pairing in the Fibonacci Basis
Defines an injective carryless pairing map on naturals using disjoint Zeckendorf index bands separated by an x-derived delimiter, with Rocq-mechanized correctness.
-
Guiding Multi-Objective Genetic Programming with Description Length Improves Symbolic Regression Solutions
Post-selection with DL or FBF after multi-objective GP search improves test-set performance over AIC/BIC baselines on noisy synthetic and real regression tasks, while using DL directly as fitness often causes premature convergence to overly simple models.