Manifold steering along activation geometry induces behavioral trajectories matching the natural manifold of outputs, while linear steering produces off-manifold unnatural behaviors.
arXiv preprint arXiv:2408.10920 , year =
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
verdicts
UNVERDICTED 4representative citing papers
The Linear Accessibility Profile predicts steering vector effectiveness and optimal layers with Spearman correlations of 0.86-0.91 using unembedding projections on intermediate states across multiple models and concepts.
AR-KAN combines a pre-trained AR module with KAN to reduce redundancy while preserving temporal features, delivering lower probabilistic approximation error and stronger forecasting results on synthetic almost-periodic signals and real datasets.
A mechanics of the learning process is emerging in deep learning theory, characterized by dynamics, coarse statistics, and falsifiable predictions across idealized settings, limits, laws, hyperparameters, and universal behaviors.
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.
-
Predicting Where Steering Vectors Succeed
The Linear Accessibility Profile predicts steering vector effectiveness and optimal layers with Spearman correlations of 0.86-0.91 using unembedding projections on intermediate states across multiple models and concepts.
-
AR-KAN: Autoregressive-Weight-Enhanced Kolmogorov-Arnold Network for Time Series Forecasting
AR-KAN combines a pre-trained AR module with KAN to reduce redundancy while preserving temporal features, delivering lower probabilistic approximation error and stronger forecasting results on synthetic almost-periodic signals and real datasets.
-
There Will Be a Scientific Theory of Deep Learning
A mechanics of the learning process is emerging in deep learning theory, characterized by dynamics, coarse statistics, and falsifiable predictions across idealized settings, limits, laws, hyperparameters, and universal behaviors.