A new BDM variant formalizes reuse of program code across blocks as an NP-hard optimization problem, relates gains to algorithmic mutual information, and proves improvement over independent block descriptions under stated conditions.
Shannon information and Kolmogorov complexity
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
Manifold steering along activation geometry induces behavioral trajectories matching the natural manifold of outputs, while linear steering produces off-manifold unnatural behaviors.
Proposes a semantic information theory for LLMs that substitutes the token for the bit as the atomic carrier of meaning, recasts the Transformer as an energy-based model, and derives directed rate-distortion and rate-reward functions using Massey's directed information.
citing papers explorer
-
Tighter Bounds for Algorithmic Complexity Estimation Using a Reusable Code-Based Block Decomposition Method
A new BDM variant formalizes reuse of program code across blocks as an NP-hard optimization problem, relates gains to algorithmic mutual information, and proves improvement over independent block descriptions under stated conditions.
-
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.
-
Forget BIT, It is All about TOKEN: Towards Semantic Information Theory for LLMs
Proposes a semantic information theory for LLMs that substitutes the token for the bit as the atomic carrier of meaning, recasts the Transformer as an energy-based model, and derives directed rate-distortion and rate-reward functions using Massey's directed information.