Local linearity of LLM layers enables LQR-based closed-loop activation steering with theoretical tracking guarantees.
Real-time optimal control of high- dimensional parametrized systems by deep learning-based reduced order models
2 Pith papers cite this work, alongside 1 external citations. Polarity classification is still indexing.
2
Pith papers citing it
1
external citations · external index
citation-role summary
method 1
citation-polarity summary
roles
method 1polarities
use method 1representative citing papers
A neural operator is trained once including a PDE residual penalty and then reused inside gradient-based optimization to solve multiple PDE-constrained tracking control problems.
citing papers explorer
-
Local Linearity of LLMs Enables Activation Steering via Model-Based Linear Optimal Control
Local linearity of LLM layers enables LQR-based closed-loop activation steering with theoretical tracking guarantees.
-
Employing Deep Neural Operators for PDE control by decoupling training and optimization
A neural operator is trained once including a PDE residual penalty and then reused inside gradient-based optimization to solve multiple PDE-constrained tracking control problems.