Cover Image

Local Linearity of LLMs Enables Activation Steering via Model-Based Linear Optimal Control

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Skifstad, Julian, Yang, Xinyue Annie, Chou, Glen
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence Systems and Control Optimization and Control
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Parallel Differentiable Reachability for Learning and Planning with Certified Neural Dynamics and Controllers
by: Shen, Keyi, et al.
Published: (2026)

Scalable Data-Driven Reachability Analysis and Control via Koopman Operators with Conformal Coverage Guarantees
by: Nath, Devesh, et al.
Published: (2026)

Active Constraint Learning in High Dimensions from Demonstrations
by: Qiu, Zheng, et al.
Published: (2025)

Fitted Q-Iteration via Max-Plus-Linear Approximation
by: Liu, Y., et al.
Published: (2024)

Analysis of Thompson Sampling for Controlling Unknown Linear Diffusion Processes
by: Faradonbeh, Mohamad Kazem Shirani, et al.
Published: (2022)

Sublinear Regret for a Class of Continuous-Time Linear-Quadratic Reinforcement Learning Problems
by: Huang, Yilie, et al.
Published: (2024)

Formal Safety Verification and Refinement for Generative Motion Planners via Certified Local Stabilization
by: Nath, Devesh, et al.
Published: (2025)

Nonlinear Non-Gaussian Density Steering with Input and Noise Channel Mismatch: Sinkhorn with Memory for Solving the Control-affine Schrödinger Bridge Problem
by: Bondar, Georgiy A., et al.
Published: (2026)

Data-Driven Exploration for a Class of Continuous-Time Indefinite Linear--Quadratic Reinforcement Learning Problems
by: Huang, Yilie, et al.
Published: (2025)

Safe Large-Scale Robust Nonlinear MPC in Milliseconds via Reachability-Constrained System Level Synthesis on the GPU
by: Fang, Jeffrey, et al.
Published: (2026)

Benchmarking Reinforcement Learning via Stochastic Converse Optimality: Generating Systems with Known Optimal Policies
by: Ibrahim, Sinan, et al.
Published: (2026)

Optimal Control Operator Perspective and a Neural Adaptive Spectral Method
by: Feng, Mingquan, et al.
Published: (2024)

Co-Learning Port-Hamiltonian Systems and Optimal Energy-Shaping Control
by: Kamboj, Ankur, et al.
Published: (2026)

Optimal Power Grid Operations with Foundation Models
by: Puech, Alban, et al.
Published: (2024)

Mutual Information Optimal Control of Discrete-Time Linear Systems
by: Enami, Shoju, et al.
Published: (2025)

On Policy Stochasticity in Mutual Information Optimal Control of Linear Systems
by: Enami, Shoju, et al.
Published: (2025)

Optimal Output Feedback Learning Control for Discrete-Time Linear Quadratic Regulation
by: Xie, Kedi, et al.
Published: (2025)

Safety Beyond the Training Data: Robust Out-of-Distribution MPC via Conformalized System Level Synthesis
by: Srinivasan, Anutam, et al.
Published: (2026)

Asynchronous Distributed Reinforcement Learning for LQR Control via Zeroth-Order Block Coordinate Descent
by: Jing, Gangshan, et al.
Published: (2021)

Markov Kernels, Distances and Optimal Control: A Parable of Linear Quadratic Non-Gaussian Distribution Steering
by: Teter, Alexis M. H., et al.
Published: (2025)

Action Dependency Graphs for Globally Optimal Coordinated Reinforcement Learning
by: Ding, Jianglin, et al.
Published: (2025)

PGLearn -- An Open-Source Learning Toolkit for Optimal Power Flow
by: Klamkin, Michael, et al.
Published: (2025)

Fixed Horizon Linear Quadratic Covariance Steering in Continuous Time with Hilbert-Schmidt Terminal Cost
by: Sial, Tushar, et al.
Published: (2025)

Mutual Information Optimal Density Control of Linear Systems and Generalized Schrödinger Bridges with Reference Refinement
by: Enami, Shoju, et al.
Published: (2026)

Differentiable Optimization for Deep Learning-Enhanced DC Approximation of AC Optimal Power Flow
by: Rosemberg, Andrew, et al.
Published: (2025)

Optimal Centered Active Excitation in Linear System Identification
by: Ito, Kaito, et al.
Published: (2026)

Physics-informed Gaussian Processes as Linear Model Predictive Controller
by: Tebbe, Jörn, et al.
Published: (2024)

gridfm-datakit-v1: A Python Library for Scalable and Realistic Power Flow and Optimal Power Flow Data Generation
by: Puech, Alban, et al.
Published: (2025)

CLT-Optimal Parameter Error Bounds for Linear System Identification
by: Zhou, Yichen, et al.
Published: (2026)

On the Hopf-Cole Transform for Control-affine Schrödinger Bridge
by: Teter, Alexis, et al.
Published: (2025)

Revisiting LQR Control from the Perspective of Receding-Horizon Policy Gradient
by: Zhang, Xiangyuan, et al.
Published: (2023)

Bridging Control with Neural Network Verifier alpha-beta-CROWN: A Tutorial
by: Li, Haoyu, et al.
Published: (2026)

Data-Driven Density Steering via the Gromov-Wasserstein Optimal Transport Distance
by: Nakashima, Haruto, et al.
Published: (2025)

Dual Control of Linear Systems from Bilinear Observations with Belief Space Model Predictive Control
by: Cao, Daniel, et al.
Published: (2026)

Lyapunov Function Consistent Adaptive Network Signal Control with Back Pressure and Reinforcement Learning
by: Ma, Chaolun, et al.
Published: (2022)

Online Control of Linear Systems under Unbounded Noise
by: Ito, Kaito, et al.
Published: (2024)

A New Approach to Controlling Linear Dynamical Systems
by: Brahmbhatt, Anand, et al.
Published: (2025)

Hereditary Geometric Meta-RL: Nonlocal Generalization via Task Symmetries
by: Nitschke, Paul, et al.
Published: (2026)

CORL: Reinforcement Learning of MILP Policies Solved via Branch and Bound
by: Anand, Akhil S, et al.
Published: (2025)

Intersection of Reinforcement Learning and Bayesian Optimization for Intelligent Control of Industrial Processes: A Safe MPC-based DPG using Multi-Objective BO
by: Esfahani, Hossein Nejatbakhsh, et al.
Published: (2025)