arXiv AI November 5, 2026 By Kasra Fallah, Rudramani Singha, Hannah Ghanei, Paul Sajda, James Anderson, Erfan Zabeh

Mind Control of LLMs via Closed-Loop Stimulation: Out-of-Distribution Robustness

arXiv:2611. 06418v1 Announce Type: cross Abstract: Brains and large language models need not be considered equivalent systems to reveal an interpretable commonality: both exhibit high-dimensional, nonlinear dynamics whose behavior can only be modeled imperfectly.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Hugging Face Trending Papers

2d ago

Mind Control of LLMs via Closed-Loop Stimulation: Out-of-Distribution Robustness

Brains and large language models need not be considered equivalent systems to reveal an interpretable commonality: both exhibit high-dimensional, nonlinear dynamics whose behavior can only be modeled...

llms benchmarks

arXiv Machine Learning

Jun 9

Beyond Linear Activation Steering: Invertible Latent Transformations for Controlling LLM Behavior

arXiv:2606. 08454v1 Announce Type: new Abstract: Activation steering provides a lightweight inference-time mechanism for controlling large language models (LLMs) by modifying their internal activation vectors toward desired behaviors.

By Tuc Nguyen, Thai Le

llms diffusion benchmarks safety

arXiv Machine Learning

Jun 19

Leverage Is Not Reach: A Control-Window Law for Single-Neuron Steering in Language Models

arXiv:2606. 19831v1 Announce Type: cross Abstract: Aligned language models gate behaviors such as refusal and language routing through sparse feed forward neurons, yet no theory predicts when a single neuron intervention controls a behavior coherently rather than collapsing the output.

By Hongliang Liu

llms safety

arXiv Machine Learning

Oct 21

High-dimensional layer-state trajectories reveal the internal dynamics of transformer inference

arXiv:2610.26866v1 Announce Type: new Abstract: Mechanistic studies of large language models localize function in parameters, attention heads or neurons, but those parts do not specify how one infere...

By Heng Zhao, Yufei Wang, Ruidian Song, Weisheng Chen

llms safety

arXiv AI

Jul 29

Minimizing Targeted Activations: Input-Only Suppression of Evaluation-Awareness Latents in Large Language Models

arXiv:2607. 25907v1 Announce Type: cross Abstract: Activation steering controls model behavior by editing internal activations at inference time.

By Deepanshu Mody, Samarth Agarwal, Utkarsh Mittal, Dipesh Mahato

llms safety

arXiv Machine Learning

Jun 24

Parallel Manifold Steering: Efficient Adaptation of Large Associative Memories via Residual Energy Shaping

arXiv:2606. 24396v1 Announce Type: new Abstract: Large Transformer models function as Dense Associative Memories (DAMs), retrieving knowledge via high-dimensional attractor dynamics driven by the self-attention mechanism \citep{ramsauer2020hopfield, wu2024attention}.

By Kanishk Awadhiya

llms fine-tuning

One email a morning, machine-written

Related stories

Mind Control of LLMs via Closed-Loop Stimulation: Out-of-Distribution Robustness

Beyond Linear Activation Steering: Invertible Latent Transformations for Controlling LLM Behavior

Leverage Is Not Reach: A Control-Window Law for Single-Neuron Steering in Language Models

High-dimensional layer-state trajectories reveal the internal dynamics of transformer inference

Minimizing Targeted Activations: Input-Only Suppression of Evaluation-Awareness Latents in Large Language Models

Parallel Manifold Steering: Efficient Adaptation of Large Associative Memories via Residual Energy Shaping