Understanding the Foundation: How LLMs Process Your Input

First of four parts Before we can understand how attackers exploit large language models, we need to understand how these models work. This first article in our four-part series on prompt injections ...
eLife

“What” × “When” working memory representations using Laplace Neural Manifolds

The results include a comparison between two different basis functions for temporal selectivity and how these generate different predictions for the dynamics of neural populations. The conclusions are ...
IEEE

Output-Feedback Adaptive Periodic Disturbances Attenuation for Linear MIMO Systems Subject to Input Delay

Abstract: This paper presents a novel output-feedback direct adaptive controller with a decoupling design to completely attenuate periodic disturbances in the linear multi-input multi-output (MIMO) ...
IEEE

Flexible Prescribed Performance Output Feedback Control for Nonlinear Systems With Input Saturation

Abstract: A flexible prescribed performance control (FPPC) approach for input saturated nonlinear systems (ISNSs) with unmeasurable states is first presented in this article. Compared to the standard ...