Enregistré dans:
Détails bibliographiques
Auteurs principaux: Jiang, Siyu, Cui, Sanshuai, Zeng, Hui
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2602.22702
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866912928097107968
author Jiang, Siyu
Cui, Sanshuai
Zeng, Hui
author_facet Jiang, Siyu
Cui, Sanshuai
Zeng, Hui
contents Existing neural network calibration methods often treat calibration as a static, post-hoc optimization task. However, this neglects the dynamic and temporal nature of real-world inference. Moreover, existing methods do not provide an intuitive interface enabling human operators to dynamically adjust model behavior under shifting conditions. In this work, we propose Knob, a framework that connects deep learning with classical control theory by mapping neural gating dynamics to a second-order mechanical system. By establishing correspondences between physical parameters -- damping ratio ($ζ$) and natural frequency ($ω_n$) -- and neural gating, we create a tunable "safety valve". The core mechanism employs a logit-level convex fusion, functioning as an input-adaptive temperature scaling. It tends to reduce model confidence particularly when model branches produce conflicting predictions. Furthermore, by imposing second-order dynamics (Knob-ODE), we enable a \textit{dual-mode} inference: standard i.i.d. processing for static tasks, and state-preserving processing for continuous streams. Our framework allows operators to tune "stability" and "sensitivity" through familiar physical analogues. This paper presents an exploratory architectural interface; we focus on demonstrating the concept and validating its control-theoretic properties rather than claiming state-of-the-art calibration performance. Experiments on CIFAR-10-C validate the calibration mechanism and demonstrate that, in Continuous Mode, the gate responses are consistent with standard second-order control signatures (step settling and low-pass attenuation), paving the way for predictable human-in-the-loop tuning.
format Preprint
id arxiv_https___arxiv_org_abs_2602_22702
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Knob: A Physics-Inspired Gating Interface for Interpretable and Controllable Neural Dynamics
Jiang, Siyu
Cui, Sanshuai
Zeng, Hui
Artificial Intelligence
Existing neural network calibration methods often treat calibration as a static, post-hoc optimization task. However, this neglects the dynamic and temporal nature of real-world inference. Moreover, existing methods do not provide an intuitive interface enabling human operators to dynamically adjust model behavior under shifting conditions. In this work, we propose Knob, a framework that connects deep learning with classical control theory by mapping neural gating dynamics to a second-order mechanical system. By establishing correspondences between physical parameters -- damping ratio ($ζ$) and natural frequency ($ω_n$) -- and neural gating, we create a tunable "safety valve". The core mechanism employs a logit-level convex fusion, functioning as an input-adaptive temperature scaling. It tends to reduce model confidence particularly when model branches produce conflicting predictions. Furthermore, by imposing second-order dynamics (Knob-ODE), we enable a \textit{dual-mode} inference: standard i.i.d. processing for static tasks, and state-preserving processing for continuous streams. Our framework allows operators to tune "stability" and "sensitivity" through familiar physical analogues. This paper presents an exploratory architectural interface; we focus on demonstrating the concept and validating its control-theoretic properties rather than claiming state-of-the-art calibration performance. Experiments on CIFAR-10-C validate the calibration mechanism and demonstrate that, in Continuous Mode, the gate responses are consistent with standard second-order control signatures (step settling and low-pass attenuation), paving the way for predictable human-in-the-loop tuning.
title Knob: A Physics-Inspired Gating Interface for Interpretable and Controllable Neural Dynamics
topic Artificial Intelligence
url https://arxiv.org/abs/2602.22702