Context is All You Need

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Delanois, Jean Erik, Joshi, Shruti, Golden, Ryan, Nick, Teresa, Bazhenov, Maxim
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915917646004224
author Delanois, Jean Erik
Joshi, Shruti
Golden, Ryan
Nick, Teresa
Bazhenov, Maxim
author_facet Delanois, Jean Erik
Joshi, Shruti
Golden, Ryan
Nick, Teresa
Bazhenov, Maxim
contents Artificial Neural Networks (ANNs) are increasingly deployed across diverse real-world settings, where they must operate under data distributions that differ from those seen during training. This challenge is central to Domain Generalization (DG), which trains models to generalize to unseen domains without target data, and Test-Time Adaptation (TTA), which improves robustness by adapting to unlabeled test data at deployment. Existing approaches to address these challenges are often complex, resource-intensive, and difficult to scale. We introduce CONTXT (Contextual augmentatiOn for Neural feaTure X Transforms), a simple and intuitive method for contextual adaptation. CONTXT modulates internal representations using simple additive and multiplicative feature transforms. Within a TTA setting, it yields consistent gains across discriminative tasks (e.g., ANN/CNN classification) and generative models (e.g., LLMs). The method is lightweight, easy to integrate, and incurs minimal overhead, enabling robust performance under domain shift without added complexity. More broadly, CONTXT provides a compact way to steer information flow and neural processing without retraining.
format Preprint
id arxiv_https___arxiv_org_abs_2604_04364
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Context is All You Need
Delanois, Jean Erik
Joshi, Shruti
Golden, Ryan
Nick, Teresa
Bazhenov, Maxim
Machine Learning
Artificial Intelligence
Artificial Neural Networks (ANNs) are increasingly deployed across diverse real-world settings, where they must operate under data distributions that differ from those seen during training. This challenge is central to Domain Generalization (DG), which trains models to generalize to unseen domains without target data, and Test-Time Adaptation (TTA), which improves robustness by adapting to unlabeled test data at deployment. Existing approaches to address these challenges are often complex, resource-intensive, and difficult to scale. We introduce CONTXT (Contextual augmentatiOn for Neural feaTure X Transforms), a simple and intuitive method for contextual adaptation. CONTXT modulates internal representations using simple additive and multiplicative feature transforms. Within a TTA setting, it yields consistent gains across discriminative tasks (e.g., ANN/CNN classification) and generative models (e.g., LLMs). The method is lightweight, easy to integrate, and incurs minimal overhead, enabling robust performance under domain shift without added complexity. More broadly, CONTXT provides a compact way to steer information flow and neural processing without retraining.
title Context is All You Need
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2604.04364