# Cached Transformers: Improving Transformers with Differentiable Memory Cache

Source: [Cached Transformers: Improving Transformers with Differentiable Memory Cache](<https://www.sota2.com/research/paper/68fa71841e209131cea51b76>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T02:08:33.784Z

Authors: Zhaoyang Zhang, Wenqi Shao, Yixiao Ge, Xiaogang Wang, Jinwei Gu, Ping Luo

Published: 2023-12-20T03:30:51.000Z

## Abstract

This work introduces a new Transformer model called Cached Transformer, which uses Gated Recurrent Cached (GRC) attention to extend the self-attention mechanism with a differentiable memory cache of tokens. GRC attention enables attending to both past and current tokens, increasing the receptive field of attention and allowing for exploring long-range dependencies. By utilizing a recurrent gating unit to continuously update the cache, our model achieves significant advancements in \\textbf{six} language and vision tasks, including language modeling, machine translation, ListOPs, image classification, object detection, and instance segmentation. Furthermore, our approach surpasses previous memory-based techniques in tasks such as language modeling and displays the ability to be applied to a broader range of situations.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2312.12742>)

[PDF](<https://arxiv.org/pdf/2312.12742.pdf>)