English
Related papers

Related papers: An Evolved Universal Transformer Memory

200 papers

Despite the recent progresses, particularly in developing Language Models, there are fundamental challenges and unanswered questions about how such models can continually learn/memorize, self-improve, and find effective solutions. In this…

Machine Learning · Computer Science 2026-01-01 Ali Behrouz , Meisam Razaviyayn , Peilin Zhong , Vahab Mirrokni

Large Language Models (LLMs) possess remarkable generalization capabilities but struggle with multi-task adaptation, particularly in balancing knowledge retention with task-specific specialization. Conventional fine-tuning methods suffer…

Artificial Intelligence · Computer Science 2025-10-21 Dayan Pan , Zhaoyang Fu , Jingyuan Wang , Xiao Han , Yue Zhu , Xiangyu Zhao

We present Adaptive Memory Networks (AMN) that processes input-question pairs to dynamically construct a network architecture optimized for lower inference times for Question Answering (QA) tasks. AMN processes the input story to extract…

Artificial Intelligence · Computer Science 2018-02-05 Daniel Li , Asim Kadav

Memory units have been widely used to enrich the capabilities of deep networks on capturing long-term dependencies in reasoning and prediction tasks, but little investigation exists on deep generative models (DGMs) which are good at…

Machine Learning · Computer Science 2016-05-31 Chongxuan Li , Jun Zhu , Bo Zhang

Transformer-based architectures have become the prevailing backbone of large language models. However, the quadratic time and memory complexity of self-attention remains a fundamental obstacle to efficient long-context modeling. To address…

Computation and Language · Computer Science 2026-02-10 Yutao Sun , Zhenyu Li , Yike Zhang , Tengyu Pan , Bowen Dong , Yuyi Guo , Jianyong Wang

Diffusion models have shown remarkable performance on many generative tasks. Despite recent success, most diffusion models are restricted in that they only allow linear transformation of the data distribution. In contrast, broader family of…

Machine Learning · Computer Science 2024-06-04 Grigory Bartosh , Dmitry Vetrov , Christian A. Naesseth

Neural networks using transformer-based architectures have recently demonstrated great power and flexibility in modeling sequences of many types. One of the core components of transformer networks is the attention layer, which allows…

Machine Learning · Computer Science 2019-07-16 Matthew Spellings

Transformer-based large language models (LLMs) excel in modeling complex language patterns but face significant computational costs during inference, especially with long inputs due to the attention mechanism's memory overhead. We observe…

Computation and Language · Computer Science 2024-10-18 Ruiqing Yan , Linghan Zheng , Xingbo Du , Han Zou , Yufeng Guo , Jianfei Yang

Transformer architectures based on the attention mechanism have revolutionized natural language processing (NLP), driving major breakthroughs across virtually every NLP task. However, their substantial memory and computational requirements…

Computation and Language · Computer Science 2026-03-25 Riccardo Bravin , Massimo Pavan , Hazem Hesham Yousef Shalby , Fabrizio Pittorino , Manuel Roveri

In this paper, we share our reflections and insights on understanding Transformer architectures through the lens of associative memory--a classic psychological concept inspired by human cognition. We start with the basics of associative…

Machine Learning · Computer Science 2025-05-27 Shu Zhong , Mingyu Xu , Tenglong Ao , Guang Shi

The concepts of unitary evolution matrices and associative memory have boosted the field of Recurrent Neural Networks (RNN) to state-of-the-art performance in a variety of sequential tasks. However, RNN still have a limited capacity to…

Machine Learning · Computer Science 2017-10-27 Rumen Dangovski , Li Jing , Marin Soljacic

This work introduces a novel Retention Layer mechanism for Transformer based architectures, addressing their inherent lack of intrinsic retention capabilities. Unlike human cognition, which can encode and dynamically recall symbolic…

Machine Learning · Computer Science 2025-01-17 M. Murat Yaslioglu

Neural networks augmented with external memory have the ability to learn algorithmic solutions to complex tasks. These models appear promising for applications such as language modeling and machine translation. However, they scale poorly in…

Machine Learning · Computer Science 2016-10-31 Jack W Rae , Jonathan J Hunt , Tim Harley , Ivo Danihelka , Andrew Senior , Greg Wayne , Alex Graves , Timothy P Lillicrap

Vision Foundation Models (VFMs) extract spatially downsampled representations, posing challenges for pixel-level tasks. Existing upsampling approaches face a fundamental trade-off: classical filters are fast and broadly applicable but rely…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Loick Chambon , Paul Couairon , Eloi Zablocki , Alexandre Boulch , Nicolas Thome , Matthieu Cord

Many large language model applications require conditioning on long contexts. Transformers typically support this by storing a large per-layer KV-cache of past activations, which incurs substantial memory overhead. A desirable alternative…

Computation and Language · Computer Science 2026-03-17 Yuri Kuratov , Matvey Kairov , Aydar Bulatov , Ivan Rodkin , Mikhail Burtsev

The success of the self-attention mechanism in classical machine learning models has inspired the development of quantum analogs aimed at reducing computational overhead. Self-attention integrates learnable query and key matrices to…

Previous studies on continual knowledge learning (CKL) in large language models (LLMs) have predominantly focused on approaches such as regularization, architectural modifications, and rehearsal techniques to mitigate catastrophic…

Computation and Language · Computer Science 2025-02-06 Yeongbin Seo , Dongha Lee , Jinyoung Yeo

Deep learning models require extensive architecture design exploration and hyperparameter optimization to perform well on a given task. The exploration of the model design space is often made by a human expert, and optimized using a…

Artificial Intelligence · Computer Science 2017-10-31 Catherine Wong , Andrea Gesmundo

Recently, large pre-trained neural language models have attained remarkable performance on many downstream natural language processing (NLP) applications via fine-tuning. In this paper, we target at how to further improve the token…

Artificial Intelligence · Computer Science 2021-09-08 Mengyuan Zhou , Jian Ma , Haiqin Yang , Lianxin Jiang , Yang Mo

Neural Machine Translation (NMT) leverages one or more trained neural networks for the translation of phrases. Sutskever introduced a sequence to sequence based encoder-decoder model which became the standard for NMT based systems.…

Computation and Language · Computer Science 2020-06-11 Satish Mylapore , Ryan Quincy Paul , Joshua Yi , Robert D. Slater
‹ Prev 1 4 5 6 7 8 10 Next ›