English
Related papers

Related papers: Associative Recurrent Memory Transformer

200 papers

Attention mechanism is a significant part of Transformer models. It helps extract features from embedded vectors by adding global information and its expressivity has been proved to be powerful. Nevertheless, the quadratic complexity…

Machine Learning · Computer Science 2025-11-11 Hanwen Liu , Yixuan Ma , Shi Jin , Yuguang Wang

Recently, recurrent neural network transducer (RNN-T) gains increasing popularity due to its natural streaming capability as well as superior performance. Nevertheless, RNN-T training requires large time and computation resources as RNN-T…

Audio and Speech Processing · Electrical Eng. & Systems 2023-05-22 Keyu An , Xian Shi , Shiliang Zhang

Modern foundation model architectures rely on attention mechanisms to effectively capture context. However, these methods require linear or quadratic memory in terms of the number of inputs/datapoints, limiting their applicability in…

Machine Learning · Computer Science 2023-06-23 Leo Feng , Frederick Tung , Hossein Hajimirsadeghi , Yoshua Bengio , Mohamed Osama Ahmed

The Abstraction and Reasoning Corpus (ARC) is designed to assess generalization beyond pattern matching, requiring models to infer symbolic rules from very few examples. In this work, we present a transformer-based system that advances ARC…

A major limitation for the broader scope of problems solvable by transformers is the quadratic scaling of computational complexity with input size. In this study, we investigate the recurrent memory augmentation of pre-trained transformer…

Computation and Language · Computer Science 2024-02-07 Aydar Bulatov , Yuri Kuratov , Yermek Kapushev , Mikhail S. Burtsev

Autoregressive (AR) video diffusion is a powerful paradigm for streaming and interactive video generation. However, its reliance on softmax self-attention leads to quadratic compute complexity in sequence length and memory usage due to…

Computer Vision and Pattern Recognition · Computer Science 2026-05-22 Kunyang Li , Mubarak Shah , Yuzhang Shang

Adaptive Computation Time for Recurrent Neural Networks (ACT) is one of the most promising architectures for variable computation. ACT adapts to the input sequence by being able to look at each sample more than once, and learn how many…

Neural and Evolutionary Computing · Computer Science 2018-03-23 Daniel Fojo , Víctor Campos , Xavier Giro-i-Nieto

Efficiently handling long contexts in transformer-based language models with low perplexity is an active area of research. Numerous recent approaches like Linformer, Longformer, Performer, and Structured state space models (SSMs)., have not…

Machine Learning · Computer Science 2025-04-22 Sushant Singh , Ausif Mahmood

Sequential recommendation aims to recommend the next item of users' interest based on their historical interactions. Recently, the self-attention mechanism has been adapted for sequential recommendation, and demonstrated state-of-the-art…

Information Retrieval · Computer Science 2022-09-19 Bo Peng , Srinivasan Parthasarathy , Xia Ning

We present an attention-based modular neural framework for computer vision. The framework uses a soft attention mechanism allowing models to be trained with gradient descent. It consists of three modules: a recurrent attention module…

Machine Learning · Computer Science 2016-04-29 Samira Ebrahimi Kahou , Vincent Michalski , Roland Memisevic

Continual learning aims to provide intelligent agents capable of learning multiple tasks sequentially with neural networks. One of its main challenging, catastrophic forgetting, is caused by the neural networks non-optimal ability to learn…

Machine Learning · Computer Science 2021-01-29 Ghada Sokar , Decebal Constantin Mocanu , Mykola Pechenizkiy

Deploying useful Long-Context Transformer Models (LCTMs) requires addressing two key challenges: (1) A growing memory footprint due to quadratic self-attention and linear KV-cache scaling in memory as sequence length increases; (2) the…

Computation and Language · Computer Science 2025-10-15 Baisub Lee , Sanghyun Byun , Mohanad Odema , Jung Guack , Jacob Song , Woo Seong Chung

Effectively learning from sequential data is a longstanding goal of Artificial Intelligence, especially in the case of long sequences. From the dawn of Machine Learning, several researchers have pursued algorithms and architectures capable…

Machine Learning · Computer Science 2025-08-19 Matteo Tiezzi , Michele Casoni , Alessandro Betti , Marco Gori , Stefano Melacci

Long-context Large Language Models, despite their expanded capacity, require careful working memory management to mitigate attention dilution during long-horizon tasks. Yet existing approaches rely on external mechanisms that lack awareness…

Artificial Intelligence · Computer Science 2026-05-08 Yuxiang Zhang , Jiangming Shu , Ye Ma , Xueyuan Lin , Shangxi Wu , Jitao Sang

Large sequence model (SM) such as GPT series and BERT has displayed outstanding performance and generalization capabilities on vision, language, and recently reinforcement learning tasks. A natural follow-up question is how to abstract…

Multiagent Systems · Computer Science 2022-10-31 Muning Wen , Jakub Grudzien Kuba , Runji Lin , Weinan Zhang , Ying Wen , Jun Wang , Yaodong Yang

Recent advances in conversational systems have changed the search paradigm. Traditionally, a user poses a query to a search engine that returns an answer based on its index, possibly leveraging external knowledge bases and conditioning the…

Computation and Language · Computer Science 2017-12-21 Tom Kenter , Maarten de Rijke

Large Language Models (LLMs) encounter significant performance bottlenecks in long-sequence tasks due to the computational complexity and memory overhead inherent in the self-attention mechanism. To address these challenges, we introduce…

Artificial Intelligence · Computer Science 2026-02-17 Ziming Wang , Xiang Wang , Kailong Peng , Lang Qin , Juan Gabriel Kostelec , Christos Sourmpis , Axel Laborieux , Qinghai Guo

Recent advancements in video generation have demonstrated the potential of using video diffusion models as world models, with autoregressive generation of infinitely long videos through masked conditioning. However, such models, usually…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Taiye Chen , Zihan Ding , Anjian Li , Christina Zhang , Zeqi Xiao , Yisen Wang , Chi Jin

Transformer-based LLMs achieve strong results on many language tasks; however, long inputs remain challenging because context windows are finite, and prefill latency and memory grow rapidly with prompt length. Flat token-stream processing…

Computation and Language · Computer Science 2026-05-26 Maryam Haghifam , Zifan He , Jason Cong , Yizhou Sun

Over more than a decade there has been an extensive research effort on how to effectively utilize recurrent models and attention. While recurrent models aim to compress the data into a fixed-size memory (called hidden state), attention…

Machine Learning · Computer Science 2025-01-03 Ali Behrouz , Peilin Zhong , Vahab Mirrokni
‹ Prev 1 3 4 5 6 7 10 Next ›