English
Related papers

Related papers: Associative Recurrent Memory Transformer

200 papers

An essential component of modern recurrent sequence models is the forget gate. While Transformers do not have an explicit recurrent form, we show that a forget gate can be naturally incorporated into Transformers by down-weighting the…

Machine Learning · Computer Science 2025-04-02 Zhixuan Lin , Evgenii Nikishin , Xu Owen He , Aaron Courville

Autoregressive transformers have shown remarkable success in video generation. However, the transformers are prohibited from directly learning the long-term dependency in videos due to the quadratic complexity of self-attention, and…

Computer Vision and Pattern Recognition · Computer Science 2023-06-01 Jaehoon Yoo , Semin Kim , Doyup Lee , Chiheon Kim , Seunghoon Hong

End-to-end automatic speech recognition (ASR) models, including both attention-based models and the recurrent neural network transducer (RNN-T), have shown superior performance compared to conventional systems. However, previous studies…

Memory-augmented neural networks consisting of a neural controller and an external memory have shown potentials in long-term sequential learning. Current RAM-like memory models maintain memory accessing every timesteps, thus they do not…

Machine Learning · Computer Science 2019-03-21 Hung Le , Truyen Tran , Svetha Venkatesh

Large Language Models (LLMs) have shown remarkable performance in multi-turn dialogue. However, in multi-turn dialogue, models still struggle to stay aligned with what has been established earlier, follow dependencies across many turns, and…

Computation and Language · Computer Science 2026-01-12 Jiawei Shen , Jia Zhu , Hanghui Guo , Weijie Shi , Yue Cui , Qingyu Niu , Guoqing Ma , Yidan Liang , Jingjiang Liu , Yiling Wang , Shimin Di , Jiajie Xu

To sustain coherent long-term interactions, Large Language Model (LLM) agents must navigate the tension between acquiring new information and retaining prior knowledge. Current unified stream-based memory systems facilitate context updates…

Artificial Intelligence · Computer Science 2026-04-15 Zhaofen Wu , Hanrong Zhang , Fulin Lin , Wujiang Xu , Xinran Xu , Yankai Chen , Henry Peng Zou , Shaowen Chen , Weizhi Zhang , Xue Liu , Philip S. Yu , Hongwei Wang

Modern language agents must operate over long-horizon, multi-turn interactions, where they retrieve external information, adapt to observations, and answer interdependent queries. Yet, most LLM systems rely on full-context prompting,…

Computation and Language · Computer Science 2025-07-18 Zijian Zhou , Ao Qu , Zhaoxuan Wu , Sunghwan Kim , Alok Prakash , Daniela Rus , Jinhua Zhao , Bryan Kian Hsiang Low , Paul Pu Liang

Recent development of agents has renewed demand for long-context reasoning capacity of LLMs. However, training LLMs for this capacity requires costly long-document curation or heuristic context synthesis. We observe that agents produce…

Computation and Language · Computer Science 2026-05-22 Qisheng Su , Zhen Fang , Shiting Huang , Yu Zeng , Yiming Zhao , Kou Shi , Ziao Zhang , Lin Chen , Zehui Chen , Lijun Wu , Feng Zhao

Training deep recurrent neural network (RNN) architectures is complicated due to the increased network complexity. This disrupts the learning of higher order abstracts using deep RNN. In case of feed-forward networks training deep…

Computation and Language · Computer Science 2018-08-07 Murali Karthick Baskar , Martin Karafiat , Lukas Burget , Karel Vesely , Frantisek Grezl , Jan Honza Cernocky

There is a growing interest in the speech community in developing Recurrent Neural Network Transducer (RNN-T) models for automatic speech recognition (ASR) applications. RNN-T is trained with a loss function that does not enforce temporal…

Computation and Language · Computer Science 2020-11-20 Jay Mahadeokar , Yuan Shangguan , Duc Le , Gil Keren , Hang Su , Thong Le , Ching-Feng Yeh , Christian Fuegen , Michael L. Seltzer

Catastrophic forgetting and capacity saturation are the central challenges of any parametric lifelong learning system. In this work, we study these challenges in the context of sequential supervised learning with an emphasis on recurrent…

Machine Learning · Computer Science 2019-09-10 Shagun Sodhani , Sarath Chandar , Yoshua Bengio

The brain must robustly store a large number of memories, corresponding to the many events encountered over a lifetime. However, the number of memory states in existing neural network models either grows weakly with network size or recall…

Neurons and Cognition · Quantitative Biology 2017-11-06 Rishidev Chaudhuri , Ila Fiete

In this paper, we demonstrate that an inherent waveform pattern in the attention allocation of large language models (LLMs) significantly affects their performance in tasks demanding a high degree of context awareness, such as utilizing…

Computation and Language · Computer Science 2024-06-05 Yuhan Chen , Ang Lv , Ting-En Lin , Changyu Chen , Yuchuan Wu , Fei Huang , Yongbin Li , Rui Yan

Long-range sequence modeling is a crucial aspect of natural language processing and time series analysis. However, traditional models like Recurrent Neural Networks (RNNs) and Transformers suffer from computational and memory…

Artificial Intelligence · Computer Science 2025-01-15 Mohamed A. Taha

Lengthy documents pose a unique challenge to neural language models due to substantial memory consumption. While existing state-of-the-art (SOTA) models segment long texts into equal-length snippets (e.g., 128 tokens per snippet) or deploy…

Computation and Language · Computer Science 2024-05-14 Guangzeng Han , Jack Tsao , Xiaolei Huang

Large language model (LLM) agents are constrained by limited context windows, necessitating external memory systems for long-term information understanding. Current memory-augmented agents typically depend on pre-defined instructions and…

Computation and Language · Computer Science 2025-10-01 Yu Wang , Ryuichi Takanobu , Zhiqi Liang , Yuzhen Mao , Yuanzhe Hu , Julian McAuley , Xiaojian Wu

Artificial neural networks suffer from catastrophic forgetting when they are sequentially trained on multiple tasks. To overcome this problem, we present a novel approach based on task-conditioned hypernetworks, i.e., networks that generate…

Machine Learning · Computer Science 2022-04-12 Johannes von Oswald , Christian Henning , Benjamin F. Grewe , João Sacramento

Transformer networks, driven by self-attention, are central to Large Language Models. In generative Transformers, self-attention uses cache memory to store token projections, avoiding recomputation at each time step. However, GPU-stored…

Neural and Evolutionary Computing · Computer Science 2024-11-26 Nathan Leroux , Paul-Philipp Manea , Chirag Sudarshan , Jan Finkbeiner , Sebastian Siegel , John Paul Strachan , Emre Neftci

Transfer learning aims to solve the data sparsity for a target domain by applying information of the source domain. Given a sequence (e.g. a natural language sentence), the transfer learning, usually enabled by recurrent neural network…

Computation and Language · Computer Science 2019-02-26 Wanyun Cui , Guangyu Zheng , Zhiqiang Shen , Sihang Jiang , Wei Wang

Video semantic segmentation requires to utilize the complex temporal relations between frames of the video sequence. Previous works usually exploit accurate optical flow to leverage the temporal relations, which suffer much from heavy…

Computer Vision and Pattern Recognition · Computer Science 2021-09-14 Hao Wang , Weining Wang , Jing Liu
‹ Prev 1 8 9 10 Next ›