English
Related papers

Related papers: mGRADE: Minimal Recurrent Gating Meets Delay Convo…

200 papers

Training deep learning models on embedded devices is typically avoided since this requires more memory, computation and power over inference. In this work, we focus on lowering the amount of memory needed for storing all activations, which…

Computer Vision and Pattern Recognition · Computer Science 2020-09-22 Robby Neven , Marian Verhelst , Tinne Tuytelaars , Toon Goedemé

Fine-tuning large foundation models presents significant memory challenges due to stateful optimizers like AdamW, often requiring several times more GPU memory than inference. While memory-efficient methods like parameter-efficient…

Machine Learning · Computer Science 2025-07-14 Pouria Mahdavinia , Mehrdad Mahdavi

Retrieval-Augmented Generation (RAG) has established itself as the standard paradigm for grounding Large Language Models (LLMs) in domain-specific, up-to-date data. However, the prevailing architecture for RAG has evolved into a complex,…

Information Retrieval · Computer Science 2026-02-27 Ahmed Bin Khalid

The recent progress in neural architecture search (NAS) has allowed scaling the automated design of neural architectures to real-world domains, such as object detection and semantic segmentation. However, one prerequisite for the…

Machine Learning · Computer Science 2021-06-15 Thomas Elsken , Benedikt Staffler , Jan Hendrik Metzen , Frank Hutter

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

Recurrent neural networks can be difficult to train on long sequence data due to the well-known vanishing gradient problem. Some architectures incorporate methods to reduce RNN state updates, therefore allowing the network to preserve…

Machine Learning · Computer Science 2019-01-23 Matthew Thornton , Jithendar Anumula , Shih-Chii Liu

Linear recurrent neural networks have emerged as efficient alternatives to the original Transformer's softmax attention mechanism, thanks to their highly parallelizable training and constant memory and computation requirements at inference.…

Machine Learning · Computer Science 2026-01-21 Younes Bouhadjar , Maxime Fabre , Felix Schmidt , Emre Neftci

Large Language Models (LLMs) achieve strong performance across diverse tasks, but their effectiveness often depends on the quality of the provided context. Retrieval-Augmented Generation (RAG) enriches prompts with external information, but…

Computation and Language · Computer Science 2025-10-02 Oussama Gabouj , Kamel Charaf , Ivan Zakazov , Nicolas Baldwin , Robert West

In this paper, we have used Recurrent Neural Networks to capture and model human motion data and generate motions by prediction of the next immediate data point at each time-step. Our RNN is armed with recently proposed Gated Recurrent…

Neural and Evolutionary Computing · Computer Science 2015-01-05 Mohammad Pezeshki

Balancing temporal resolution and spatial detail under limited compute budget remains a key challenge for video-based multi-modal large language models (MLLMs). Existing methods typically compress video representations using predefined…

Computer Vision and Pattern Recognition · Computer Science 2025-04-03 Min Shi , Shihao Wang , Chieh-Yun Chen , Jitesh Jain , Kai Wang , Junjun Xiong , Guilin Liu , Zhiding Yu , Humphrey Shi

Transformers have been established as the de-facto backbones for most recent advances in sequence modeling, mainly due to their growing memory capacity that scales with the context length. While plausible for retrieval tasks, it causes…

Machine Learning · Computer Science 2026-03-02 Ali Behrouz , Zeman Li , Yuan Deng , Peilin Zhong , Meisam Razaviyayn , Vahab Mirrokni

This paper addresses the challenges of fault prediction and delayed response in distributed systems by proposing an intelligent prediction method based on temporal feature learning. The method takes multi-dimensional performance metric…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-05-28 Yang Wang , Wenxuan Zhu , Xuehui Quan , Heyi Wang , Chang Liu , Qiyuan Wu

Many multi-source localization and tracking models based on neural networks use one or several recurrent layers at their final stages to track the movement of the sources. Conventional recurrent neural networks (RNNs), such as the long…

Audio and Speech Processing · Electrical Eng. & Systems 2024-02-29 David Diaz-Guerra , Archontis Politis , Antonio Miguel , Jose R. Beltran , Tuomas Virtanen

Machine learning architectures, including transformers and recurrent neural networks (RNNs) have revolutionized forecasting in applications ranging from text processing to extreme weather. Notably, advanced network architectures, tuned for…

Machine Learning · Computer Science 2024-10-04 Hunter S. Heidenreich , Pantelis R. Vlachas , Petros Koumoutsakos

Large Language Models (LLMs) currently struggle to sequentially add new memories and integrate new knowledge. These limitations contrast with the human ability to continuously learn from new experiences and acquire knowledge throughout…

Computation and Language · Computer Science 2025-05-01 Xu Pan , Ely Hahami , Zechen Zhang , Haim Sompolinsky

Token prediction stability remains a challenge in autoregressive generative models, where minor variations in early inference steps often lead to significant semantic drift over extended sequences. A structured modulation mechanism was…

Real-time multimodal inference on resource-constrained edge devices is essential for applications such as autonomous driving, human-computer interaction, and mobile health. However, prior work often overlooks the tight coupling between…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Runxi Huang , Mingxuan Yu , Mingyu Tsoi , Xiaomin Ouyang

Learning an efficient update rule from data that promotes rapid learning of new tasks from the same distribution remains an open problem in meta-learning. Typically, previous works have approached this issue either by attempting to train a…

Machine Learning · Computer Science 2020-02-19 Sebastian Flennerhag , Andrei A. Rusu , Razvan Pascanu , Francesco Visin , Hujun Yin , Raia Hadsell

Progress in deep learning has spawned great successes in many engineering applications. As a prime example, convolutional neural networks, a type of feedforward neural networks, are now approaching -- and sometimes even surpassing -- human…

Computer Vision and Pattern Recognition · Computer Science 2019-06-12 Drew Linsley , Junkyung Kim , Vijay Veerabadran , Thomas Serre

Memory mechanism is a core component of LLM-based agents, enabling reasoning and knowledge discovery over long-horizon contexts. Existing agent memory systems are typically designed within isolated paradigms (e.g., explicit, parametric, or…

Artificial Intelligence · Computer Science 2026-02-10 Xin Zhang , Kailai Yang , Chenyue Li , Hao Li , Qiyu Wei , Jun'ichi Tsujii , Sophia Ananiadou
‹ Prev 1 8 9 10 Next ›