English
Related papers

Related papers: RAM-Net: Expressive Linear Attention with Selectiv…

200 papers

More and more empirical and theoretical evidence shows that deepening neural networks can effectively improve their performance under suitable training settings. However, deepening the backbone of neural networks will inevitably and…

Machine Learning · Computer Science 2022-10-31 Shanshan Zhong , Wushao Wen , Jinghui Qin , Zhongzhan Huang

Deep convolutional neural networks, assisted by architectural design strategies, make extensive use of data augmentation techniques and layers with a high number of feature maps to embed object transformations. That is highly inefficient…

Computer Vision and Pattern Recognition · Computer Science 2021-12-21 Vittorio Mazzia , Francesco Salvetti , Marcello Chiaberge

The Segment Anything Model (SAM) achieves strong open-vocabulary segmentation, but its ViT-based image encoders dominate inference latency and memory. Existing activation compression methods, such as token merging, reduce the token length…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Hoai-Chau Tran , Chi H. Nguyen , Duy M. H. Nguyen , Mathias Niepert , Fan Lai , Khoa D. Doan

Designing lightweight convolutional neural network (CNN) models is an active research area in edge AI. Compute-in-memory (CIM) provides a new computing paradigm to alleviate time and energy consumption caused by data transfer in von Neumann…

Hardware Architecture · Computer Science 2025-08-19 Wenyong Zhou , Yuan Ren , Jiajun Zhou , Tianshu Hou , Ngai Wong

Long-context understanding is crucial for many NLP applications, yet transformers struggle with efficiency due to the quadratic complexity of self-attention. Sparse attention methods alleviate this cost but often impose static, predefined…

Computation and Language · Computer Science 2025-06-16 Hanzhi Zhang , Heng Fan , Kewei Sha , Yan Huang , Yunhe Feng

Recurrent neural networks (RNNs) provide state-of-the-art performance in processing sequential data but are memory intensive to train, limiting the flexibility of RNN models which can be trained. Reversible RNNs---RNNs for which the…

Machine Learning · Computer Science 2018-10-26 Matthew MacKay , Paul Vicol , Jimmy Ba , Roger Grosse

Despite the impressive search rate of one key per clock cycle, the update stage of a random-access-memory-based content-addressable-memory (RAM-based CAM) always suffers high latency. Two primary causes of such latency include: (1) the…

Hardware Architecture · Computer Science 2018-06-28 Xuan-Thuan Nguyen , Trong-Thuc Hoang , Hong-Thu Nguyen , Katsumi Inoue , Cong-Kha Pham

When answering a question, people often draw upon their rich world knowledge in addition to the particular context. While recent works retrieve supporting facts/evidence from commonsense knowledge bases to supply additional information to…

Computation and Language · Computer Science 2021-03-26 Yinya Huang , Meng Fang , Xunlin Zhan , Qingxing Cao , Xiaodan Liang , Liang Lin

Structured dilated attention has an appealing inference-time efficiency knob: it reduces the FLOPs of attention and the KV cache size by a factor of the dilation size D, while preserving long-range connectivity. While prior work studies it…

Machine Learning · Computer Science 2026-05-29 Xiuying Wei , Caglar Gulcehre

The brain, as the source of inspiration for Artificial Neural Networks (ANN), is based on a sparse structure. This sparse structure helps the brain to consume less energy, learn easier and generalize patterns better than any other ANN. In…

Machine Learning · Computer Science 2021-03-16 Seyed Majid Naji , Azra Abtahi , Farokh Marvasti

ATM-Net is a novel neural network architecture tailored for energy-harvested IoT devices, integrating adaptive termination points with multi-precision computing. It dynamically adjusts computational precision (32/8/4-bit) and network depth…

Machine Learning · Computer Science 2025-02-17 Neeraj Solanki , Sepehr Tabrizchi , Samin Sohrabi , Jason Schmidt , Arman Roohi

Network pruning is aimed at imposing sparsity in a neural network architecture by increasing the portion of zero-valued weights for reducing its size regarding energy-efficiency consideration and increasing evaluation speed. In most of the…

Machine Learning · Computer Science 2018-07-17 Amirsina Torfi , Rouzbeh A. Shirvani , Sobhan Soleymani , Nasser M. Nasrabadi

Recurrent neural networks (RNNs) and self-attention are both widely used sequence-mixing layers that maintain an internal memory. However, this memory is constructed using two orthogonal mechanisms: RNNs compress the entire past into a…

Machine Learning · Computer Science 2026-03-30 Leon Lufkin , Tomás Figliolia , Beren Millidge , Kamesh Krishnamurthy

We show that a coherent network of lasers exhibits emergent neural computing capabilities. The proposed scheme is built on harnessing the collective behavior of laser networks for storing a number of phase patterns as stable fixed points of…

Optics · Physics 2022-04-06 Mohammad-Ali Miri , Vinod Menon

Stack-augmented recurrent neural networks (RNNs) have been of interest to the deep learning community for some time. However, the difficulty of training memory models remains a problem obstructing the widespread use of such models. In this…

Machine Learning · Computer Science 2019-11-05 Yikang Shen , Shawn Tan , Arian Hosseini , Zhouhan Lin , Alessandro Sordoni , Aaron Courville

Sequence labeling architectures use word embeddings for capturing similarity, but suffer when handling previously unseen or rare words. We investigate character-level extensions to such models and propose a novel architecture for combining…

Computation and Language · Computer Science 2016-11-15 Marek Rei , Gamal K. O. Crichton , Sampo Pyysalo

Compressed sensing (CS) is a challenging problem in image processing due to reconstructing an almost complete image from a limited measurement. To achieve fast and accurate CS reconstruction, we synthesize the advantages of two well-known…

Computer Vision and Pattern Recognition · Computer Science 2020-11-17 Nanyu Li , Charles C. Zhou

Linear attention offers a computationally efficient yet expressive alternative to softmax attention. However, recent empirical results indicate that the hidden state of trained linear attention models often exhibits a low-rank structure,…

Machine Learning · Computer Science 2026-02-13 Philipp Nazari , T. Konstantin Rusch

Self-attention-based models have achieved remarkable progress in short-text mining. However, the quadratic computational complexities restrict their application in long text processing. Prior works have adopted the chunking strategy to…

Computation and Language · Computer Science 2023-06-13 Xianming Li , Zongxi Li , Xiaotian Luo , Haoran Xie , Xing Lee , Yingbin Zhao , Fu Lee Wang , Qing Li

We explore the ways that a reference point may direct attention. Utilizing a stochastic choice framework, we provide behavioral foundations for the Reference-Dependent Random Attention Model (RD-RAM). Our characterization result shows that…

Theoretical Economics · Economics 2023-03-21 Matthew Kovach , Elchin Suleymanov