English
Related papers

Related papers: Enabling Long FFT Convolutions on Memory-Constrain…

200 papers

Recent neural-network-based architectures for image segmentation make extensive usage of feature forwarding mechanisms to integrate information from multiple scales. Although yielding good results, even deeper architectures and alternative…

Computer Vision and Pattern Recognition · Computer Science 2018-06-06 Fausto Milletari , Nicola Rieke , Maximilian Baust , Marco Esposito , Nassir Navab

Language models struggle to generalize beyond pretraining context lengths, limiting long-horizon reasoning and retrieval. Continued pretraining on long-context data can help but is expensive due to the quadratic scaling of Attention. We…

Computation and Language · Computer Science 2026-03-19 Sakshi Choudhary , Aditya Chattopadhyay , Luca Zancato , Elvis Nunez , Matthew Trager , Wei Xia , Stefano Soatto

Federated learning (FL) scenarios inherently generate a large communication overhead by frequently transmitting neural network updates between clients and server. To minimize the communication cost, introducing sparsity in conjunction with…

Machine Learning · Computer Science 2022-04-12 Daniel Becking , Heiner Kirchhoffer , Gerhard Tech , Paul Haase , Karsten Müller , Heiko Schwarz , Wojciech Samek

Large Language Models (LLMs) face significant computational challenges when processing long contexts due to the quadratic complexity of self-attention. While soft context compression methods, which map input text to smaller latent…

Computation and Language · Computer Science 2025-09-24 Gabriele Berton , Jayakrishnan Unnikrishnan , Son Tran , Mubarak Shah

Recently, there is growing attention on one-stage panoptic segmentation methods which aim to segment instances and stuff jointly within a fully convolutional pipeline efficiently. However, most of the existing works directly feed the…

Computer Vision and Pattern Recognition · Computer Science 2022-01-14 Yifeng Chen , Wenqing Chu , Fangfang Wang , Ying Tai , Ran Yi , Zhenye Gan , Liang Yao , Chengjie Wang , Xi Li

Large Language Models (LLMs) require significant GPU memory when processing long texts, with the key value (KV) cache consuming up to 70\% of total memory during inference. Although existing compression methods reduce memory by evaluating…

Computation and Language · Computer Science 2025-10-15 Xiang Liu , Zhenheng Tang , Peijie Dong , Zeyu Li , Yue Liu , Bo Li , Xuming Hu , Xiaowen Chu

Convolution is a fundamental operation in many applications, such as computer vision, natural language processing, image processing, etc. Recent successes of convolutional neural networks in various deep learning applications put even…

Distributed, Parallel, and Cluster Computing · Computer Science 2017-05-31 Xiaoming Chen , Jianxu Chen , Danny Z. Chen , Xiaobo Sharon Hu

We introduce convolutional multi-hybrid architectures, with a design grounded on two simple observations. First, operators in hybrid models can be tailored to token manipulation tasks such as in-context recall, multi-token recall, and…

Long-sequence modeling faces a fundamental trade-off between the efficiency of compressive fixed-size memory in RNN-like models and the fidelity of lossless growing memory in attention-based Transformers. Inspired by the Multi-Store Model…

Computation and Language · Computer Science 2025-12-18 Yunhao Fang , Weihao Yu , Shu Zhong , Qinghao Ye , Xuehan Xiong , Lai Wei

Recent work in neural networks for image classification has seen a strong tendency towards increasing the spatial context. Whether achieved through large convolution kernels or self-attention, models scale poorly with the increased spatial…

Computer Vision and Pattern Recognition · Computer Science 2024-05-16 Julia Grabinski , Janis Keuper , Margret Keuper

Recurrent neural networks (RNNs) with deep test-time memorization modules, such as Titans and TTT, represent a promising, linearly-scaling paradigm distinct from Transformers. While these expressive models do not yet match the peak…

Machine Learning · Computer Science 2025-11-11 Zeman Li , Ali Behrouz , Yuan Deng , Peilin Zhong , Praneeth Kacham , Mahdi Karami , Meisam Razaviyayn , Vahab Mirrokni

Research has shown that convolutional neural networks contain significant redundancy, and high classification accuracy can be obtained even when weights and activations are reduced from floating point to binary values. In this paper, we…

Computer Vision and Pattern Recognition · Computer Science 2016-12-22 Yaman Umuroglu , Nicholas J. Fraser , Giulio Gambardella , Michaela Blott , Philip Leong , Magnus Jahre , Kees Vissers

As Convolutional Neural Networks (CNNs) gain prominence in deep learning, algorithms like Winograd Convolution have been introduced to enhance computational efficiency. However, existing implementations often face challenges such as high…

Performance · Computer Science 2024-12-30 Haoyuan Gui , Xiaoyu Zhang , Chong Zhang , Zitong Su , Huiyuan Li

FPGA accelerators for lightweight neural convolutional networks (LWCNNs) have recently attracted significant attention. Most existing LWCNN accelerators focus on single-Computing-Engine (CE) architecture with local optimization. However,…

Hardware Architecture · Computer Science 2024-12-17 Zhiyuan Zhao , Yihao Chen , Pengcheng Feng , Jixing Li , Gang Chen , Rongxuan Shen , Huaxiang Lu

The self-attention mechanism is the key to the success of transformers in recent Large Language Models (LLMs). However, the quadratic computational cost $O(n^2)$ in the input sequence length $n$ is a notorious obstacle for further…

Machine Learning · Computer Science 2024-10-17 Yingyu Liang , Heshan Liu , Zhenmei Shi , Zhao Song , Zhuoyan Xu , Junze Yin

We present a series of long-context LLMs that support effective context windows of up to 32,768 tokens. Our model series are built through continual pretraining from Llama 2 with longer training sequences and on a dataset where long texts…

The increasing demand for real-time, low-latency artificial intelligence applications has propelled the use of Field-Programmable Gate Arrays (FPGAs) for Convolutional Neural Network (CNN) implementations. FPGAs offer reconfigurability,…

Hardware Architecture · Computer Science 2025-10-06 Philippe Magalhães , Virginie Fresse , Benoît Suffran , Olivier Alata

Recent language models exhibit strong reasoning capabilities, yet the influence of long-context capacity on reasoning remains underexplored. In this work, we hypothesize that current limitations in reasoning stem, in part, from insufficient…

Artificial Intelligence · Computer Science 2025-05-26 Wang Yang , Zirui Liu , Hongye Jin , Qingyu Yin , Vipin Chaudhary , Xiaotian Han

Although transformer architectures have achieved state-of-the-art performance across diverse domains, their quadratic computational complexity with respect to sequence length remains a significant bottleneck, particularly for…

Computation and Language · Computer Science 2025-11-05 Zeyu Liu , Souvik Kundu , Lianghao Jiang , Anni Li , Srikanth Ronanki , Sravan Bodapati , Gourav Datta , Peter A. Beerel

Extending the functionality of the Transformer model to accommodate longer sequence lengths has become a critical challenge. This extension is crucial not only for improving tasks such as language translation and long-context processing but…

Computation and Language · Computer Science 2024-06-11 Hengyu Zhang