English
Related papers

Related papers: Hardware Acceleration of Fully Quantized BERT for …

200 papers

Large language models (LLMs) require substantial compute, and thus energy, at inference time. While quantizing weights and activations is effective at improving efficiency, naive quantization of LLMs can significantly degrade performance…

Machine Learning · Computer Science 2025-06-06 Boris van Breugel , Yelysei Bondarenko , Paul Whatmough , Markus Nagel

Point cloud registration serves as a basis for vision and robotic applications including 3D reconstruction and mapping. Despite significant improvements on the quality of results, recent deep learning approaches are computationally…

Robotics · Computer Science 2024-04-02 Keisuke Sugiura , Hiroki Matsutani

With the popularity of the recent Transformer-based models represented by BERT, GPT-3 and ChatGPT, there has been state-of-the-art performance in a range of natural language processing tasks. However, the massive computations, huge memory…

Computation and Language · Computer Science 2023-04-04 Gaochen Dong , Wei Chen

Encoder-only transformer models such as BERT offer a great performance-size tradeoff for retrieval and classification tasks with respect to larger decoder-only models. Despite being the workhorse of numerous production pipelines, there have…

BERT-enhanced neural machine translation (NMT) aims at leveraging BERT-encoded representations for translation tasks. A recently proposed approach uses attention mechanisms to fuse Transformer's encoder and decoder layers with BERT's…

Computation and Language · Computer Science 2020-11-10 Zhebin Zhang , Sai Wu , Dawei Jiang , Gang Chen

Vision Transformers (ViTs) have emerged as a state-of-the-art solution for object classification tasks. However, their computational demands and high parameter count make them unsuitable for real-time inference, prompting the need for…

Image and Video Processing · Electrical Eng. & Systems 2024-02-16 Kyle Marino , Pengmiao Zhang , Viktor Prasanna

Research has shown that deep neural networks contain significant redundancy, and thus that high classification accuracy can be achieved even when weights and activations are quantized down to binary values. Network binarization on FPGAs…

Machine Learning · Computer Science 2020-03-04 Erwei Wang , James J. Davis , Peter Y. K. Cheung , George A. Constantinides

Transformer-based large language models (LLMs) rely heavily on intensive matrix multiplications for attention and feed-forward layers, with the Q, K, and V linear projections in the Multi-Head Self-Attention (MHA) module constituting a…

Hardware Architecture · Computer Science 2025-05-22 Richie Li , Sicheng Chen

How to efficiently serve ever-larger trained natural language models in practice has become exceptionally challenging even for powerful cloud servers due to their prohibitive memory/computation requirements. In this work, we present an…

Computation and Language · Computer Science 2022-06-07 Zhewei Yao , Reza Yazdani Aminabadi , Minjia Zhang , Xiaoxia Wu , Conglong Li , Yuxiong He

In this demonstration, we present an efficient BERT-based multi-task (MT) framework that is particularly suitable for iterative and incremental development of the tasks. The proposed framework is based on the idea of partial fine-tuning,…

Computation and Language · Computer Science 2022-03-10 Tianwen Wei , Jianwei Qi , Shenghuan He

Transformer-based architectures like BERT have achieved great success in a wide range of Natural Language tasks. Despite their decent performance, the models still have numerous parameters and high computational complexity, impeding their…

Computation and Language · Computer Science 2022-11-01 Ting Hu , Christoph Meinel , Haojin Yang

This research introduces an FPGA-based hardware accelerator to optimize the Singular Value Decomposition (SVD) and Fast Fourier transform (FFT) operations in AI models. The proposed design aims to improve processing speed and reduce…

Hardware Architecture · Computer Science 2025-04-15 Hong Ding , Chia Chao Kang , SuYang Xi , Zehang Liu , Xuan Zhang , Yi Ding

Research has shown that deep neural networks contain significant redundancy, and that high classification accuracies can be achieved even when weights and activations are quantised down to binary values. Network binarisation on FPGAs…

Machine Learning · Computer Science 2019-04-02 Erwei Wang , James J. Davis , Peter Y. K. Cheung , George A. Constantinides

A BERT-based Neural Ranking Model (NRM) can be either a crossencoder or a bi-encoder. Between the two, bi-encoder is highly efficient because all the documents can be pre-processed before the actual query time. In this work, we show two…

Computation and Language · Computer Science 2022-03-03 Euna Jung , Jaekeol Choi , Wonjong Rhee

Improving the deployment efficiency of transformer-based language models has been challenging given their high computation and memory cost. While INT8 quantization has recently been shown to be effective in reducing both the memory cost and…

Computation and Language · Computer Science 2023-06-01 Xiaoxia Wu , Cheng Li , Reza Yazdani Aminabadi , Zhewei Yao , Yuxiong He

Limited computational budgets often prevent transformers from being used in production and from having their high accuracy utilized. A knowledge distillation approach addresses the computational efficiency by self-distilling BERT into a…

Computation and Language · Computer Science 2023-05-11 Shira Guskin , Moshe Wasserblat , Chang Wang , Haihao Shen

Parameterized quantum circuits (PQCs) have recently emerged as promising components for enhancing the expressibility of neural architectures. In this work, we introduce QFFN-BERT, a hybrid quantum-classical transformer where the feedforward…

Computation and Language · Computer Science 2025-07-04 Pilsung Kang

We develop a novel method, called PoWER-BERT, for improving the inference time of the popular BERT model, while maintaining the accuracy. It works by: a) exploiting redundancy pertaining to word-vectors (intermediate encoder outputs) and…

Convolutional Neural Networks (CNNs) are fundamental to deep learning, driving applications across various domains. However, their growing complexity has significantly increased computational demands, necessitating efficient hardware…

Machine Learning · Computer Science 2025-05-21 Junye Jiang , Yaan Zhou , Yuanhao Gong , Haoxuan Yuan , Shuanglong Liu

While humans process language incrementally, the best language encoders currently used in NLP do not. Both bidirectional LSTMs and Transformers assume that the sequence that is to be encoded is available in full, to be processed either…

Computation and Language · Computer Science 2024-03-29 Brielen Madureira , David Schlangen
‹ Prev 1 4 5 6 7 8 10 Next ›