English
Related papers

Related papers: Block-wise Bit-Compression of Transformer-based Mo…

200 papers

Pre-trained BERT models have achieved impressive accuracy on natural language processing (NLP) tasks. However, their excessive amount of parameters hinders them from efficient deployment on edge devices. Binarization of the BERT models can…

Computation and Language · Computer Science 2023-05-10 Jiayi Tian , Chao Fang , Haonan Wang , Zhongfeng Wang

Existing works on Binary Neural Network (BNN) mainly focus on model's weights and activations while discarding considerations on the input raw data. This article introduces Generic Learned Thermometer (GLT), an encoding technique to improve…

Machine Learning · Computer Science 2025-05-21 Thien Nguyen , William Guicquero

Block compression is a widely used technique to compress textures in real-time graphics applications, offering a reduction in storage size. However, their storage efficiency is constrained by the fixed compression ratio, which substantially…

Image and Video Processing · Electrical Eng. & Systems 2024-10-24 Shin Fujieda , Takahiro Harada

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 paper proposes a highly compact, lightweight text-to-speech (TTS) model for on-device applications. To reduce the model size, the proposed model introduces two techniques. First, we introduce quantization-aware training (QAT), which…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-05 Masaya Kawamura , Takuya Hasumi , Yuma Shirahata , Ryuichi Yamamoto

Recently, leveraging pre-trained Transformer based language models in down stream, task specific models has advanced state of the art results in natural language understanding tasks. However, only a little research has explored the…

Computation and Language · Computer Science 2020-12-07 Daniel Grießhaber , Johannes Maucher , Ngoc Thang Vu

The bits-back argument suggests that latent variable models can be turned into lossless compression schemes. Translating the bits-back argument into efficient and practical lossless compression schemes for general latent variable models,…

Machine Learning · Computer Science 2019-10-03 Friso H. Kingma , Pieter Abbeel , Jonathan Ho

Recent works have indicated redundancy across transformer blocks, prompting the research of depth compression to prune less crucial blocks. However, current ways of entire-block pruning suffer from risks of discarding meaningful cues…

Computer Vision and Pattern Recognition · Computer Science 2026-02-10 Ruihan Xu , Qingpei Guo , Yao Zhu , Xiangyang Ji , Ming Yang , Shiliang Zhang

BERT (Bidirectional Encoder Representations from Transformers) has revolutionized the field of natural language processing through its exceptional performance on numerous tasks. Yet, the majority of researchers have mainly concentrated on…

Computation and Language · Computer Science 2024-12-11 Wen Liang , Youzhi Liang

Increasing model size when pretraining natural language representations often results in improved performance on downstream tasks. However, at some point further model increases become harder due to GPU/TPU memory limitations and longer…

Computation and Language · Computer Science 2020-02-11 Zhenzhong Lan , Mingda Chen , Sebastian Goodman , Kevin Gimpel , Piyush Sharma , Radu Soricut

Recently, deep neural networks (DNNs) have been regarded as the state-of-the-art classification methods in a wide range of applications, especially in image classification. Despite the success, the huge number of parameters blocks its…

Machine Learning · Statistics 2017-12-18 Guangxi Li , Jinmian Ye , Haiqin Yang , Di Chen , Shuicheng Yan , Zenglin Xu

Bidirectional Encoder Representations from Transformers (BERT) reach state-of-the-art results in a variety of Natural Language Processing tasks. However, understanding of their internal functioning is still insufficient and unsatisfactory.…

Computation and Language · Computer Science 2019-09-12 Betty van Aken , Benjamin Winter , Alexander Löser , Felix A. Gers

The current state-of-the-art task-oriented semantic parsing models use BERT or RoBERTa as pretrained encoders; these models have huge memory footprints. This poses a challenge to their deployment for voice assistants such as Amazon Alexa…

Computation and Language · Computer Science 2020-10-13 Prafull Prakash , Saurabh Kumar Shashidhar , Wenlong Zhao , Subendhu Rongali , Haidar Khan , Michael Kayser

Generative Pre-trained Transformer models, known as GPT or OPT, set themselves apart through breakthrough performance across complex language modelling tasks, but also by their extremely high computational and storage costs. Specifically,…

Machine Learning · Computer Science 2023-03-23 Elias Frantar , Saleh Ashkboos , Torsten Hoefler , Dan Alistarh

The Gradient Boosted Tree (GBT) algorithm is one of the most popular machine learning algorithms used in production, for tasks that include Click-Through Rate (CTR) prediction and learning-to-rank. To deal with the massive datasets…

Machine Learning · Computer Science 2019-05-30 Theodore Vasiloudis , Hyunsu Cho , Henrik Boström

Transformer-based neural models are used in many AI applications. Training these models is expensive, as it takes huge GPU resources and long duration. It is challenging because typical data like sentences have variable lengths, and…

Computation and Language · Computer Science 2022-06-17 Xiaohui Wang , Yang Wei , Ying Xiong , Guyue Huang , Xian Qian , Yufei Ding , Mingxuan Wang , Lei Li

The rapid scaling of language models is motivating research using low-bitwidth quantization. In this work, we propose a novel binarization technique for Transformers applied to machine translation (BMT), the first of its kind. We identify…

Computation and Language · Computer Science 2023-12-12 Yichi Zhang , Ankush Garg , Yuan Cao , Łukasz Lew , Behrooz Ghorbani , Zhiru Zhang , Orhan Firat

In recent years, large pre-trained Transformer networks have demonstrated dramatic improvements in many natural language understanding tasks. However, the huge size of these models brings significant challenges to their fine-tuning and…

Computation and Language · Computer Science 2022-07-01 Connor Holmes , Minjia Zhang , Yuxiong He , Bo Wu

Transformer-based models have delivered impressive results on many tasks, particularly vision and language tasks. In many model training situations, conventional configurations are typically adopted. For example, we often set the base model…

Machine Learning · Computer Science 2023-05-19 Fuzhao Xue , Jianghai Chen , Aixin Sun , Xiaozhe Ren , Zangwei Zheng , Xiaoxin He , Yongming Chen , Xin Jiang , Yang You