English
Related papers

Related papers: DE$^3$-BERT: Distance-Enhanced Early Exiting for B…

200 papers

The ability to dynamically adjust the computational load of neural models during inference is crucial for on-device processing scenarios characterised by limited and time-varying computational resources. A promising solution is presented by…

Audio and Speech Processing · Electrical Eng. & Systems 2024-02-23 George August Wright , Umberto Cappellazzo , Salah Zaiem , Desh Raj , Lucas Ondel Yang , Daniele Falavigna , Mohamed Nabih Ali , Alessio Brutti

This paper presents a modular approach to accelerate inference in large language models (LLMs) by adding early exit heads at intermediate transformer layers. Each head is trained in a self-supervised manner to mimic the main model's…

Computation and Language · Computer Science 2026-02-13 Florian Valade

Deep neural networks have significantly improved performance on a range of tasks with the increasing demand for computational resources, leaving deployment on low-resource devices (with limited memory and battery power) infeasible. Binary…

Machine Learning · Computer Science 2022-06-22 Aaqib Saeed

Recently, pre-trained models have been the dominant paradigm in natural language processing. They achieved remarkable state-of-the-art performance across a wide range of related tasks, such as textual entailment, natural language inference,…

Computation and Language · Computer Science 2019-05-21 Dongfang Li , Yifei Yu , Qingcai Chen , Xinyu Li

Deep neural networks (DNNs) have been successfully applied in various fields. In DNNs, a large number of multiply-accumulate (MAC) operations are required to be performed, posing critical challenges in applying them in resource-constrained…

Machine Learning · Computer Science 2024-02-20 Jingcun Wang , Bing Li , Grace Li Zhang

Language Model pre-training uses broad data mixtures to enhance performance across domains and languages. However, training on such heterogeneous text corpora requires extensive and expensive efforts. Since these data sources vary…

Machine Learning · Computer Science 2025-04-08 Alex Iacob , Lorenzo Sani , Meghdad Kurmanji , William F. Shen , Xinchi Qiu , Dongqi Cai , Yan Gao , Nicholas D. Lane

Early Time Series Classification (ETSC) is critical in time-sensitive medical applications such as sepsis, yet it presents an inherent trade-off between accuracy and earliness. This trade-off arises from two core challenges: 1) models…

Machine Learning · Computer Science 2025-11-06 Tao Xie , Zexi Tan , Haoyi Xiao , Binbin Sun , Yiqun Zhang

Transformer-based language models such as BERT provide significant accuracy improvement for a multitude of natural language processing (NLP) tasks. However, their hefty computational and memory demands make them challenging to deploy to…

Early-exit neural networks reduce inference cost by enabling confident predictions at intermediate layers. However, joint training often leads to gradient interference, with deeper classifiers dominating optimization. We propose…

Machine Learning · Computer Science 2026-01-12 Saad Mokssit , Ouassim Karrakchou , Alejandro Mousist , Mounir Ghogho

Heavily overparameterized language models such as BERT, XLNet and T5 have achieved impressive success in many NLP tasks. However, their high model complexity requires enormous computation resources and extremely long training time for both…

Computation and Language · Computer Science 2021-06-09 Xiaohan Chen , Yu Cheng , Shuohang Wang , Zhe Gan , Zhangyang Wang , Jingjing Liu

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

We present EE-LLM, a framework for large-scale training and inference of early-exit large language models (LLMs). While recent works have shown preliminary evidence for the efficacy of early exiting in accelerating LLM inference, EE-LLM…

Machine Learning · Computer Science 2024-06-18 Yanxi Chen , Xuchen Pan , Yaliang Li , Bolin Ding , Jingren Zhou

Backpropagation has long been criticized for being biologically implausible due to its reliance on concepts that are not viable in natural learning processes. Two core issues are the weight transport and update locking problems caused by…

Machine Learning · Computer Science 2026-01-14 Katharina Flügel , Daniel Coquelin , Marie Weiel , Charlotte Debus , Achim Streit , Markus Götz

A typical architecture for end-to-end entity linking systems consists of three steps: mention detection, candidate generation and entity disambiguation. In this study we investigate the following questions: (a) Can all those steps be…

Computation and Language · Computer Science 2021-01-14 Samuel Broscheit

State-of-the-art neural networks with early exit mechanisms often need considerable amount of training and fine tuning to achieve good performance with low computational cost. We propose a novel early exit technique, Early Exit Class Means…

Machine Learning · Computer Science 2022-10-28 Alperen Görmez , Venkat R. Dasari , Erdem Koyuncu

Neural language representation models such as BERT, pre-trained on large-scale unstructured corpora lack explicit grounding to real-world commonsense knowledge and are often unable to remember facts required for reasoning and inference.…

Computation and Language · Computer Science 2021-08-04 Amit Gajbhiye , Noura Al Moubayed , Steven Bradley

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…

Current language models are usually trained using a self-supervised scheme, where the main focus is learning representations at the word or sentence level. However, there has been limited progress in generating useful discourse-level…

Computation and Language · Computer Science 2021-09-13 Vladimir Araujo , Andrés Villa , Marcelo Mendoza , Marie-Francine Moens , Alvaro Soto

This work addresses the need for a balanced approach between performance and efficiency in scalable production environments for visually-rich document understanding (VDU) tasks. Currently, there is a reliance on large document foundation…

Computer Vision and Pattern Recognition · Computer Science 2024-05-22 Omar Hamed , Souhail Bakkali , Marie-Francine Moens , Matthew Blaschko , Jordy Van Landeghem

Language identification is the task of automatically determining the identity of a language conveyed by a spoken segment. It has a profound impact on the multilingual interoperability of an intelligent speech system. Despite language…

Computation and Language · Computer Science 2025-01-14 Yuting Nie , Junhong Zhao , Wei-Qiang Zhang , Jinfeng Bai