English
Related papers

Related papers: DAISY: Data Adaptive Self-Supervised Early Exit fo…

200 papers

Large-scale pre-trained language models such as BERT have brought significant improvements to NLP applications. However, they are also notorious for being slow in inference, which makes them difficult to deploy in real-time applications. We…

Computation and Language · Computer Science 2020-04-28 Ji Xin , Raphael Tang , Jaejun Lee , Yaoliang Yu , Jimmy Lin

Despite much success in natural language processing (NLP), pre-trained language models typically lead to a high computational cost during inference. Multi-exit is a mainstream approach to address this issue by making a trade-off between…

Computation and Language · Computer Science 2023-05-23 Yiming Chen , Simin Chen , Zexin Li , Wei Yang , Cong Liu , Robby T. Tan , Haizhou Li

By leveraging the data sample diversity, the early-exit network recently emerges as a prominent neural network architecture to accelerate the deep learning inference process. However, intermediate classifiers of the early exits introduce…

Machine Learning · Computer Science 2022-06-22 Rongkang Dong , Yuyi Mao , Jun Zhang

This paper introduces TinySaver, an early-exit-like dynamic model compression approach which employs tiny models to substitute large models adaptively. Distinct from traditional compression techniques, dynamic methods like TinySaver can…

Artificial Intelligence · Computer Science 2025-01-14 Qingyuan Wang , Barry Cardiff , Antoine Frappé , Benoit Larras , Deepu John

Adaptive inference is a simple method for reducing inference costs. The method works by maintaining multiple classifiers of different capacities, and allocating resources to each test instance according to its difficulty. In this work, we…

Computation and Language · Computer Science 2023-06-06 Daniel Rotem , Michael Hassid , Jonathan Mamou , Roy Schwartz

Early Exiting (EE) is a promising technique for speeding up inference by adaptively allocating compute resources to data points based on their difficulty. The approach enables predictions to exit at earlier layers for simpler samples while…

Machine Learning · Computer Science 2024-12-30 Mehrnaz Mofakhami , Reza Bayat , Ioannis Mitliagkas , Joao Monteiro , Valentina Zantedeschi

Pre-trained Language Models (PLMs), like BERT, with self-supervision objectives exhibit remarkable performance and generalization across various tasks. However, they suffer in inference latency due to their large size. To address this…

Computation and Language · Computer Science 2024-05-27 Divya Jyoti Bajpai , Manjesh Kumar Hanawal

In Large Language Model (LLM) inference, early-exit refers to stopping computation at an intermediate layer once the prediction is sufficiently confident, thereby reducing latency and cost. However, recent LLMs adopt improved pretraining…

Computation and Language · Computer Science 2026-03-26 Rui Wei , Rui Du , Hanfei Yu , Devesh Tiwari , Jian Li , Zhaozhuo Xu , Hao Wang

The growing demand for intelligent applications beyond the network edge, coupled with the need for sustainable operation, are driving the seamless integration of deep learning (DL) algorithms into energy-limited, and even energy-harvesting…

Machine Learning · Computer Science 2024-11-08 Marcello Bullo , Seifallah Jardak , Pietro Carnelli , Deniz Gündüz

Early-exiting neural networks enable adaptive inference by allowing inputs to exit at intermediate classifiers, reducing computation for easy samples while maintaining high accuracy. In practice, exits can be trained sequentially by…

Machine Learning · Computer Science 2026-05-08 Alaa Zniber , Ouassim Karrakchou , Mounir Ghogho

In this paper, we propose Patience-based Early Exit, a straightforward yet effective inference method that can be used as a plug-and-play technique to simultaneously improve the efficiency and robustness of a pretrained language model…

Computation and Language · Computer Science 2020-10-23 Wangchunshu Zhou , Canwen Xu , Tao Ge , Julian McAuley , Ke Xu , Furu Wei

Large language models have achieved remarkable capabilities, but their practical deployment is hindered by significant computational costs. While adaptive computation methods like early-exiting promise to reduce these costs, they introduce…

Computation and Language · Computer Science 2025-12-16 Sangmin Bae

We present an approach to adaptively utilize deep neural networks in order to reduce the evaluation time on new examples without loss of accuracy. Rather than attempting to redesign or approximate existing networks, we propose two schemes…

Machine Learning · Computer Science 2017-09-20 Tolga Bolukbasi , Joseph Wang , Ofer Dekel , Venkatesh Saligrama

With its strong modeling capacity that comes from a multi-head and multi-layer structure, Transformer is a very powerful model for learning a sequential representation and has been successfully applied to speech separation recently.…

Sound · Computer Science 2020-10-26 Sanyuan Chen , Yu Wu , Zhuo Chen , Takuya Yoshioka , Shujie Liu , Jinyu Li

Large reasoning models achieve strong performance on complex tasks by generating extended chains of thought, but they often "overthink": continuing to reason long after they have enough information to answer correctly. This wastes…

Computation and Language · Computer Science 2025-12-08 Ömer Faruk Akgül , Yusuf Hakan Kalaycı , Rajgopal Kannan , Willie Neiswanger , Viktor Prasanna

In recent years, much speech separation research has focused primarily on improving model performance. However, for low-latency speech processing systems, high efficiency is equally important. Therefore, we propose a speech separation model…

Sound · Computer Science 2026-03-02 Mohan Xu , Kai Li , Guo Chen , Xiaolin Hu

Deep learning (DL) techniques are increasingly pervasive across various domains, including wireless communication, where they extract insights from raw radio signals. However, the computational demands of DL pose significant challenges,…

Signal Processing · Electrical Eng. & Systems 2024-09-05 Dieter Verbruggen , Hazem Sallouha , Sofie Pollin

Deep learning (DL) models have emerged as a promising solution for the Internet of Things (IoT). However, due to their computational complexity, DL models consume significant amounts of energy, which can rapidly drain the battery and…

Systems and Control · Electrical Eng. & Systems 2024-11-05 Marcello Bullo , Seifallah Jardak , Pietro Carnelli , Deniz Gündüz

The inference of large language models imposes significant computational workloads, often requiring the processing of billions of parameters. Although early-exit strategies have proven effective in reducing computational demands by halting…

Computation and Language · Computer Science 2026-01-08 Sangmin Yoo , Srikanth Malla , Chiho Choi , Wei D. Lu , Joon Hee Choi

Deep Neural Networks (DNNs) are generally designed as sequentially cascaded differentiable blocks/layers with a prediction module connected only to its last layer. DNNs can be attached with prediction modules at multiple points along the…

Machine Learning · Computer Science 2022-09-21 Hari Narayan N U , Manjesh K. Hanawal , Avinash Bhardwaj