English
Related papers

Related papers: BEEM: Boosting Performance of Early Exit DNNs usin…

200 papers

Ensembling multiple predictions is a widely used technique for improving the accuracy of various machine learning tasks. One obvious drawback of ensembling is its higher execution cost during inference. In this paper, we first describe our…

Machine Learning · Computer Science 2019-03-11 Hiroshi Inoue

Distributed inference techniques can be broadly classified into data-distributed and model-distributed schemes. In data-distributed inference (DDI), each worker carries the entire deep neural network (DNN) model but processes only a subset…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-08-13 Marco Colocrese , Erdem Koyuncu , Hulya Seferoglu

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

Currently, pre-trained models can be considered the default choice for a wide range of NLP tasks. Despite their SoTA results, there is practical evidence that these models may require a different number of computing layers for different…

Machine Learning · Computer Science 2023-05-19 Nikita Balagansky , Daniil Gavrilov

Benchmarking models is a key factor for the rapid progress in machine learning (ML) research. Thus, further progress depends on improving benchmarking metrics. A standard metric to measure the behavioral alignment between ML models and…

Neurons and Cognition · Quantitative Biology 2025-11-10 Thomas Klein , Sascha Meyen , Wieland Brendel , Felix A. Wichmann , Kristof Meding

Early-Exit Large Language Models (EE-LLMs) enable high throughput inference by allowing tokens to exit early at intermediate layers. However, their throughput is limited by the computational and memory savings. Existing EE-LLM frameworks…

Computation and Language · Computer Science 2025-11-03 Avinash Kumar , Shashank Nag , Jason Clemons , Lizy John , Poulami Das

Computational complexity and overthinking problems have become the bottlenecks for pre-training language models (PLMs) with millions or even trillions of parameters. A Flexible-Patience-Based Early Exiting method (F-PABEE) has been proposed…

Computation and Language · Computer Science 2023-05-23 Xiangxiang Gao , Wei Zhu , Jiasheng Gao , Congrui Yin

This paper proposes a novel knowledge distillation-based learning method to improve the classification performance of convolutional neural networks (CNNs) without a pre-trained teacher network, called exit-ensemble distillation. Our method…

Computer Vision and Pattern Recognition · Computer Science 2021-04-06 Hojung Lee , Jong-Seok Lee

The ensemble of deep neural networks has been shown, both theoretically and empirically, to improve generalization accuracy on the unseen test set. However, the high training cost hinders its efficiency since we need a sufficient number of…

Machine Learning · Computer Science 2021-12-28 Wentao Zhang , Jiawei Jiang , Yingxia Shao , Bin Cui

To tackle the high inference latency exhibited by autoregressive language models, previous studies have proposed an early-exiting framework that allocates adaptive computation paths for each token based on the complexity of generating the…

Computation and Language · Computer Science 2023-10-10 Sangmin Bae , Jongwoo Ko , Hwanjun Song , Se-Young Yun

Deep Ensembles, as a type of Bayesian Neural Networks, can be used to estimate uncertainty on the prediction of multiple neural networks by collecting votes from each network and computing the difference in those predictions. In this paper,…

Machine Learning · Computer Science 2023-07-10 Illia Oleksiienko , Alexandros Iosifidis

The recent advances in Deep Neural Networks (DNNs) stem from their exceptional performance across various domains. However, their inherent large size hinders deploying these networks on resource-constrained devices like edge, mobile, and…

Machine Learning · Computer Science 2024-01-22 Divya Jyoti Bajpai , Aastha Jaiswal , Manjesh Kumar Hanawal

The recent decade has seen an enormous rise in the popularity of deep learning and neural networks. These algorithms have broken many previous records and achieved remarkable results. Their outstanding performance has significantly sped up…

Early-exit deep neural networks enable adaptive inference by terminating computation when sufficient confidence is achieved, reducing cost for edge AI accelerators in resource-constrained settings. Existing methods, however, rely on…

Hardware Architecture · Computer Science 2026-03-16 Parth Patne , Mahdi Taheri , Christian Herglotz , Maksim Jenihhin , Milos Krstic , Michael Hübner

Deploying deep neural networks on edge devices requires balancing accuracy, latency, and resource constraints under realistic execution conditions. To fit models within these constraints, two broad strategies have emerged: static…

Artificial Intelligence · Computer Science 2026-04-17 Nekane Fernandez , Ivan Valdes , Steven Van Vaerenbergh , Idoia de la Iglesia , Julen Arratibel

To accelerate learning process with few samples, meta-learning resorts to prior knowledge from previous tasks. However, the inconsistent task distribution and heterogeneity is hard to be handled through a global sharing model…

Machine Learning · Computer Science 2022-06-22 Geng Li , Boyuan Ren , Hongzhi Wang

Parameter-efficient transfer learning (PETL) has shown great potential in adapting a vision transformer (ViT) pre-trained on large-scale datasets to various downstream tasks. Existing studies primarily focus on minimizing the number of…

Computer Vision and Pattern Recognition · Computer Science 2024-09-24 Zheng Liu , Jinchao Zhu , Nannan Li , Gao Huang

In recent years, deep learning-based single-channel speech separation has improved considerably, in large part driven by increasingly compute- and parameter-efficient neural network architectures. Most such architectures are, however,…

Early exiting has recently emerged as a promising technique for accelerating large language models (LLMs) by effectively reducing the hardware computation and memory access. In this paper, we present SpecEE, a fast LLM inference engine with…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-04-15 Jiaming Xu , Jiayi Pan , Yongkang Zhou , Siming Chen , Jinhao Li , Yaoxiu Lian , Junyi Wu , Guohao Dai

This work aims to enable persistent, event-driven sensing and decision capabilities for energy-harvesting (EH)-powered devices by deploying lightweight DNNs onto EH-powered devices. However, harvested energy is usually weak and…

Machine Learning · Computer Science 2020-07-24 Yawen Wu , Zhepeng Wang , Zhenge Jia , Yiyu Shi , Jingtong Hu
‹ Prev 1 3 4 5 6 7 10 Next ›