English
Related papers

Related papers: ADEPT: Adaptive Dynamic Early-Exit Process for Tra…

200 papers

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-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

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

Large language model (LLM) decoding involves generating a sequence of tokens based on a given context, where each token is predicted one at a time using the model's learned probabilities. The typical autoregressive decoding method requires…

Computation and Language · Computer Science 2024-08-20 Xukun Liu , Bowen Lei , Ruqi Zhang , Dongkuan Xu

Deep Neural Networks (DNNs) have grown increasingly large in size to achieve state of the art performance across a wide range of tasks. However, their high computational requirements make them less suitable for resource-constrained…

Machine Learning · Computer Science 2025-01-15 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

Deploying deep learning models in time-critical applications with limited computational resources, for instance in edge computing systems and IoT networks, is a challenging task that often relies on dynamic inference methods such as early…

Machine Learning · Computer Science 2022-06-30 Arian Bakhtiarnia , Qi Zhang , Alexandros Iosifidis

Recently, the efficient deployment and acceleration of powerful vision transformers (ViTs) on resource-limited edge devices for providing multimedia services have become attractive tasks. Although early exiting is a feasible solution for…

Computer Vision and Pattern Recognition · Computer Science 2023-08-02 Guanyu Xu , Jiawei Hao , Li Shen , Han Hu , Yong Luo , Hui Lin , Jialie Shen

Large Language Models (LLMs) have demonstrated exceptional performance across diverse domains but are increasingly constrained by high inference latency. Early Exit has emerged as a promising solution to accelerate inference by dynamically…

Computation and Language · Computer Science 2026-05-26 Yingtao Shen , An Zou

Despite the great success in Natural Language Processing (NLP) area, large pre-trained language models like BERT are not well-suited for resource-constrained or real-time applications owing to the large number of parameters and slow…

Computation and Language · Computer Science 2021-07-02 Keli Xie , Siyuan Lu , Meiqi Wang , Zhongfeng Wang

Inference with transformer-based language models begins with a prompt processing step. In this step, the model generates the first output token and stores the KV cache needed for future generation steps. This prompt processing step can be…

Computation and Language · Computer Science 2024-10-14 Maxwell Horton , Qingqing Cao , Chenfan Sun , Yanzi Jin , Sachin Mehta , Mohammad Rastegari , Moin Nabi

Large-scale Transformer models bring significant improvements for various downstream vision language tasks with a unified architecture. The performance improvements come with increasing model size, resulting in slow inference speed and…

Computer Vision and Pattern Recognition · Computer Science 2023-04-04 Shengkun Tang , Yaqing Wang , Zhenglun Kong , Tianchi Zhang , Yao Li , Caiwen Ding , Yanzhi Wang , Yi Liang , Dongkuan Xu

Transformers have become central to natural language processing and large language models, but their deployment at scale faces three major challenges. First, the attention mechanism requires massive matrix multiplications and frequent…

Hardware Architecture · Computer Science 2026-01-22 Xiaoxuan Yang , Peilin Chen , Tergel Molom-Ochir , Yiran Chen

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

Well-trained deep neural networks (DNNs) treat all test samples equally during prediction. Adaptive DNN inference with early exiting leverages the observation that some test examples can be easier to predict than others. This paper presents…

In real scenarios, it is often necessary and significant to control the inference speed of speech enhancement systems under different conditions. To this end, we propose a stage-wise adaptive inference approach with early exit mechanism for…

Sound · Computer Science 2021-06-23 Andong Li , Chengshi Zheng , Lu Zhang , Xiaodong Li

It is usually infeasible to fit and train an entire large deep neural network (DNN) model using a single edge device due to the limited resources. To facilitate intelligent applications across edge devices, researchers have proposed…

Machine Learning · Computer Science 2023-11-13 Yuhao Chen , Yuxuan Yan , Qianqian Yang , Yuanchao Shu , Shibo He , Zhiguo Shi , Jiming Chen

Huge memory consumption has been a major bottleneck for deploying high-throughput large language models in real-world applications. In addition to the large number of parameters, the key-value (KV) cache for the attention mechanism in the…

Computation and Language · Computer Science 2024-06-05 Haoyi Wu , Kewei Tu

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