English
Related papers

Related papers: Once-for-All Sequence Compression for Self-Supervi…

200 papers

Compressing self-supervised models has become increasingly necessary, as self-supervised models become larger. While previous approaches have primarily focused on compressing the model size, shortening sequences is also effective in…

Computation and Language · Computer Science 2022-10-26 Yen Meng , Hsuan-Jui Chen , Jiatong Shi , Shinji Watanabe , Paola Garcia , Hung-yi Lee , Hao Tang

We address the challenging problem of efficient inference across many devices and resource constraints, especially on edge devices. Conventional approaches either manually design or use neural architecture search (NAS) to find a specialized…

Machine Learning · Computer Science 2020-05-01 Han Cai , Chuang Gan , Tianzhe Wang , Zhekai Zhang , Song Han

The Diffusion Probabilistic Model (DPM) achieves remarkable performance in image generation, while its increasing parameter size and computational overhead hinder its deployment in practical applications. To improve this, the existing…

Computer Vision and Pattern Recognition · Computer Science 2026-04-15 Haoyang Jiang , Zekun Wang , Mingyang Yi , Xiuyu Li , Lanqing Hu , Junxian Cai , Qingbin Liu , Xi Chen , Ju Fan

This thesis concerns sequential-access data compression, i.e., by algorithms that read the input one or more times from beginning to end. In one chapter we consider adaptive prefix coding, for which we must read the input character by…

Information Theory · Computer Science 2009-02-03 Travis Gagie

Large Language Models (LLMs) have advanced rapidly but face significant memory demands. While quantization has shown promise for LLMs, current methods typically require lengthy training to alleviate the performance degradation from…

Artificial Intelligence · Computer Science 2024-05-31 Ke Yi , Yuhui Xu , Heng Chang , Chen Tang , Yuan Meng , Tong Zhang , Jia Li

In this work, we pursue a unified paradigm for multimodal pretraining to break the scaffolds of complex task/modality-specific customization. We propose OFA, a Task-Agnostic and Modality-Agnostic framework that supports Task…

Computer Vision and Pattern Recognition · Computer Science 2022-06-02 Peng Wang , An Yang , Rui Men , Junyang Lin , Shuai Bai , Zhikang Li , Jianxin Ma , Chang Zhou , Jingren Zhou , Hongxia Yang

Scaling language models to longer contexts is essential for capturing rich dependencies across extended discourse. However, na\"ive context extension imposes significant computational and memory burdens, often resulting in inefficiencies…

Computation and Language · Computer Science 2026-02-03 Wenhao Li , Bangcheng Sun , Weihao Ye , Tianyi Zhang , Daohai Yu , Fei Chao , Rongrong Ji

This paper presents a context key/value compression method for Transformer language models in online scenarios, where the context continually expands. As the context lengthens, the attention process demands increasing memory and…

Machine Learning · Computer Science 2024-02-07 Jang-Hyun Kim , Junyoung Yeom , Sangdoo Yun , Hyun Oh Song

Self-supervised learning (SSL) has proven vital in speech and audio-related applications. The paradigm trains a general model on unlabeled data that can later be used to solve specific downstream tasks. This type of model is costly to train…

Sequence data is challenging for machine learning approaches, because the lengths of the sequences may vary between samples. In this paper, we present an unsupervised learning model for sequence data, called the Integrated Sequence…

Computer Vision and Pattern Recognition · Computer Science 2018-04-30 Wenjie Pei , David M. J. Tax

Sentence compression reduces the length of text by removing non-essential content while preserving important facts and grammaticality. Unsupervised objective driven methods for sentence compression can be used to create customized models…

Computation and Language · Computer Science 2022-05-18 Demian Gholipour Ghalandari , Chris Hokamp , Georgiana Ifrim

The Once-For-All (OFA) method offers an excellent pathway to deploy a trained neural network model into multiple target platforms by utilising the supernet-subnet architecture. Once trained, a subnet can be derived from the supernet (both…

Machine Learning · Computer Science 2022-04-21 Jordan Shipard , Arnold Wiliem , Clinton Fookes

Modern end-to-end speech recognition models show astonishing results in transcribing audio signals into written text. However, conventional data feeding pipelines may be sub-optimal for low-resource speech recognition, which still remains a…

Audio and Speech Processing · Electrical Eng. & Systems 2022-02-21 Anastasia Kuznetsova , Anurag Kumar , Jennifer Drexler Fox , Francis Tyers

Instead of pretraining multilingual language models from scratch, a more efficient method is to adapt existing pretrained language models (PLMs) to new languages via vocabulary extension and continued pretraining. However, this method…

Computation and Language · Computer Science 2024-03-26 Yihong Liu , Peiqin Lin , Mingyang Wang , Hinrich Schütze

Audio-visual speech separation methods aim to integrate different modalities to generate high-quality separated speech, thereby enhancing the performance of downstream tasks such as speech recognition. Most existing state-of-the-art (SOTA)…

Sound · Computer Science 2024-03-22 Samuel Pegg , Kai Li , Xiaolin Hu

Modern language models are trained almost exclusively on token sequences produced by a fixed tokenizer, an external lossless compressor often over UTF-8 byte sequences, thereby coupling the model to that compressor. This work introduces…

Computation and Language · Computer Science 2026-05-15 Lin Zheng , Xinyu Li , Qian Liu , Xiachong Feng , Lingpeng Kong

Neural audio codecs, used as speech tokenizers, have demonstrated remarkable potential in the field of speech generation. However, to ensure high-fidelity audio reconstruction, neural audio codecs typically encode audio into long sequences…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-02 Wenrui Liu , Qian Chen , Wen Wang , Yafeng Chen , Jin Xu , Zhifang Guo , Guanrou Yang , Weiqin Li , Xiaoda Yang , Tao Jin , Minghui Fang , Jialong Zuo , Bai Jionghao , Zemin Liu

Consider the case where consecutive blocks of N letters of a semi-infinite individual sequence X over a finite-alphabet are being compressed into binary sequences by some one-to-one mapping. No a-priori information about X is available at…

Information Theory · Computer Science 2013-01-25 Jacob Ziv

Recurrent neural networks have proved to be an effective method for statistical language modeling. However, in practice their memory and run-time complexity are usually too large to be implemented in real-time offline mobile applications.…

Computation and Language · Computer Science 2019-04-09 Artem M. Grachev , Dmitry I. Ignatov , Andrey V. Savchenko

Weight-sharing neural architecture search aims to optimize a configurable neural network model (supernet) for a variety of deployment scenarios across many devices with different resource constraints. Existing approaches use evolutionary…

Machine Learning · Computer Science 2023-07-04 Achintya Kundu , Laura Wynter , Rhui Dih Lee , Luis Angel Bathen
‹ Prev 1 2 3 10 Next ›