English
Related papers

Related papers: To Asymmetry and Beyond: Structured Pruning of Seq…

200 papers

Self-supervised speech representation learning (SSL) has shown to be effective in various downstream tasks, but SSL models are usually large and slow. Model compression techniques such as pruning aim to reduce the model size and computation…

Computation and Language · Computer Science 2023-03-01 Yifan Peng , Kwangyoun Kim , Felix Wu , Prashant Sridhar , Shinji Watanabe

This paper presents an efficient technique to prune deep and/or wide convolutional neural network models by eliminating redundant features (or filters). Previous studies have shown that over-sized deep neural network models tend to produce…

Computer Vision and Pattern Recognition · Computer Science 2018-02-22 Babajide O. Ayinde , Jacek M. Zurada

Structured pruning of modern large language models (LLMs) has emerged as a way of decreasing their high computational needs. Width pruning reduces the size of projection weight matrices (e.g., by removing attention heads) while maintaining…

Machine Learning · Computer Science 2024-06-25 Bo-Kyeong Kim , Geonmin Kim , Tae-Ho Kim , Thibault Castells , Shinkook Choi , Junho Shin , Hyoung-Kyu Song

The excellent performance of deep neural networks is usually accompanied by a large number of parameters and computations, which have limited their usage on the resource-limited edge devices. To address this issue, abundant methods such as…

Computer Vision and Pattern Recognition · Computer Science 2023-05-23 Muzhou Yu , Linfeng Zhang , Kaisheng Ma

Representation learning plays a central role in structuring internal embeddings to capture the statistical properties of language, influencing the coherence and contextual consistency of generated text. Statistical Coherence Alignment is…

Computation and Language · Computer Science 2025-08-11 Jonathan Gale , Godfrey Aldington , Harriet Thistlewood , Thomas Tattershall , Basil Wentworth , Vincent Enoasmo

In a controlled experiment of sequence-to-sequence approaches for the task of sentence correction, we find that character-based models are generally more effective than word-based models and models that encode subword information via…

Computation and Language · Computer Science 2017-07-31 Allen Schmaltz , Yoon Kim , Alexander M. Rush , Stuart M. Shieber

While multi-vector retrieval models outperform single-vector models of comparable size in retrieval quality, their practicality is limited by substantially larger index sizes, driven by the additional sequence-length dimension in their…

Information Retrieval · Computer Science 2026-03-25 Rohan Jha , Chunsheng Zuo , Reno Kriz , Benjamin Van Durme

Small language models (SLMs) have attracted considerable attention from both academia and industry due to their broad range of applications in edge devices. To obtain SLMs with strong performance, conventional approaches either pre-train…

Machine Learning · Computer Science 2025-11-17 Rui Pan , Shivanshu Shekhar , Boyao Wang , Shizhe Diao , Jipeng Zhang , Xingyuan Pan , Renjie Pi , Tong Zhang

How can we accelerate large language models(LLMs) without sacrificing accuracy? The slow inference speed of LLMs hinders us to benefit from their remarkable performance in diverse applications. This is mainly because numerous sublayers are…

Computation and Language · Computer Science 2025-06-05 Seungcheol Park , Sojin Lee , Jongjin Kim , Jinsik Lee , Hyunjik Jo , U Kang

Efficient machine learning implementations optimized for inference in hardware have wide-ranging benefits, depending on the application, from lower inference latency to higher data throughput and reduced energy consumption. Two popular…

Machine Learning · Computer Science 2021-07-21 Benjamin Hawks , Javier Duarte , Nicholas J. Fraser , Alessandro Pappalardo , Nhan Tran , Yaman Umuroglu

Attention mechanism in sequence-to-sequence models is designed to model the alignments between acoustic features and output tokens in speech recognition. However, attention weights produced by models trained end to end do not always…

Audio and Speech Processing · Electrical Eng. & Systems 2022-04-27 Gene-Ping Yang , Hao Tang

Recent work targeting large language models (LLMs) for code generation demonstrated that increasing the amount of training data through synthetic code generation often leads to exceptional performance. In this paper we explore data pruning…

Software Engineering · Computer Science 2024-07-09 Yun-Da Tsai , Mingjie Liu , Haoxing Ren

Model pruning technique is vital for accelerating large language models by reducing their size and computational requirements. However, the generalizability of existing pruning methods across diverse datasets and tasks remains unclear.…

Computation and Language · Computer Science 2025-03-04 Yizhuo Ding , Xinwei Sun , Yanwei Fu , Guosheng Hu

We study the scaling properties of latent diffusion models (LDMs) with an emphasis on their sampling efficiency. While improved network architecture and inference algorithms have shown to effectively boost sampling efficiency of diffusion…

Computer Vision and Pattern Recognition · Computer Science 2024-12-11 Kangfu Mei , Zhengzhong Tu , Mauricio Delbracio , Hossein Talebi , Vishal M. Patel , Peyman Milanfar

Pruning has emerged as a promising direction for accelerating large language model (LLM) inference, yet existing approaches often suffer from instability because they rely on offline calibration data that may not generalize across inputs.…

Computation and Language · Computer Science 2025-12-09 Jungmin Lee , Gwangeun Byeon , Yulhwa Kim , Seokin Hong

Large, pre-trained models are problematic to use in resource constrained applications. Fortunately, task-aware structured pruning methods offer a solution. These approaches reduce model size by dropping structural units like layers and…

Computation and Language · Computer Science 2023-11-14 Lucio Dery , David Grangier , Awni Hannun

One surprising trait of neural networks is the extent to which their connections can be pruned with little to no effect on accuracy. But when we cross a critical level of parameter sparsity, pruning any further leads to a sudden drop in…

Machine Learning · Computer Science 2023-01-20 Junyang Cai , Khai-Nguyen Nguyen , Nishant Shrestha , Aidan Good , Ruisen Tu , Xin Yu , Shandian Zhe , Thiago Serra

Recent advancements in large language models have intensified the need for efficient and deployable models within limited inference budgets. Structured pruning pipelines have shown promise in token efficiency compared to training…

Computation and Language · Computer Science 2025-03-11 Yixiao Li , Xianzhi Du , Ajay Jaiswal , Tao Lei , Tuo Zhao , Chong Wang , Jianyu Wang

Recurrent Neural Networks (RNN) are widely used to solve a variety of problems and as the quantity of data and the amount of available compute have increased, so have model sizes. The number of parameters in recent state-of-the-art networks…

Machine Learning · Computer Science 2017-11-08 Sharan Narang , Erich Elsen , Gregory Diamos , Shubho Sengupta

Autoregressive Transformers adopted in Large Language Models (LLMs) are hard to scale to long sequences. Despite several works trying to reduce their computational cost, most of LLMs still adopt attention layers between all pairs of tokens…

Computation and Language · Computer Science 2024-06-03 Sotiris Anagnostidis , Dario Pavllo , Luca Biggio , Lorenzo Noci , Aurelien Lucchi , Thomas Hofmann