English
Related papers

Related papers: GRASPrune: Global Gating for Budgeted Structured P…

200 papers

Making large language models (LLMs) more efficient in memory, latency, and serving cost is crucial for edge deployment, interactive applications, and sustainable inference at scale. Pruning is a promising technique, but existing pruning…

Computation and Language · Computer Science 2025-10-13 Eugene Kwek , Wenpeng Yin

Large language models (LLMs) have shown impressive capabilities across various tasks. However, training LLMs from scratch requires significant computational power and extensive memory capacity. Recent studies have explored low-rank…

Machine Learning · Computer Science 2024-11-05 Andi Han , Jiaxiang Li , Wei Huang , Mingyi Hong , Akiko Takeda , Pratik Jawanpuria , Bamdev Mishra

As Large Language Models (LLMs) continue to scale, post-training pruning has emerged as a promising approach to reduce computational costs while preserving performance. Existing methods such as SparseGPT and Wanda achieve high sparsity…

Computation and Language · Computer Science 2026-01-15 Sai Varun Kodathala , Rakesh Vunnam

In recent years, the size of pre-trained language models (PLMs) has grown by leaps and bounds. However, efficiency issues of these large-scale PLMs limit their utilization in real-world scenarios. We present a suite of cost-effective…

We surely enjoy the larger the better models for their superior performance in the last couple of years when both the hardware and software support the birth of such extremely huge models. The applied fields include text mining and others.…

Computation and Language · Computer Science 2024-06-04 Hanjuan Huang , Hao-Jia Song , Hsing-Kuo Pao

Large Language Models (LLMs) are distinguished by their massive parameter counts, which typically result in significant redundancy. This work introduces MaskLLM, a learnable pruning method that establishes Semi-structured (or ``N:M'')…

Artificial Intelligence · Computer Science 2024-12-10 Gongfan Fang , Hongxu Yin , Saurav Muralidharan , Greg Heinrich , Jeff Pool , Jan Kautz , Pavlo Molchanov , Xinchao Wang

Parameter efficient fine tuning is a way to adapt LLMs to new languages when compute or data are limited, yet adapter pipelines usually choose a global prune ratio by grid search. This practice is computationally expensive and development…

Computation and Language · Computer Science 2026-01-13 Besher Hassan , Xiuying Chen

Large Vision Language Models show impressive performance across image and video understanding tasks, yet their computational cost grows rapidly with the number of visual tokens. Existing token pruning methods mitigate this issue through…

Computer Vision and Pattern Recognition · Computer Science 2026-04-02 Dong-Jae Lee , Sunghyun Baek , Junmo Kim

Pruning is a compression method which aims to improve the efficiency of neural networks by reducing their number of parameters while maintaining a good performance, thus enhancing the performance-to-cost ratio in nontrivial ways. Of…

Neural and Evolutionary Computing · Computer Science 2023-09-25 Hugo Tessier , Ghouti Boukli Hacene , Vincent Gripon

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

In Vision-Language Models (VLMs), processing a massive number of visual tokens incurs prohibitive computational overhead. While recent training-aware pruning methods attempt to selectively discard redundant tokens, they largely rely on…

Computer Vision and Pattern Recognition · Computer Science 2026-05-14 Mingzhe Huang , Weijun Wang , Xin Ding , Liang Mi , Hao Wen , Yuanchun Li , Lichen Pang , Shansong Yang , Yunxin Liu , Ting Cao

While Transformer-based models have shown impressive language modeling performance, the large computation cost is often prohibitive for practical use. Attention head pruning, which removes unnecessary attention heads in the multihead…

Computation and Language · Computer Science 2021-10-08 Kyuhong Shim , Iksoo Choi , Wonyong Sung , Jungwook Choi

LLM-powered coding agents spend the majority of their token budget reading repository files, yet much of the retrieved code is irrelevant to the task at hand. Existing learned pruners compress this context with a single-objective sequence…

Artificial Intelligence · Computer Science 2026-05-18 Jingjing Wang , Xiwen Chen , Wenhui Zhu , Huayu Li , Zhengxiao He , Feiyang Cai , Ana S. Carreon-Rascon , Xuanzhao Dong , Feng Luo

Pre-trained language models (PLM), for example BERT or RoBERTa, mark the state-of-the-art for natural language understanding task when fine-tuned on labeled data. However, their large size poses challenges in deploying them for inference in…

Machine Learning · Computer Science 2024-08-27 Aaron Klein , Jacek Golebiowski , Xingchen Ma , Valerio Perrone , Cedric Archambeau

In spite of strong performance achieved by LLMs, the costs of their deployment are unaffordable. For the compression of LLMs, gradient-based pruning methods present promising effectiveness. However, in these methods, the gradient…

Computation and Language · Computer Science 2025-06-16 Hourun Zhu , Chengchao Shen

State-of-the-art LLMs often rely on scale with high computational costs, which has sparked a research agenda to reduce parameter counts and costs without significantly impacting performance. Our study focuses on Transformer-based LLMs,…

Computation and Language · Computer Science 2024-07-25 Xiuying Wei , Skander Moalla , Razvan Pascanu , Caglar Gulcehre

Recent advances in pruning of neural networks have made it possible to remove a large number of filters or weights without any perceptible drop in accuracy. The number of parameters and that of FLOPs are usually the reported metrics to…

Computer Vision and Pattern Recognition · Computer Science 2020-11-10 Sara Elkerdawy , Mostafa Elhoushi , Abhineet Singh , Hong Zhang , Nilanjan Ray

Self-supervised learning (SSL) models like WavLM can be effectively utilized when building speaker diarization systems but are often large and slow, limiting their use in resource constrained scenarios. Previous studies have explored…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-02 Jiangyu Han , Federico Landini , Johan Rohdin , Anna Silnova , Mireia Diez , Jan Cernocky , Lukas Burget

Deploying Large Language Models (LLMs) on resource-constrained (or weak) devices presents significant challenges due to limited resources and heterogeneous data distribution. To address the data concern, it is necessary to fine-tune LLMs…

Machine Learning · Computer Science 2025-01-07 Zhiwei Yao , Yang Xu , Hongli Xu , Yunming Liao , Zuan Xie

Structured pruning of filters or neurons has received increased focus for compressing convolutional neural networks. Most existing methods rely on multi-stage optimizations in a layer-wise manner for iteratively pruning and retraining which…

Computer Vision and Pattern Recognition · Computer Science 2019-03-25 Shaohui Lin , Rongrong Ji , Chenqian Yan , Baochang Zhang , Liujuan Cao , Qixiang Ye , Feiyue Huang , David Doermann