English
Related papers

Related papers: Towards Lossless Token Pruning in Late-Interaction…

200 papers

Deploying transformer models in practice is challenging due to their inference cost, which scales quadratically with input sequence length. To address this, we present a novel Learned Token Pruning (LTP) method which adaptively removes…

Computation and Language · Computer Science 2022-06-06 Sehoon Kim , Sheng Shen , David Thorsley , Amir Gholami , Woosuk Kwon , Joseph Hassoun , Kurt Keutzer

The unmatched ability of Deep Neural Networks in capturing complex patterns in large and noisy datasets is often associated with their large hypothesis space, and consequently to the vast amount of parameters that characterize model…

Machine Learning · Computer Science 2026-02-25 Enrico Ballini , Luca Muscarnera , Alessio Fumagalli , Anna Scotti , Francesco Regazzoni

With the advancement of large-scale language modeling techniques, large multimodal models combining visual encoders with large language models have demonstrated exceptional performance in various visual tasks. Most of the current…

Computer Vision and Pattern Recognition · Computer Science 2024-12-20 Yi Chen , Jian Xu , Xu-Yao Zhang , Wen-Zhuo Liu , Yang-Yang Liu , Cheng-Lin Liu

Pruning is an efficient model compression technique to remove redundancy in the connectivity of deep neural networks (DNNs). Computations using sparse matrices obtained by pruning parameters, however, exhibit vastly different parallelism…

Machine Learning · Computer Science 2019-05-15 Dongsoo Lee , Se Jung Kwon , Byeongwook Kim , Parichay Kapoor , Gu-Yeon Wei

Prior research notes that BERT's computational cost grows quadratically with sequence length thus leading to longer training times, higher GPU memory constraints and carbon emissions. While recent work seeks to address these scalability…

Computation and Language · Computer Science 2020-11-02 Yatin Chaudhary , Pankaj Gupta , Khushbu Saxena , Vivek Kulkarni , Thomas Runkler , Hinrich Schütze

This research aims to unravel how large language models (LLMs) iteratively refine token predictions through internal processing. We utilized a logit lens technique to analyze the model's token predictions derived from intermediate…

Computation and Language · Computer Science 2025-06-10 Jaturong Kongmanee

Dataset pruning reduces the storage and training costs of deep learning by selecting an informative subset from a large dataset. However, most existing pruning methods require fully labeled data, which limits their applicability in…

Machine Learning · Computer Science 2026-05-25 Yeseul Cho , Baekrok Shin , Changmin Kang , Chulhee Yun

Structural pruning of neural network parameters reduces computation, energy, and memory transfer costs during inference. We propose a novel method that estimates the contribution of a neuron (filter) to the final loss and iteratively…

Machine Learning · Computer Science 2019-06-27 Pavlo Molchanov , Arun Mallya , Stephen Tyree , Iuri Frosio , Jan Kautz

This work suggests fundamentally rethinking the current practice of pruning large language models (LLMs). The way it is done is by divide and conquer: split the model into submodels, sequentially prune them, and reconstruct predictions of…

Computation and Language · Computer Science 2024-10-14 Sungbin Shin , Wonpyo Park , Jaeho Lee , Namhoon Lee

Visual token compression is critical for Large Vision-Language Models (LVLMs) to efficiently process high-resolution inputs. Existing methods that typically adopt fixed compression ratios cannot adapt to scenes of varying complexity, often…

Computer Vision and Pattern Recognition · Computer Science 2025-08-05 Quan-Sheng Zeng , Yunheng Li , Qilong Wang , Peng-Tao Jiang , Zuxuan Wu , Ming-Ming Cheng , Qibin Hou

The PLAID (Performance-optimized Late Interaction Driver) algorithm for ColBERTv2 uses clustered term representations to retrieve and progressively prune documents for final (exact) document scoring. In this paper, we reproduce and fill in…

Information Retrieval · Computer Science 2024-04-24 Sean MacAvaney , Nicola Tonellotto

Despite the superior performance, it is challenging to deploy foundation models or large language models (LLMs) due to their massive parameters and computations. While pruning is a promising technique to reduce model size and accelerate the…

Machine Learning · Computer Science 2024-10-22 Pu Zhao , Fei Sun , Xuan Shen , Pinrui Yu , Zhenglun Kong , Yanzhi Wang , Xue Lin

Real-time inference of vision-language-action (VLA) models is essential for robotic control. While visual token pruning has shown strong potential for accelerating inference, most existing methods mainly base pruning decisions on…

Computer Vision and Pattern Recognition · Computer Science 2026-05-29 Shilin Ma , Chubin Zhang , Changyuan Wang , Yuji Wang , Yue Wu , Zixuan Wang , Jingqi Tian , Zheng Zhu , Yansong Tang

Late interaction retrieval methods, pioneered by ColBERT, have emerged as a powerful alternative to single-vector neural IR. By leveraging fine-grained, token-level representations, they have been demonstrated to deliver strong…

Information Retrieval · Computer Science 2025-11-04 Benjamin Clavié , Xianming Li , Antoine Chaffin , Omar Khattab , Tom Aarsen , Manuel Faysse , Jing Li

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) based on transformer are witnessing a notable trend of size expansion, which brings considerable costs to both model training and inference. However, existing methods such as model quantization, knowledge…

Computation and Language · Computer Science 2024-10-16 Yifei Yang , Zouying Cao , Hai Zhao

Recent advances in deep learning rely heavily on massive datasets, leading to substantial storage and training costs. Dataset pruning aims to alleviate this demand by discarding redundant examples. However, many existing methods require…

Machine Learning · Computer Science 2025-06-13 Yeseul Cho , Baekrok Shin , Changmin Kang , Chulhee Yun

It is common to encounter situations where one must solve a sequence of similar computational problems. Running a standard algorithm with worst-case runtime guarantees on each instance will fail to take advantage of valuable structure…

Machine Learning · Computer Science 2019-04-29 Daniel Alabi , Adam Tauman Kalai , Katrina Ligett , Cameron Musco , Christos Tzamos , Ellen Vitercik

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

Visual token pruning is a promising approach for reducing the computational cost of vision-language models (VLMs), and existing methods often rely on early pruning decisions to improve efficiency. While effective on coarse-grained reasoning…

Computer Vision and Pattern Recognition · Computer Science 2026-02-04 Chen Qian , Xinran Yu , Danyang Li , Guoxuan Chi , Zheng Yang , Qiang Ma , Xin Miao
‹ Prev 1 8 9 10 Next ›