English
Related papers

Related papers: A Brief Comparison of Training-Free Multi-Vector S…

200 papers

There are increasingly efficient data processing pipelines that work on vectors of numbers, for instance most machine learning models, or vector databases for fast similarity search. These require converting the data to numbers. While this…

Machine Learning · Statistics 2023-12-18 Léo Grinsztajn , Edouard Oyallon , Myung Jun Kim , Gaël Varoquaux

Transformer based large language models have achieved tremendous success. However, the significant memory and computational costs incurred during the inference process make it challenging to deploy large models on resource-constrained…

Computation and Language · Computer Science 2024-02-16 Wenxiao Wang , Wei Chen , Yicong Luo , Yongliu Long , Zhengkai Lin , Liye Zhang , Binbin Lin , Deng Cai , Xiaofei He

Transformers are central in modern natural language processing and computer vision applications. Despite recent works devoted to reducing the quadratic cost of such models (as a function of the sequence length), dealing with ultra long…

Computation and Language · Computer Science 2023-05-30 Zhanpeng Zeng , Cole Hawkins , Mingyi Hong , Aston Zhang , Nikolaos Pappas , Vikas Singh , Shuai Zheng

We study model pruning methods applied to Transformer-based neural network language models for automatic speech recognition. We explore three aspects of the pruning frame work, namely criterion, method and scheduler, analyzing their…

Machine Learning · Computer Science 2023-10-06 Leonardo Emili , Thiago Fraga-Silva , Ernest Pusateri , Markus Nußbaum-Thom , Youssef Oualil

As the computational needs of Large Vision-Language Models (LVLMs) increase, visual token pruning has proven effective in improving inference speed and memory efficiency. Traditional pruning methods in LVLMs predominantly focus on attention…

Computer Vision and Pattern Recognition · Computer Science 2025-03-12 Bozhi Luan , Wengang Zhou , Hao Feng , Zhe Wang , Xiaosong Li , Houqiang Li

Cross-modal retrieval is an important functionality in modern search engines, as it increases the user experience by allowing queries and retrieved objects to pertain to different modalities. In this paper, we focus on the image-sentence…

Computer Vision and Pattern Recognition · Computer Science 2021-06-02 Nicola Messina , Giuseppe Amato , Fabrizio Falchi , Claudio Gennaro , Stéphane Marchand-Maillet

Tokenization is a fundamental component of language models for code. It involves breaking down the input into units that are later passed to the language model stack to learn high-dimensional representations used in various contexts, from…

Software Engineering · Computer Science 2025-07-22 Mootez Saad , Hao Li , Tushar Sharma , Ahmed E. Hassan

Modern deep neural networks, particularly recent large language models, come with massive model sizes that require significant computational and storage resources. To enable the deployment of modern models on resource-constrained…

Machine Learning · Computer Science 2024-08-12 Hongrong Cheng , Miao Zhang , Javen Qinfeng Shi

The ability of machine learning models to store input information in hidden layer vector embeddings, analogous to the concept of `memory', is widely employed but not well characterized. We find that language model embeddings typically…

Computation and Language · Computer Science 2026-05-20 Benjamin L. Badger

Multivector retrieval models achieve state-of-the-art effectiveness through fine-grained token-level representations, but their deployment incurs substantial computational and memory costs. Current solutions, based on the well-known k-means…

Information Retrieval · Computer Science 2026-05-01 Silvio Martinico , Franco Maria Nardini , Cosimo Rulli , Rossano Venturini

Vector averaging remains one of the most popular sentence embedding methods in spite of its obvious disregard for syntactic structure. While more complex sequential or convolutional networks potentially yield superior classification…

Computation and Language · Computer Science 2020-01-10 Nada Almarwani , Hanan Aldarmaki , Mona Diab

Current approaches to reducing undesired capabilities in language models are largely post hoc, and can thus be easily bypassed by adversaries. A natural alternative is to shape capabilities during pretraining itself. On the proxy task of…

Machine Learning · Computer Science 2026-02-03 Neil Rathi , Alec Radford

In large vision-language models, visual tokens typically constitute the majority of input tokens, leading to substantial computational overhead. To address this, recent studies have explored pruning redundant or less informative visual…

Computer Vision and Pattern Recognition · Computer Science 2026-05-14 Sangin Lee , Yukyung Choi

Embedding-based vector search underpins many important applications, such as recommendation and retrieval-augmented generation (RAG). It relies on vector indices to enable efficient search. However, these indices require storing…

Vision-Language Models (VLMs) have advanced rapidly within the unified Transformer architecture, yet their deployment on resource-constrained devices remains challenging due to high computational complexity. While pruning has emerged as an…

Computer Vision and Pattern Recognition · Computer Science 2026-04-06 Zimeng Wu , Yunhong Wang , Donghao Wang , Jiaxin Chen

Prompt compression methods enhance the efficiency of Large Language Models (LLMs) and minimize the cost by reducing the length of input context. The goal of prompt compression is to shorten the LLM prompt while maintaining a high generation…

Computation and Language · Computer Science 2025-08-25 Tinghui Zhang , Yifan Wang , Daisy Zhe Wang

Vision-language models (VLMs) face significant computational inefficiencies caused by excessive generation of visual tokens. While prior work shows that a large fraction of visual tokens are redundant, existing compression methods struggle…

Computer Vision and Pattern Recognition · Computer Science 2026-03-12 Zhengyao Fang , Pengyuan Lyu , Chengquan Zhang , Guangming Lu , Jun Yu , Wenjie Pei

Vision-Language Models (VLMs) demand substantial computational resources during inference, largely due to the extensive visual input tokens for representing visual information. Previous studies have noted that visual tokens tend to receive…

Computer Vision and Pattern Recognition · Computer Science 2025-04-01 Cheng Yang , Yang Sui , Jinqi Xiao , Lingyi Huang , Yu Gong , Chendi Li , Jinghua Yan , Yu Bai , Ponnuswamy Sadayappan , Xia Hu , Bo Yuan

Recent advances have explored visual token pruning to accelerate the inference of large vision-language models (LVLMs). However, existing methods often struggle to balance token importance and diversity: importance-based methods tend to…

Computer Vision and Pattern Recognition · Computer Science 2026-04-08 Zhaohong Huang , Wenjing Liu , Yuxin Zhang , Fei Chao , Rongrong Ji

Recently, Information Retrieval community has witnessed fast-paced advances in Dense Retrieval (DR), which performs first-stage retrieval with embedding-based search. Despite the impressive ranking performance, previous studies usually…

Information Retrieval · Computer Science 2021-08-24 Jingtao Zhan , Jiaxin Mao , Yiqun Liu , Jiafeng Guo , Min Zhang , Shaoping Ma