English
Related papers

Related papers: Compression Barriers for Autoregressive Transforme…

200 papers

Many studies have been conducted to improve the efficiency of Transformer from quadric to linear. Among them, the low-rank-based methods aim to learn the projection matrices to compress the sequence length. However, the projection matrices…

Machine Learning · Computer Science 2022-11-30 Bosheng Qin , Juncheng Li , Siliang Tang , Yueting Zhuang

Given the query, key and value matrices $Q, K, V\in \mathbb{R}^{n\times d}$, the attention module is defined as $\mathrm{Att}(Q, K, V)=D^{-1}AV$ where $A=\exp(QK^\top/\sqrt{d})$ with $\exp(\cdot)$ applied entrywise, $D=\mathrm{diag}(A{\bf…

Quantum Physics · Physics 2026-02-03 Zhao Song , Jianfei Xue , Jiahao Zhang , Lichen Zhang

Many computational factors limit broader deployment of large language models. In this paper, we focus on a memory bottleneck imposed by the key-value (KV) cache, a computational shortcut that requires storing previous KV pairs during…

Machine Learning · Computer Science 2024-06-13 Harry Dong , Xinyu Yang , Zhenyu Zhang , Zhangyang Wang , Yuejie Chi , Beidi Chen

We introduce GoldFinch, a hybrid Linear Attention/Transformer sequence model that uses a new technique to efficiently generate a highly compressed and reusable KV-Cache in linear time and space with respect to sequence length. GoldFinch…

Computation and Language · Computer Science 2024-07-18 Daniel Goldstein , Fares Obeid , Eric Alcaide , Guangyu Song , Eugene Cheah

Modern Large Language Models (LLMs) are increasingly trained to support very large context windows. We present Compactor, a training-free, query-agnostic KV compression strategy that uses approximate leverage scores to determine token…

Computation and Language · Computer Science 2025-12-10 Vivek Chari , Benjamin Van Durme

As Large Language Models (LLMs) scale to support context windows exceeding one million tokens, the linear growth of Key-Value (KV) cache imposes severe memory capacity and bandwidth bottlenecks, constraining the efficiency of long-context…

Computation and Language · Computer Science 2026-04-09 Zhirui Chen , Peiyang Liu , Ling Shao

Generative models have demonstrated strong performance in conditional settings and can be viewed as a form of data compression, where the condition serves as a compact representation. However, their limited controllability and…

Machine Learning · Computer Science 2025-07-04 Xiao Li , Liangji Zhu , Anand Rangarajan , Sanjay Ranka

In memory-constrained algorithms we have read-only access to the input, and the number of additional variables is limited. In this paper we introduce the compressed stack technique, a method that allows to transform algorithms whose space…

Computational Geometry · Computer Science 2014-06-26 Luis Barba , Matias Korman , Stefan Langerman , Kunikiko Sadakane , Rodrigo Silveira

Key-Value cache (\texttt{KV} \texttt{cache}) compression has emerged as a promising technique to optimize Large Language Model (LLM) serving. It primarily decreases the memory consumption of \texttt{KV} \texttt{cache} to reduce the…

Machine Learning · Computer Science 2025-04-01 Wei Gao , Xinyu Zhou , Peng Sun , Tianwei Zhang , Yonggang Wen

Autoregressive (AR) visual generation has emerged as a powerful paradigm for image and multimodal synthesis, owing to its scalability and generality. However, existing AR image generation suffers from severe memory bottlenecks due to the…

Computer Vision and Pattern Recognition · Computer Science 2025-12-05 Ziran Qin , Youru Lv , Mingbao Lin , Zeren Zhang , Chanfan Gan , Tieyuan Chen , Weiyao Lin

Large language models (LLMs) based on Transformer Decoders have become the preferred choice for conversational generative AI. Despite the overall superiority of the Decoder architecture, the gradually increasing Key-Value (KV) cache during…

Computation and Language · Computer Science 2025-07-16 Luohe Shi , Zuchao Li , Lefei Zhang , Guoming Liu , Baoyuan Qi , Hai Zhao

The Transformer architecture is widely deployed in many popular and impactful Large Language Models. At its core is the attention mechanism for calculating correlations between pairs of tokens. Performing an attention computation takes…

Machine Learning · Computer Science 2025-05-26 Josh Alman , Hantao Yu

In this work, we study the limits of compressed data structures, i.e., structures that support various queries on an input text $T\in\Sigma^n$ using space proportional to the size of $T$ in compressed form. Nearly all fundamental queries…

Data Structures and Algorithms · Computer Science 2025-10-23 Dominik Kempa , Tomasz Kociumaka

Efficient lossless compression is essential for minimizing storage costs and transmission overhead while preserving data integrity. Traditional compression techniques, such as dictionary-based and statistical methods, often struggle to…

Artificial Intelligence · Computer Science 2026-02-13 Mahdi Khodabandeh , Ghazal Shabani , Arash Yousefi Jordehi , Seyed Abolghasem Mirroshandel

In recent years, Large Language Models (LLMs) have demonstrated remarkable capabilities across a wide array of text-centric tasks. However, their `large' scale introduces significant computational and storage challenges, particularly in…

Computation and Language · Computer Science 2024-07-03 Chaoran Zhang , Lixin Zou , Dan Luo , Min Tang , Xiangyang Luo , Zihao Li , Chenliang Li

Deep learning's success has led to larger and larger models to handle more and more complex tasks; trained models can contain millions of parameters. These large models are compute- and memory-intensive, which makes it a challenge to deploy…

Machine Learning · Computer Science 2023-05-19 Chong Yu , Jeff Pool

Long-context reasoning is a critical capability of large language models (LLMs), enabling applications such as long-document understanding, summarization, and code generation. However, efficient autoregressive inference relies on the…

Computation and Language · Computer Science 2026-04-28 Zahra Dehghanighobadi , Asja Fischer

Transformer-based large language models (LLMs) demonstrate impressive potential in various practical applications. However, long context inference poses a significant challenge due to the enormous memory requirements of the key-value (KV)…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-09-03 Bo Jiang , Taolue Yang , Youyuan Liu , Chengming Zhang , Xubin He , Sian Jin

Transformers are widely used across data modalities, and yet the principles distilled from text models often transfer imperfectly to models trained to other modalities. In this paper, we analyze Transformers through the lens of rank…

Attention-based models, such as Transformer, excel across various tasks but lack a comprehensive theoretical understanding, especially regarding token-wise sparsity and internal linear representations. To address this gap, we introduce the…

Machine Learning · Statistics 2025-02-27 Pierre Marion , Raphaël Berthier , Gérard Biau , Claire Boyer