English
Related papers

Related papers: On Match Lengths, Zero Entropy and Large Deviation…

200 papers

Repository-level code intelligence tasks require large language models (LLMs) to process long, multi-file contexts. Such inputs introduce three challenges: crucial context can be obscured by noise, truncated due to limited windows, and…

Software Engineering · Computer Science 2026-04-16 Jia Feng , Zhanyue Qin , Cuiyun Gao , Ruiqi Wang , Chaozheng Wang , Yingwei Ma , Xiaoyuan Xie

Lossless model compression holds tremendous promise for alleviating the memory and bandwidth bottlenecks in bit-exact Large Language Model (LLM) serving. However, existing approaches often result in substantial inference slowdowns due to…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-03-19 Ruibo Fan , Xiangrui Yu , Xinglin Pan , Zeyu Li , Weile Luo , Qiang Wang , Wei Wang , Xiaowen Chu

The advent of massive datasets (and the consequent design of high-performing distributed storage systems) have reignited the interest of the scientific and engineering community towards the design of lossless data compressors which achieve…

Information Theory · Computer Science 2013-07-16 Andrea Farruggia , Paolo Ferragina , Antonio Frangioni , Rossano Venturini

The linear growth of key-value (KV) cache memory and quadratic computational in attention mechanisms complexity pose significant bottlenecks for large language models (LLMs) in long-context processing. While existing KV cache optimization…

Computation and Language · Computer Science 2025-10-07 Xin Liu , Xudong Wang , Pei Liu , Guoming Tang

Large Language Models (LLMs) have shown exciting performance in listwise passage ranking. Due to the limited input length, existing methods often adopt the sliding window strategy. Such a strategy, though effective, is inefficient as it…

Information Retrieval · Computer Science 2024-12-20 Wenhan Liu , Xinyu Ma , Yutao Zhu , Ziliang Zhao , Shuaiqiang Wang , Dawei Yin , Zhicheng Dou

Random access to highly compressed strings -- represented by straight-line programs or Lempel-Ziv parses, for example -- is a well-studied topic. Random access to such strings in strongly sublogarithmic time is impossible in the worst case,…

Data Structures and Algorithms · Computer Science 2026-02-05 Ferdinando Cicalese , Zsuzsanna Lipták , Travis Gagie , Gonzalo Navarro , Nicola Prezza , Cristian Urbina

Language models (LMs) are trained on billions of tokens in an attempt to recover the true language distribution. Still, vanilla random sampling from LMs yields low quality generations. Decoding algorithms attempt to restrict the LM…

Machine Learning · Computer Science 2026-01-06 Kareem Ahmed , Sameer Singh

Pipeline-parallel distributed optimization is essential for large-scale machine learning but is challenged by significant communication overhead from transmitting high-dimensional activations and gradients between workers. Existing…

Optimization and Control · Mathematics 2025-09-24 Boao Kong , Xu Huang , Yuqi Xu , Yixuan Liang , Bin Wang , Kun Yuan

Large Language Models (LLMs) have significantly impacted many facets of natural language processing and information retrieval. Unlike previous encoder-based approaches, the enlarged context window of these generative models allows for…

Information Retrieval · Computer Science 2024-05-24 Andrew Parry , Sean MacAvaney , Debasis Ganguly

We study restricted permutations of sets which have a geometrical structure. The study of restricted permutations is motivated by their application in coding for flash memories, and their relevance in different applications of networking…

Dynamical Systems · Mathematics 2020-01-03 Dor Elimelech

The rapid advancement of large language models (LLMs) has led to a significant increase in automated tools in the software engineering, capable of performing various code-related tasks such as code generation, completion, and translation.…

Software Engineering · Computer Science 2026-02-26 Madhusudan Ghosh , Rishabh Gupta

We conceptualize the process of understanding as information compression, and propose a method for ranking large language models (LLMs) based on lossless data compression. We demonstrate the equivalence of compression length under…

Artificial Intelligence · Computer Science 2024-06-21 Peijia Guo , Ziguang Li , Haibo Hu , Chao Huang , Ming Li , Rui Zhang

Lossless floating-point time series compression is crucial for a wide range of critical scenarios. Nevertheless, it is a big challenge to compress time series losslessly due to the complex underlying layouts of floating-point values. The…

Data Structures and Algorithms · Computer Science 2023-09-15 Ruiyuan Li , Zheng Li , Yi Wu , Chao Chen , Tong Liu , Yu Zheng

With the advancements in long-context inference capabilities of large language models (LLMs), the KV cache has become one of the foundational components. However, its substantial GPU memory consumption makes KV cache compression a key…

Computation and Language · Computer Science 2025-03-28 Youhui Zuo , Sibo Wei , Chen Zhang , Zhuorui Liu , Wenpeng Lu , Dawei Song

Large Language Models (LLMs) can perform zero-shot learning on unseen tasks and few-shot learning on complex reasoning tasks. However, resource-limited mobile edge networks struggle to support long-context LLM serving for LLM agents during…

Networking and Internet Architecture · Computer Science 2025-01-27 Minrui Xu , Dusit Niyato , Christopher G. Brinton

This study evaluates the effectiveness of zero-shot compression techniques on large language models (LLMs) under long-context. We identify the tendency for computational errors to increase under long-context when employing certain…

Computation and Language · Computer Science 2025-02-14 Chenyu Wang , Yihan Wang , Kai Li

During the training of Large Language Models (LLMs), tensor data is periodically "checkpointed" to persistent storage to allow recovery of work done in the event of failure. The volume of data that must be copied during each checkpoint,…

Machine Learning · Computer Science 2025-05-16 Daniel Waddington , Cornel Constantinescu

Dynamic dictionary-based compression schemes are the most daily used data compression schemes since they appeared in the foundational papers of Ziv and Lempel in 1977, commonly referred to as LZ77. Their work is the base of Deflate, gZip,…

Data Structures and Algorithms · Computer Science 2012-11-26 Maxime Crochemore , Alessio Langiu , Filippo Mignosi

This paper studies variable-length (VL) source coding of general sources with side-information. Novel one-shot coding theorems for coding with common side-information available at the encoder and the decoder and Slepian- Wolf (SW) coding…

Information Theory · Computer Science 2014-04-09 Shigeaki Kuzuoka , Shun Watanabe

The Lempel-Ziv 77 (LZ77) factorization is a fundamental compression scheme widely used in text processing and data compression. In this work, we investigate the time complexity of maintaining the LZ77 factorization of a dynamic string. By…

Data Structures and Algorithms · Computer Science 2025-10-28 Itai Boneh , Shay Golan , Matan Kraus