中文
相关论文

相关论文: Pushdown Compression

200 篇论文

Learned video compression methods have demonstrated great promise in catching up with traditional video codecs in their rate-distortion (R-D) performance. However, existing learned video compression schemes are limited by the binding of the…

图像与视频处理 · 电气工程与系统科学 2022-01-06 Runsen Feng , Zongyu Guo , Zhizheng Zhang , Zhibo Chen

Text compression for large language model (LLM) systems is usually framed as token deletion, retrieval, summarization, or exact reconstruction. We study a more aggressive but explicitly lossy setting: compress text into compact codes that…

机器学习 · 计算机科学 2026-05-26 Natalia Trukhina , Vadim Vashkelis

Present day computational fluid dynamics simulations generate extremely large amounts of data, sometimes on the order of TB/s. Often, a significant fraction of this data is discarded because current storage systems are unable to keep pace.…

计算工程、金融与科学 · 计算机科学 2021-03-03 Heather Pacella , Alec Dunton , Alireza Doostan , Gianluca Iaccarino

User data confidentiality protection is becoming a rising challenge in the present deep learning research. Without access to data, conventional data-driven model compression faces a higher risk of performance degradation. Recently, some…

机器学习 · 计算机科学 2022-01-28 Yuhang Li , Feng Zhu , Ruihao Gong , Mingzhu Shen , Xin Dong , Fengwei Yu , Shaoqing Lu , Shi Gu

In the modern paradigm of multi-agent networks, communication has become one of the main bottlenecks for decentralized optimization, where a large number of agents are involved in minimizing the average of the local cost functions. In this…

最优化与控制 · 数学 2023-03-14 Yiwei Liao , Zhuorui Li , Shi Pu

In a system that performs both encryption and lossy compression, the conventional way is to compress first and then encrypt the compressed data. This separation approach proves to be optimal. In certain applications where sensitive…

信息论 · 计算机科学 2014-08-26 Wei Kang , Nan Liu

Our goal is compression of massive-scale grid-structured data, such as the multi-terabyte output of a high-fidelity computational simulation. For such data sets, we have developed a new software package called TuckerMPI, a parallel C++/MPI…

数学软件 · 计算机科学 2020-07-09 Grey Ballard , Alicia Klinvex , Tamara G. Kolda

Split computing ($\neq$ split learning) is a promising approach to deep learning models for resource-constrained edge computing systems, where weak sensor (mobile) devices are wirelessly connected to stronger edge servers through channels…

计算机视觉与模式识别 · 计算机科学 2025-01-22 Yoshitomo Matsubara , Matteo Mendula , Marco Levorato

Text encoding is one of the most important steps in Natural Language Processing (NLP). It has been done well by the self-attention mechanism in the current state-of-the-art Transformer encoder, which has brought about significant…

计算与语言 · 计算机科学 2021-02-12 Zuchao Li , Zhuosheng Zhang , Hai Zhao , Rui Wang , Kehai Chen , Masao Utiyama , Eiichiro Sumita

In-context learning has established itself as an important learning paradigm for Large Language Models (LLMs). In this paper, we demonstrate that LLMs can learn encoding keys in-context and perform analysis directly on encoded…

计算与语言 · 计算机科学 2026-04-16 Andresa Rodrigues de Campos , David Lee , Imry Kissos , Piyush Paritosh

As the memory channel count is confined by physical dimensions, memory expanders appear to be a promising approach to extending memory capacity and channels by augmenting the existing I/O interface (e.g., PCIe) with memory-semantic…

硬件体系结构 · 计算机科学 2026-03-30 Younghoon Ko , Hyemin Park , Hyuk-Jae Lee , Hyokeun Lee

Advances in large language models have driven strong performance across many tasks, but their memory and compute costs still hinder deployment. SVD-based compression reduces storage and can speed up inference via low-rank factors, yet…

机器学习 · 计算机科学 2026-02-04 Ali Abbasi , Chayne Thrash , Haoran Qin , Shansita Sharma , Sepehr Seifi , Soheil Kolouri

Modern smart distribution system requires storage, transmission and processing of big data generated by sensors installed in electric meters. On one hand, this data is essentially required for intelligent decision making by smart grid but…

信号处理 · 电气工程与系统科学 2018-07-19 Syed Muhammad Atif , Anees Ahmed , Sameer Qazi

Computing problems that handle large amounts of data necessitate the use of lossless data compression for efficient storage and transmission. We present a novel lossless universal data compression algorithm that uses parallel computational…

信息论 · 计算机科学 2023-07-19 Nikhil Krishnan , Dror Baron

Efficient key-value (KV) cache management is crucial for the practical deployment of large language models (LLMs), yet existing compression techniques often incur a trade-off between performance degradation and computational overhead. We…

机器学习 · 计算机科学 2026-02-10 Jang-Hyun Kim , Dongyoon Han , Sangdoo Yun

Pushdown systems (PDSs) and recursive state machines (RSMs), which are linearly equivalent, are standard models for interprocedural analysis. Yet RSMs are more convenient as they (a) explicitly model function calls and returns, and (b)…

编程语言 · 计算机科学 2020-01-13 Krishnendu Chatterjee , Bernhard Kragl , Samarth Mishra , Andreas Pavlogiannis

With ever-increasing volumes of scientific data produced by HPC applications, significantly reducing data size is critical because of limited capacity of storage space and potential bottlenecks on I/O or networks in writing/reading or…

分布式、并行与集群计算 · 计算机科学 2019-01-08 Dingwen Tao , Sheng Di , Xin Liang , Zizhong Chen , Franck Cappello

Several emerging non-volatile (NV) memory technologies are rising as interesting alternatives to build the Last-Level Cache (LLC). Their advantages, compared to SRAM memory, are higher density and lower static power, but write operations…

硬件体系结构 · 计算机科学 2022-06-09 Carlos Escuin , Pablo Ibañez , Teresa Monreal , Jose M. Llaberia , Victor Viñals

Zero-shot Composed Image Retrieval (ZS-CIR) enables image search using a reference image and a text prompt without requiring specialized text-image composition networks trained on large-scale paired data. However, current ZS-CIR approaches…

计算机视觉与模式识别 · 计算机科学 2025-09-29 Osman Tursun , Sinan Kalkan , Simon Denman , Clinton Fookes

Error-bounded lossy compression has been a critical technique to significantly reduce the sheer amounts of simulation datasets for high-performance computing (HPC) scientific applications while effectively controlling the data distortion…

分布式、并行与集群计算 · 计算机科学 2024-08-23 Tripti Agarwal , Sheng Di , Jiajun Huang , Yafan Huang , Ganesh Gopalakrishnan , Robert Underwood , Kai Zhao , Xin Liang , Guanpeng Li , Franck Cappello
‹ 上一页 1 8 9 10 下一页 ›