English
Related papers

Related papers: Dynamic Memory Compression: Retrofitting LLMs for …

200 papers

Scientific research faces high costs and inefficiencies with traditional methods, but the rise of deep learning and large language models (LLMs) offers innovative solutions. This survey reviews transformer-based LLM applications across…

Machine Learning · Computer Science 2025-09-16 Kaiyuan Tian , Linbo Qiao , Baihui Liu , Gongqingjian Jiang , Shanshan Li , Dongsheng Li

Transformers have become central to natural language processing and large language models, but their deployment at scale faces three major challenges. First, the attention mechanism requires massive matrix multiplications and frequent…

Hardware Architecture · Computer Science 2026-01-22 Xiaoxuan Yang , Peilin Chen , Tergel Molom-Ochir , Yiran Chen

Incorporating external knowledge in large language models (LLMs) enhances their utility across diverse applications, but existing methods have trade-offs. Retrieval-Augmented Generation (RAG) fetches evidence via similarity search, but key…

Computation and Language · Computer Science 2025-03-10 Giulio Corallo , Orion Weller , Fabio Petroni , Paolo Papotti

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

Large Language Models (LLMs) face computational inefficiencies and redundant processing when handling long context inputs, prompting a focus on compression techniques. While existing semantic vector-based compression methods achieve…

Computation and Language · Computer Science 2025-02-18 Shaoshen Chen , Yangning Li , Zishan Xu , Yinghui Li , Xin Su , Zifei Shan , Hai-tao Zheng

While Large Language Models (LLMs) demonstrate exceptional performance in surface-level text generation, their nature in handling complex multi-step reasoning tasks often remains one of ``statistical fitting'' rather than systematic logical…

Machine Learning · Computer Science 2026-01-27 Lianlei Shan , Han Chen , Yixuan Wang , Zhenjie Liu , Wei Li

We formalize the problem of prompt compression for large language models (LLMs) and present a framework to unify token-level prompt compression methods which create hard prompts for black-box models. We derive the distortion-rate function…

Machine Learning · Computer Science 2024-12-12 Alliot Nagle , Adway Girish , Marco Bondaschi , Michael Gastpar , Ashok Vardhan Makkuva , Hyeji Kim

Despite the recent success of Large Language Models (LLMs), it remains challenging to feed LLMs with long prompts due to the fixed size of LLM inputs. As a remedy, prompt compression becomes a promising solution by removing redundant tokens…

Computation and Language · Computer Science 2025-01-06 Ziyang Yu , Yuyu Liu

Large language models (LLMs) have demonstrated remarkable capabilities across various tasks. However, their widespread application is hindered by the resource-intensive decoding process. To address this challenge, current approaches have…

Computation and Language · Computer Science 2024-04-19 Ziqian Zeng , Jiahong Yu , Qianshi Pang , Zihao Wang , Huiping Zhuang , Hongen Shao , Xiaofeng Zou

Recent advances in Video Large Language Models (VLLMs) have achieved remarkable video understanding capabilities, yet face critical efficiency bottlenecks due to quadratic computational growth with lengthy visual token sequences of long…

Computer Vision and Pattern Recognition · Computer Science 2025-12-09 Yulin Li , Haokun Gui , Ziyang Fan , Junjie Wang , Bin Kang , Bin Chen , Zhuotao Tian

Retrieval-augmented generation (RAG) enhances large language models (LLMs) with external knowledge but incurs significant inference costs due to lengthy retrieved contexts. While context compression mitigates this issue, existing methods…

Computation and Language · Computer Science 2025-09-25 Shuyu Guo , Shuo Zhang , Zhaochun Ren

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

In large-language models, memory constraints in the Key-Value Cache (KVC) pose a challenge during inference. In this work, we propose FDC, a fast KV dimensionality compression system that eliminates the decompression overhead incurred in…

Machine Learning · Computer Science 2025-06-10 Zeyu Zhang , Haiying Shen

Modern data compression methods are slowly reaching their limits after 80 years of research, millions of papers, and wide range of applications. Yet, the extravagant 6G communication speed requirement raises a major open question for…

Information Theory · Computer Science 2025-05-01 Ziguang Li , Chao Huang , Xuliang Wang , Haibo Hu , Cole Wyeth , Dongbo Bu , Quan Yu , Wen Gao , Xingwu Liu , Ming Li

Multimodal Large Language Models (MLLMs) are becoming increasingly popular, while the high computational cost associated with multimodal data input, particularly from visual tokens, poses a significant challenge. Existing training-based…

Computer Vision and Pattern Recognition · Computer Science 2025-03-14 Xudong Tan , Peng Ye , Chongjun Tu , Jianjian Cao , Yaoxin Yang , Lin Zhang , Dongzhan Zhou , Tao Chen

We develop a new approach to tackle communication constraints in a distributed learning problem with a central server. We propose and analyze a new algorithm that performs bidirectional compression and achieves the same convergence rate as…

Machine Learning · Computer Science 2022-06-17 Constantin Philippenko , Aymeric Dieuleveut

Conventional video compression approaches use the predictive coding architecture and encode the corresponding motion information and residual information. In this paper, taking advantage of both classical architecture in the conventional…

Image and Video Processing · Electrical Eng. & Systems 2019-04-09 Guo Lu , Wanli Ouyang , Dong Xu , Xiaoyun Zhang , Chunlei Cai , Zhiyong Gao

Transformer-based large language models (LLM) have been widely used in language processing applications. However, due to the memory constraints of the devices, most of them restrict the context window. Even though recurrent models in…

Computation and Language · Computer Science 2025-02-07 Zifan He , Yingqi Cao , Zongyue Qin , Neha Prakriya , Yizhou Sun , Jason Cong

Computing-in-Memory (CIM) macros have gained popularity for deep learning acceleration due to their highly parallel computation and low power consumption. However, limited macro size and ADC precision introduce throughput and accuracy…

Hardware Architecture · Computer Science 2026-05-01 Ming-Han Lin , Tian-Sheuan Chang

Unlike autoregressive models, which generate one token at a time, dLLMs denoise a chunk of [MASK] tokens jointly and sample one or more tokens per step; despite enabling parallel decoding, this process incurs substantial computational cost…

Machine Learning · Computer Science 2026-05-19 Junyi Wu , Tianchen Zhao , Shaoqiu Zhang , Linfeng Zhang , Guohao Dai , Yu Wang
‹ Prev 1 8 9 10 Next ›