English
Related papers

Related papers: Context Compression for Auto-regressive Transforme…

200 papers

AI applications increasingly depend on long-context inference, where LLMs consume substantial context to support stronger reasoning. Common examples include retrieval-augmented generation, agent memory layers, and multi-agent orchestration.…

Machine Learning · Computer Science 2026-05-07 Yinsicheng Jiang , Yeqi Huang , Liang Cheng , Cheng Deng , Xuan Sun , Luo Mai

Key-Value (KV) cache has become a bottleneck of LLMs for long-context generation. Despite the numerous efforts in this area, the optimization for the decoding phase is generally ignored. However, we believe such optimization is crucial,…

Computation and Language · Computer Science 2025-06-04 Jialong Wu , Zhenglin Wang , Linhai Zhang , Yilong Lai , Yulan He , Deyu Zhou

While large language models (LLMs) excel at handling long-context sequences, they require substantial prefill computation and key-value (KV) cache, which can heavily burden computational efficiency and memory usage in both prefill and…

Machine Learning · Computer Science 2026-04-21 Dongwon Jo , Jiwon Song , Yulhwa Kim , Jae-Joon Kim

Entropy estimation is essential for the performance of learned image compression. It has been demonstrated that a transformer-based entropy model is of critical importance for achieving a high compression ratio, however, at the expense of a…

Image and Video Processing · Electrical Eng. & Systems 2024-02-28 A. Burakhan Koyuncu , Panqi Jia , Atanas Boev , Elena Alshina , Eckehard Steinbach

The quadratic complexity of self-attention in Transformer models remains a significant bottleneck for processing long sequences and deploying large language models efficiently. For this approach, there has been significant research into…

Computation and Language · Computer Science 2026-05-26 Spandan Pratyush

Tokenization efficiency plays a critical role in the performance and cost of large language models (LLMs), yet most models rely on static tokenizers optimized on general-purpose corpora. These tokenizers' fixed vocabularies often fail to…

Computation and Language · Computer Science 2025-10-27 Saibo Geng , Nathan Ranchin , Yunzhen yao , Maxime Peyrard , Chris Wendler , Michael Gastpar , Robert West

Recent large language models (LLMs) are rapidly extending their context windows, yet inference throughput lags due to increasing GPU memory and bandwidth demands. This is because the key-value (KV) cache, an intermediate structure storing…

The limited context window of contemporary large language models (LLMs) remains a primary bottleneck for their broader application across diverse domains. Although continual pre-training on long-context data offers a straightforward…

Computation and Language · Computer Science 2026-04-10 Wei Han , Pan Zhou , Soujanya Poria , Shuicheng Yan

The quadratic complexity of self-attention in Transformers has hindered the processing of long text. To alleviate this problem, previous works have proposed to sparsify the attention matrix, taking advantage of the observation that crucial…

Computation and Language · Computer Science 2024-01-12 Ziwei He , Jian Yuan , Le Zhou , Jingwen Leng , Bo Jiang

Token representation strategies within large-scale neural architectures often rely on contextually refined embeddings, yet conventional approaches seldom encode structured relationships explicitly within token interactions. Self-attention…

Computation and Language · Computer Science 2025-03-27 James Blades , Frederick Somerfield , William Langley , Susan Everingham , Maurice Witherington

The quadratic cost of attention in transformers motivated the development of efficient approaches: namely sparse and sliding window attention, convolutions and linear attention. Although these approaches result in impressive reductions in…

Machine Learning · Computer Science 2025-11-10 Jatin Prakash , Aahlad Puli , Rajesh Ranganath

Transformers predict over a representation of a sequence. The same data can be written as bytes, characters, or subword tokens, and these representations may be lossless. Yet, under a fixed context window, they need not expose the same…

Machine Learning · Computer Science 2026-05-14 Amirmehdi Jafari Fesharaki , Mohammadamin Rami , Aslan Tchamkerten

Long-context LLMs have enabled numerous downstream applications but also introduced significant challenges related to computational and memory efficiency. To address these challenges, optimizations for long-context inference have been…

Computation and Language · Computer Science 2025-03-12 Yucheng Li , Huiqiang Jiang , Qianhui Wu , Xufang Luo , Surin Ahn , Chengruidong Zhang , Amir H. Abdi , Dongsheng Li , Jianfeng Gao , Yuqing Yang , Lili Qiu

Recent advances in large language models (LLMs) have significantly boosted long-context processing. However, the increasing key-value (KV) cache size poses critical challenges to memory and execution efficiency. Most KV cache compression…

Computation and Language · Computer Science 2025-08-05 Xiaolin Lin , Jingcun Wang , Olga Kondrateva , Yiyu Shi , Bing Li , Grace Li Zhang

Fine-tuning provides an effective means to specialize pre-trained models for various downstream tasks. However, fine-tuning often incurs high memory overhead, especially for large transformer-based models, such as LLMs. While existing…

Computation and Language · Computer Science 2025-02-03 Antoine Simoulin , Namyong Park , Xiaoyi Liu , Grey Yang

Inference-time scaling trades efficiency for increased reasoning accuracy by generating longer or more parallel sequences. However, in Transformer LLMs, generation cost is bottlenecked by the size of the key-value (KV) cache, rather than…

Machine Learning · Computer Science 2025-11-10 Adrian Łańcucki , Konrad Staniszewski , Piotr Nawrot , Edoardo M. Ponti

The memory and computational demands of Key-Value (KV) cache present significant challenges for deploying long-context language models. Previous approaches attempt to mitigate this issue by selectively dropping tokens, which irreversibly…

Machine Learning · Computer Science 2024-07-24 Hanlin Tang , Yang Lin , Jing Lin , Qingsen Han , Shikuan Hong , Yiwu Yao , Gongyi Wang

Many large language model applications require conditioning on long contexts. Transformers typically support this by storing a large per-layer KV-cache of past activations, which incurs substantial memory overhead. A desirable alternative…

Computation and Language · Computer Science 2026-03-17 Yuri Kuratov , Matvey Kairov , Aydar Bulatov , Ivan Rodkin , Mikhail Burtsev

Transformer-based language models (LMs) are inefficient in long contexts. We propose Dodo, a solution for context compression. Instead of one vector per token in a standard transformer model, Dodo represents text with a dynamic number of…

Computation and Language · Computer Science 2024-12-10 Guanghui Qin , Corby Rosset , Ethan C. Chau , Nikhil Rao , Benjamin Van Durme

Large language models (LLMs) based on Transformer have been widely applied in the filed of natural language processing (NLP), demonstrating strong performance, particularly in handling short text tasks. However, when it comes to long…

Computation and Language · Computer Science 2025-07-09 Yijun Liu , Jinzheng Yu , Yang Xu , Zhongyang Li , Qingfu Zhu
‹ Prev 1 8 9 10 Next ›