English
Related papers

Related papers: Thin Keys, Full Values: Reducing KV Cache via Low-…

200 papers

Singular Value Decomposition (SVD) has recently seen a surge of interest as a simple yet powerful tool for large language models (LLMs) compression, with a growing number of works demonstrating 20-80% parameter reductions at minimal…

Machine Learning · Computer Science 2025-08-05 Zishan Shao , Yixiao Wang , Qinsi Wang , Ting Jiang , Zhixu Du , Hancheng Ye , Danyang Zhuo , Yiran Chen , Hai Li

The transformer's attention mechanism has revolutionized AI and machine learning, with its efficient computation being crucial to its performance. However, calculating attention involves matrix operations interspersed with softmax…

Machine Learning · Computer Science 2025-05-21 Kosmas Alexandridis , Vasileios Titopoulos , Giorgos Dimitrakopoulos

The Key-Value (KV) cache introduces substantial memory overhead during large language model (LLM) inference. Although existing vector quantization (VQ) methods reduce KV cache usage and provide flexible representational capacity across…

Computation and Language · Computer Science 2025-10-08 Dingyu Yao , Chenxu Yang , Zhengyang Tong , Zheng Lin , Wei Liu , Jian Luan , Weiping Wang

In modern large language models (LLMs), increasing the context length is crucial for improving comprehension and coherence in long-context, multi-modal, and retrieval-augmented language generation. While many recent transformer models…

Computation and Language · Computer Science 2025-01-24 Heejun Lee , Geon Park , Youngwan Lee , Jaduk Suh , Jina Kim , Wonyoung Jeong , Bumsik Kim , Hyemin Lee , Myeongjae Jeon , Sung Ju Hwang

A fundamental challenge in Visual Autoregressive models is the substantial memory overhead required during inference to store previously generated representations. Despite various attempts to mitigate this issue through compression…

Machine Learning · Computer Science 2026-01-26 Yang Cao , Xiaoyu Li , Yekun Ke , Yingyu Liang , Zhenmei Shi , Zhao Song

Large language models have shown exceptional capabilities in a wide range of tasks, such as text generation and video generation, among others. However, due to their massive parameter count, these models often require substantial storage…

Machine Learning · Computer Science 2024-10-18 Qian Tao , Wenyuan Yu , Jingren Zhou

Transformers have demonstrated remarkable success across vision, language, and video. Yet, increasing task complexity has led to larger models and more tokens, raising the quadratic cost of self-attention and the overhead of GPU memory…

Computer Vision and Pattern Recognition · Computer Science 2025-08-04 Joonmyung Choi , Sanghyeok Lee , Byungoh Ko , Eunseo Kim , Jihyung Kil , Hyunwoo J. Kim

Vision-language models (VLMs) rely on long visual token sequences for visual understanding, making the prefill stage expensive in both computation and memory. Most existing pruning methods follow an absolute-ranking paradigm, assigning…

Computer Vision and Pattern Recognition · Computer Science 2026-05-29 Geng Li , Guohao Chen , Ting Chen , Shilin Shan , Kuangji Zuo , Bofan Lyu , Tuo An , Gen Li , Jianfei Yang

Vector Quantization (VQ) is an appealing model compression method to obtain a tiny model with less accuracy loss. While methods to obtain better codebooks and codes under fixed clustering dimensionality have been extensively studied,…

Computer Vision and Pattern Recognition · Computer Science 2022-11-22 Zezhou Zhu , Yucong Zhou , Zhao Zhong

KV caches, typically used only to speed up autoregressive decoding, encode contextual information that can be reused for downstream tasks at no extra cost. We propose treating the KV cache as a lightweight representation, eliminating the…

Computation and Language · Computer Science 2026-01-29 Zeyu Xing , Xing Li , Hui-Ling Zhen , Mingxuan Yuan , Sinno Jialin Pan

Linear-attention models that compress the entire input sequence into a fixed-size recurrent state offer an efficient alternative to Transformers, but their finite memory induces forgetfulness that harms retrieval-intensive tasks. To…

Computation and Language · Computer Science 2025-10-27 Mutian He , Philip N. Garner

Transformers have revolutionized deep learning in numerous fields, including natural language processing, computer vision, and audio processing. Their strength lies in their attention mechanism, which allows for the discovering of complex…

Machine Learning · Computer Science 2024-04-02 Uladzislau Yorsh , Martin Holeňa , Ondřej Bojar , David Herel

To improve the robustness of transformer neural networks used for temporal-dynamics prediction of chaotic systems, we propose a novel attention mechanism called easy attention which we demonstrate in time-series reconstruction and…

Machine Learning · Computer Science 2025-06-05 Marcial Sanchis-Agudo , Yuning Wang , Roger Arnau , Luca Guastoni , Jasmin Lim , Karthik Duraisamy , Ricardo Vinuesa

Unneeded elements in the attention's context degrade performance. We introduce Selective Attention, a simple parameter-free change to the standard attention mechanism which reduces attention to unneeded elements. Selective attention…

Computation and Language · Computer Science 2025-04-25 Yaniv Leviathan , Matan Kalman , Yossi Matias

Despite the significant success of large language models (LLMs), their extensive memory requirements pose challenges for deploying them in long-context token generation. The substantial memory footprint of LLM decoders arises from the…

Machine Learning · Computer Science 2024-02-12 Amir Zandieh , Insu Han , Vahab Mirrokni , Amin Karbasi

Key-Value (KV) cache plays a crucial role in accelerating inference in large language models (LLMs) by storing intermediate attention states and avoiding redundant computation during autoregressive generation. However, its memory footprint…

Machine Learning · Computer Science 2026-04-14 Yuzhen Mao , Qitong Wang , Martin Ester , Ke Li

Quantizing the key-value (KV) cache is a promising strategy for improving the inference efficiency of large language models (LLMs). However, aggressive quantization to very low precision (e.g., 2 bits) introduces significant errors in the…

Machine Learning · Computer Science 2025-10-08 Utkarsh Saxena , Kaushik Roy

Attention is a core component of transformer architecture, whether encoder-only, decoder-only, or encoder-decoder model. However, the standard softmax attention often produces noisy probability distribution, which can impair effective…

Computation and Language · Computer Science 2025-11-11 Dhananjay Ram , Wei Xia , Stefano Soatto

Although Transformers have successfully transitioned from their language modelling origins to image-based applications, their quadratic computational complexity remains a challenge, particularly for dense prediction. In this paper we…

Computer Vision and Pattern Recognition · Computer Science 2022-08-30 Yutong Xie , Jianpeng Zhang , Yong Xia , Anton van den Hengel , Qi Wu

Generating long sequences of tokens given a long-context input is a very compute-intensive inference scenario for large language models (LLMs). One prominent inference speed-up approach is to construct a smaller key-value (KV) cache,…

Computation and Language · Computer Science 2025-03-04 Fangyuan Xu , Tanya Goyal , Eunsol Choi
‹ Prev 1 8 9 10 Next ›