English
Related papers

Related papers: Adaptive Layer Selection for Layer-Wise Token Prun…

200 papers

In many application domains such as computer vision, Convolutional Layers (CLs) are key to the accuracy of deep learning methods. However, it is often required to assemble a large number of CLs, each containing thousands of parameters, in…

Neural and Evolutionary Computing · Computer Science 2019-05-30 Ghouthi Boukli Hacene , Carlos Lassance , Vincent Gripon , Matthieu Courbariaux , Yoshua Bengio

Recent advances have explored visual token pruning to accelerate the inference of large vision-language models (LVLMs). However, existing methods often struggle to balance token importance and diversity: importance-based methods tend to…

Computer Vision and Pattern Recognition · Computer Science 2026-04-08 Zhaohong Huang , Wenjing Liu , Yuxin Zhang , Fei Chao , Rongrong Ji

Serving transformer language models with high throughput requires caching Key-Values (KVs) to avoid redundant computation during autoregressive generation. The memory footprint of KV caching is significant and heavily impacts serving costs.…

Machine Learning · Computer Science 2026-04-28 Anastasiia Filippova , David Grangier , Marco Cuturi , João Monteiro

Structured pruning is a commonly used convolutional neural network (CNN) compression approach. Pruning rate setting is a fundamental problem in structured pruning. Most existing works introduce too many additional learnable parameters to…

Computer Vision and Pattern Recognition · Computer Science 2023-09-26 Pucheng Zhai , Kailing Guo , Fang Liu , Xiaofen Xing , Xiangmin Xu

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

Recently, large language models (LLMs) have been able to handle longer and longer contexts. However, a context that is too long may cause intolerant inference latency and GPU memory usage. Existing methods propose mixed-precision…

Computation and Language · Computer Science 2025-04-01 Wei Tao , Bin Zhang , Xiaoyang Qu , Jiguang Wan , Jianzong Wang

Aligning general-purpose large language models (LLMs) to downstream tasks often incurs significant training adjustment costs. Prior research has explored various avenues to enhance alignment efficiency, primarily through minimal-data…

Computation and Language · Computer Science 2025-06-19 Hao Chen , Haoze Li , Zhiqing Xiao , Lirong Gao , Qi Zhang , Xiaomeng Hu , Ningtao Wang , Xing Fu , Junbo Zhao

Many-Shot In-Context Learning (ICL) has emerged as a promising paradigm, leveraging extensive examples to unlock the reasoning potential of Large Language Models (LLMs). However, existing methods typically rely on a predetermined, fixed…

Artificial Intelligence · Computer Science 2026-05-06 Jie Ou , Jinyu Guo , Shiyao Guo , Yuang Li , Ruiqi Wu , Zhaokun Wang , Wenyi Li , Wenhong Tian

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

Recently, Sharma et al. suggested a method called Layer-SElective-Rank reduction (LASER) which demonstrated that pruning high-order components of carefully chosen LLM's weight matrices can boost downstream accuracy -- without any…

Machine Learning · Computer Science 2025-10-24 Shiva Sreeram , Alaa Maalouf , Pratyusha Sharma , Daniela Rus

Various Large Language Models~(LLMs) from the Generative Pretrained Transformer(GPT) family have achieved outstanding performances in a wide range of text generation tasks. However, the enormous model sizes have hindered their practical use…

Computation and Language · Computer Science 2024-04-24 Hang Shao , Bei Liu , Bo Xiao , Ke Zeng , Guanglu Wan , Yanmin Qian

The deployment of large language models (LLMs) is often hindered by the extensive memory requirements of the Key-Value (KV) cache, especially as context lengths increase. Existing approaches to reduce the KV cache size involve either…

Computation and Language · Computer Science 2024-11-05 Alessio Devoto , Yu Zhao , Simone Scardapane , Pasquale Minervini

The efficiency of large vision-language models (LVLMs) is constrained by the computational bottleneck of the attention mechanism during the prefill phase and the memory bottleneck of fetching the key-value (KV) cache in the decoding phase,…

Computer Vision and Pattern Recognition · Computer Science 2024-12-19 Yefei He , Feng Chen , Jing Liu , Wenqi Shao , Hong Zhou , Kaipeng Zhang , Bohan Zhuang

Large Language Models(LLMs) have had a profound impact on AI applications, particularly in the domains of long-text comprehension and generation. KV Cache technology is one of the most widely used techniques in the industry. It ensures…

Computation and Language · Computer Science 2024-04-30 Qiaozhi He , Zhihua Wu

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

Long-context inference in large language models (LLMs) is increasingly constrained by the KV cache bottleneck: memory usage grows linearly with sequence length, while attention computation scales quadratically. Existing approaches address…

Computation and Language · Computer Science 2025-11-13 Huanxuan Liao , Yixing Xu , Shizhu He , Guanchen Li , Xuanwu Yin , Dong Li , Emad Barsoum , Jun Zhao , Kang Liu

Large Language Model (LLM) inference is increasingly constrained by memory bandwidth, with frequent access to the key-value (KV) cache dominating data movement. While attention sparsity reduces some memory traffic, the relevance of past…

Hardware Architecture · Computer Science 2025-09-16 Yunhua Fang , Rui Xie , Asad Ul Haq , Linsen Ma , Kaoutar El Maghraoui , Naigang Wang , Meng Wang , Liu Liu , Tong Zhang

Large Vision-Language Models (LVLMs) rely on dense visual tokens to capture fine-grained visual information, but processing all these tokens incurs substantial computational and memory overhead during inference. To address this issue, we…

Machine Learning · Computer Science 2026-03-24 Xu Li , Yi Zheng , Yuxuan Liang , Zhe Liu , Xiaolei Chen , Haotian Chen , Rui Zhu , Xiangyang Xue

We present Adaptive Soft Rolling KV Freeze with Entropy-Guided Recovery (ASR-KF-EGR), a training-free inference-time framework for efficient large language model generation. Our method introduces a reversible soft-freeze mechanism that…

Machine Learning · Computer Science 2025-12-15 Adilet Metinov , Gulida M. Kudakeeva , Bolotbek uulu Nursultan , Gulnara D. Kabaeva

Large language models (LLMs) utilize key-value (KV) cache to store historical information during sequence processing. The size of KV cache grows linearly as the length of the sequence extends, which seriously affects memory usage and…

Computation and Language · Computer Science 2026-01-16 Yijun Liu , Yixuan Wang , Yuzhuang Xu , Shiyu Ji , Yang Xu , Qingfu Zhu , Wanxiang Che