English
Related papers

Related papers: Fast-weight Product Key Memory

200 papers

Long-term conversational agents need memory systems that capture relationships between events, not merely isolated facts, to support temporal reasoning and multi-hop question answering. Current approaches face a fundamental trade-off: flat…

Computation and Language · Computer Science 2026-04-24 Buqiang Xu , Yijun Chen , Jizhan Fang , Ruobin Zhong , Yunzhi Yao , Yuqi Zhu , Lun Du , Shumin Deng

Scaling Large Language Models (LLMs) typically relies on increasing the number of parameters or test-time computations to boost performance. However, these strategies are impractical for edge device deployment due to limited RAM and NPU…

Machine Learning · Computer Science 2026-02-04 Ning Ding , Fangcheng Liu , Kyungrae Kim , Linji Hao , Kyeng-Hun Lee , Hyeonmok Ko , Yehui Tang

Quantization is a powerful tool to improve large language model (LLM) inference efficiency by utilizing more energy-efficient low-precision datapaths and reducing memory footprint. However, accurately quantizing LLM weights and activations…

Hardware Architecture · Computer Science 2025-04-22 Coleman Hooper , Charbel Sakr , Ben Keller , Rangharajan Venkatesan , Kurt Keutzer , Sophia Shao , Brucek Khailany

A critical approach for efficiently deploying computationally demanding large language models (LLMs) is Key-Value (KV) caching. The KV cache stores key-value states of previously generated tokens, significantly reducing the need for…

Computation and Language · Computer Science 2024-09-10 Akide Liu , Jing Liu , Zizheng Pan , Yefei He , Gholamreza Haffari , Bohan Zhuang

The quadratic time and memory complexity inherent to self-attention mechanisms, with respect to sequence length, presents a critical computational bottleneck in the training and deployment of large-scale Transformer-based language models.…

Machine Learning · Computer Science 2024-03-19 Praneeth Kacham , Vahab Mirrokni , Peilin Zhong

Large language model (LLM) agents require long-term memory to leverage information from past interactions. However, existing memory systems often face a fidelity--efficiency trade-off: raw dialogue histories are expensive, while flat facts…

Computation and Language · Computer Science 2026-05-26 Wentao Qiu , Haotian Hu , Fanyi Wang , Jinwei Kong , Yu Zhang

The emergence of large language models (LLMs) like GPT-4 has revolutionized natural language processing (NLP), enabling diverse, complex tasks. However, extensive token counts lead to high computational and financial burdens. To address…

Computation and Language · Computer Science 2025-03-12 Yun-Hao Cao , Yangsong Wang , Shuzheng Hao , Zhenxing Li , Chengjun Zhan , Sichao Liu , Yi-Qi Hu

The Softmax function is used in the final layer of nearly all existing sequence-to-sequence models for language generation. However, it is usually the slowest layer to compute which limits the vocabulary size to a subset of most frequent…

Computation and Language · Computer Science 2019-03-25 Sachin Kumar , Yulia Tsvetkov

Large Language Models struggle with memory demands from the growing Key-Value (KV) cache as context lengths increase. Existing compression methods homogenize head dimensions or rely on attention-guided token pruning, often sacrificing…

Computation and Language · Computer Science 2025-06-16 Xiaoran Liu , Siyang He , Qiqi Wang , Ruixiao Li , Yuerong Song , Zhigeng Liu , Linlin Li , Qun Liu , Zengfeng Huang , Qipeng Guo , Ziwei He , Xipeng Qiu

This study investigates the mechanisms and factors influencing memorization in fine-tuned large language models (LLMs), with a focus on the medical domain due to its privacy-sensitive nature. We examine how different aspects of the…

Computation and Language · Computer Science 2025-08-06 Danil Savine

Large language models (LLM) have achieved remarkable performance across a wide range of tasks. However, their substantial parameter sizes pose significant challenges for deployment on edge devices with limited computational and memory…

Computation and Language · Computer Science 2025-12-16 Yu-Chen Lu , Sheng-Feng Yu , Hui-Hsien Weng , Pei-Shuo Wang , Yu-Fang Hu , Liang Hung-Chun , Hung-Yueh Chiang , Kai-Chiang Wu

We propose a simple modification to the conventional attention mechanism applied by Transformers: Instead of quantifying pairwise query-key similarity with scaled dot-products, we quantify it with the logarithms of scaled dot-products of…

Machine Learning · Computer Science 2024-04-30 Franz A. Heinsen

Despite significant advancements in large language models (LLMs), the rapid and frequent integration of small-scale experiences, such as interactions with surrounding objects, remains a substantial challenge. Two critical factors in…

Computation and Language · Computer Science 2025-02-24 Yu Wang , Xinshuang Liu , Xiusi Chen , Sean O'Brien , Junda Wu , Julian McAuley

Large language models (LLMs) demonstrate remarkable capabilities but face substantial serving costs due to their high memory demands, with the key-value (KV) cache being a primary bottleneck. State-of-the-art KV cache compression…

Machine Learning · Computer Science 2025-09-03 Yanqi Zhang , Yuwei Hu , Runyuan Zhao , John C. S. Lui , Haibo Chen

Large language models (LLMs) can now handle longer sequences of tokens, enabling complex tasks like book understanding and generating lengthy novels. However, the key-value (KV) cache required for LLMs consumes substantial memory as context…

Machine Learning · Computer Science 2024-11-13 Haojie Duanmu , Zhihang Yuan , Xiuhong Li , Jiangfei Duan , Xingcheng Zhang , Dahua Lin

Large Language Models (LLMs) face challenges for on-device inference due to high memory demands. Traditional methods to reduce memory usage often compromise performance and lack adaptability. We propose FlexInfer, an optimized offloading…

Operating Systems · Computer Science 2025-03-07 Hongchao Du , Shangyu Wu , Arina Kharlamova , Nan Guan , Chun Jason Xue

Generative recommendation (GenRec) models typically model user behavior via full attention, but scaling to lifelong sequences is hindered by prohibitive computational costs and noise accumulation from stochastic interactions. To address…

Information Retrieval · Computer Science 2026-02-16 Yixiao Chen , Yuan Wang , Yue Liu , Qiyao Wang , Ke Cheng , Xin Xu , Juntong Yan , Shuojin Yang , Menghao Guo , Jun Zhang , Huan Yu , Jie Jiang

Large language models (LLMs) have shown remarkable performance in complex reasoning tasks, but their efficiency is hindered by the substantial memory and computational costs associated with generating lengthy tokens. In this paper, we…

Computation and Language · Computer Science 2025-09-24 Jintian Zhang , Yuqi Zhu , Mengshu Sun , Yujie Luo , Shuofei Qiao , Lun Du , Da Zheng , Huajun Chen , Ningyu Zhang

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

Reinforcement Learning (RL) has become essential for eliciting complex reasoning capabilities in Large Language Models (LLMs). However, the substantial memory overhead of storing Key-Value (KV) caches during long-horizon rollouts acts as a…

Machine Learning · Computer Science 2026-03-31 Sijia Luo , Xiaokang Zhang , Yuxuan Hu , Bohan Zhang , Ke Wang , Jinbo Su , Mengshu Sun , Lei Liang , Jing Zhang