English
Related papers

Related papers: HATA: Trainable and Hardware-Efficient Hash-Aware …

200 papers

We describe an efficient hierarchical method to compute attention in the Transformer architecture. The proposed attention mechanism exploits a matrix structure similar to the Hierarchical Matrix (H-Matrix) developed by the numerical…

Machine Learning · Computer Science 2021-07-27 Zhenhai Zhu , Radu Soricut

As the demand for long-context large language models (LLMs) increases, models with context windows of up to 128K or 1M tokens are becoming increasingly prevalent. However, long-context LLM inference is challenging since the inference speed…

Computation and Language · Computer Science 2024-08-28 Jiaming Tang , Yilong Zhao , Kan Zhu , Guangxuan Xiao , Baris Kasikci , Song Han

As long-context inference becomes central to large language models (LLMs), attention over growing key-value caches emerges as a dominant decoding bottleneck, motivating sparse attention for scalable inference. Fixed-budget top-k sparse…

Machine Learning · Computer Science 2026-02-06 Wentao Ni , Kangqi Zhang , Zhongming Yu , Oren Nelson , Mingu Lee , Hong Cai , Fatih Porikli , Jongryool Kim , Zhijian Liu , Jishen Zhao

Multi-head attention (MHA) has become the cornerstone of modern large language models, enhancing representational capacity through parallel attention heads. However, increasing the number of heads inherently weakens individual head…

Computation and Language · Computer Science 2025-10-28 Zhanchao Zhou , Xiaodong Chen , Haoxing Chen , Zhenzhong Lan , Jianguo Li

While the Self-Attention mechanism in the Transformer model has proven to be effective in many domains, we observe that it is less effective in more diverse settings (e.g. multimodality) due to the varying granularity of each token and the…

Computer Vision and Pattern Recognition · Computer Science 2024-06-06 Wayner Barrios , SouYoung Jin

Long-term memory is a cornerstone of human intelligence. Enabling AI to process lifetime-scale information remains a long-standing pursuit in the field. Due to the constraints of full-attention architectures, the effective context length of…

Computation and Language · Computer Science 2026-04-14 Yu Chen , Runkai Chen , Sheng Yi , Xinda Zhao , Xiaohong Li , Jianjin Zhang , Jun Sun , Chuanrui Hu , Yunyun Han , Lidong Bing , Yafeng Deng , Tianqiao Chen

Large Audio-Language Models (LALMs) often suffer from audio-textual attention imbalance, prioritizing text over acoustic information, particularly in the multi-modal fusion layers of the Transformer architecture. This bias hinders their…

Sound · Computer Science 2025-09-24 Junyu Wang , Ziyang Ma , Zhengding Luo , Tianrui Wang , Meng Ge , Xiaobao Wang , Longbiao Wang

Large Language Models (LLMs) encounter significant performance bottlenecks in long-sequence tasks due to the computational complexity and memory overhead inherent in the self-attention mechanism. To address these challenges, we introduce…

Artificial Intelligence · Computer Science 2026-02-17 Ziming Wang , Xiang Wang , Kailong Peng , Lang Qin , Juan Gabriel Kostelec , Christos Sourmpis , Axel Laborieux , Qinghai Guo

Large Language Models (LLMs) face significant computational bottlenecks during inference due to the quadratic complexity of self-attention mechanisms, particularly as context lengths increase. We introduce SpecAttn, a novel training-free…

Computation and Language · Computer Science 2025-11-03 Harsh Shah

In large language models built upon the Transformer architecture, recent studies have shown that inter-head interaction can enhance attention performance. Motivated by this, we propose Multi-head Explicit Attention (MEA), a simple yet…

Machine Learning · Computer Science 2026-01-28 Runyu Peng , Yunhua Zhou , Demin Song , Kai Lv , Bo Wang , Qipeng Guo , Xipeng Qiu

Disaggregated Large Language Model (LLM) inference has gained popularity as it separates the computation-intensive prefill stage from the memory-intensive decode stage, avoiding the prefill-decode interference and improving resource…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-02-07 Zeyu Zhang , Haiying Shen , Shay Vargaftik , Ran Ben Basat , Michael Mitzenmacher , Minlan Yu

The Hierarchical Kernel Transformer (HKT) is a multi-scale attention mechanism that processes sequences at L resolution levels via trainable causal downsampling, combining level-specific score matrices through learned convex weights. The…

Machine Learning · Computer Science 2026-04-13 Giansalvo Cirrincione

Large language model inference on Central Processing Units (CPU) is challenging due to the vast quantities of expensive Multiply-Add (MAD) matrix operations in the attention computations. In this paper, we argue that there is a rare gem in…

Machine Learning · Computer Science 2024-03-05 Tianyi Zhang , Jonah Wonkyu Yi , Bowen Yao , Zhaozhuo Xu , Anshumali Shrivastava

Long-context inference in LLMs faces the dual challenges of quadratic attention complexity and prohibitive KV cache memory. While token-level sparse attention offers superior accuracy, its indexing overhead is costly; block-level methods…

Computation and Language · Computer Science 2026-04-10 Yuxuan Hu , Jianchao Tan , Jiaqi Zhang , Wen Zan , Pingwei Sun , Yifan Lu , Yerui Sun , Yuchen Xie , Xunliang Cai , Jing Zhang

Large Language Models (LLMs) are widely used in generative applications such as chatting, code generation, and reasoning. However, many realworld workloads such as classification, question answering, recommendation, and text embedding rely…

Computation and Language · Computer Science 2025-11-13 Dinghong Song , Yuan Feng , Yiwei Wang , Shangye Chen , Cyril Guyot , Filip Blagojevic , Hyeran Jeon , Pengfei Su , Dong Li

Attention mechanisms in sequence to sequence models have shown great ability and wonderful performance in various natural language processing (NLP) tasks, such as sentence embedding, text generation, machine translation, machine reading…

Computation and Language · Computer Science 2018-08-14 Zehao Dou , Zhihua Zhang

Transformers with linear attention allow for efficient parallel training but can simultaneously be formulated as an RNN with 2D (matrix-valued) hidden states, thus enjoying linear-time inference complexity. However, linear attention…

Machine Learning · Computer Science 2024-08-28 Songlin Yang , Bailin Wang , Yikang Shen , Rameswar Panda , Yoon Kim

Large Language Models (LLMs) have become the central paradigm in artificial intelligence, yet the core computational primitive of attention has remained structurally unchanged. Local Linear Attention (LLA) is an attention mechanism derived…

Machine Learning · Computer Science 2026-05-29 Yifei Zuo , Dhruv Pai , Zhichen Zeng , Alec Dewulf , Shuming Hu , Zhaoran Wang

Recently, there has been growing interest in collecting reasoning-intensive pretraining data to improve LLMs' complex reasoning ability. Prior approaches typically rely on supervised classifiers to identify such data, which requires…

Computation and Language · Computer Science 2025-05-13 Kai Hua , Steven Wu , Ge Zhang , Ke Shen

The continual learning (CL) ability is vital for deploying large language models (LLMs) in the dynamic world. Existing methods devise the learning module to acquire task-specific knowledge with parameter-efficient tuning (PET) block and the…

Computation and Language · Computer Science 2024-06-07 Weixiang Zhao , Shilong Wang , Yulin Hu , Yanyan Zhao , Bing Qin , Xuanyu Zhang , Qing Yang , Dongliang Xu , Wanxiang Che