English
Related papers

Related papers: RCMHA: Relative Convolutional Multi-Head Attention…

200 papers

Large Language Models (LLMs) need to adapt to the continuous changes in data, tasks, and user preferences. Due to their massive size and the high costs associated with training, LLMs are not suitable for frequent retraining. However,…

Computation and Language · Computer Science 2024-12-11 Dongfang Li , Zetian Sun , Xinshuo Hu , Baotian Hu , Min Zhang

We present a Transformer architecture for long-context language modeling that combines global attention with two biologically inspired components: chunked local attention and a gated FIFO memory mechanism. This unified attention block…

Machine Learning · Computer Science 2025-07-02 Ankit Kashyap

Sequence-to-sequence models with soft attention have been successfully applied to a wide variety of problems, but their decoding process incurs a quadratic time and space cost and is inapplicable to real-time sequence transduction. To…

Computation and Language · Computer Science 2018-02-26 Chung-Cheng Chiu , Colin Raffel

Large language model (LLM) agents increasingly rely on accumulated memory to solve long-horizon decision-making tasks. However, most existing approaches store memory in fixed representations and reuse it at a single or implicit level of…

Artificial Intelligence · Computer Science 2026-01-13 Sirui Liang , Pengfei Cao , Jian Zhao , Wenhao Teng , Xiangwen Liao , Jun Zhao , Kang Liu

Attention mechanisms, especially self-attention, have played an increasingly important role in deep feature representation for visual tasks. Self-attention updates the feature at each position by computing a weighted sum of features using…

Computer Vision and Pattern Recognition · Computer Science 2021-06-01 Meng-Hao Guo , Zheng-Ning Liu , Tai-Jiang Mu , Shi-Min Hu

Transformer-based deep learning models are increasingly deployed on energy, and DRAM bandwidth constrained devices such as laptops and gaming consoles, which presents significant challenges in meeting the latency requirements of the models.…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-08-26 Aadesh Deshmukh , Venkata Yaswanth Raparti , Samuel Hsu

Visual encoding constitutes the basis of large multimodal models (LMMs) in understanding the visual world. Conventional LMMs process images in fixed sizes and limited resolutions, while recent explorations in this direction are limited in…

Computer Vision and Pattern Recognition · Computer Science 2024-03-19 Ruyi Xu , Yuan Yao , Zonghao Guo , Junbo Cui , Zanlin Ni , Chunjiang Ge , Tat-Seng Chua , Zhiyuan Liu , Maosong Sun , Gao Huang

Large Language Models (LLMs) with hundreds of billions of parameters have transformed the field of machine learning. However, serving these models at inference time is both compute and memory intensive, where a single request can require…

This paper describes how to apply self-attention with relative positional encodings to the task of relation extraction. We propose to use the self-attention encoder layer together with an additional position-aware attention layer that takes…

Computation and Language · Computer Science 2018-07-10 Ivan Bilan , Benjamin Roth

When modeling a given type of data, we consider it to involve two key aspects: 1) identifying relevant elements (e.g., image pixels or textual words) to a central element, as in a convolutional receptive field, or to a query element, as in…

Machine Learning · Computer Science 2025-10-14 Hehe Fan , Yi Yang , Mohan Kankanhalli , Fei Wu

We explore deep autoregressive Transformer models in language modeling for speech recognition. We focus on two aspects. First, we revisit Transformer model configurations specifically for language modeling. We show that well configured…

Computation and Language · Computer Science 2019-09-25 Kazuki Irie , Albert Zeyer , Ralf Schlüter , Hermann Ney

The performance of convolutional neural networks (CNNs) can be improved by adjusting the interrelationship between channels with attention mechanism. However, attention mechanism in recent advance has not fully utilized spatial information…

Computer Vision and Pattern Recognition · Computer Science 2020-10-13 YuTao Shen , Ying Wen

The attention mechanism of the Listen, Attend and Spell (LAS) model requires the whole input sequence to calculate the attention context and thus is not suitable for online speech recognition. To deal with this problem, we propose…

Computation and Language · Computer Science 2020-05-04 Baiji Liu , Songjun Cao , Sining Sun , Weibin Zhang , Long Ma

The evolution of Large Vision-Language Models (LVLMs) has progressed from single to multi-image reasoning. Despite this advancement, our findings indicate that LVLMs struggle to robustly utilize information across multiple images, with…

Computer Vision and Pattern Recognition · Computer Science 2025-03-19 Xinyu Tian , Shu Zou , Zhaoyuan Yang , Jing Zhang

Excessive memory requirements of key and value features (KV-cache) present significant challenges in the autoregressive inference of large language models (LLMs), restricting both the speed and length of text generation. Approaches such as…

Computation and Language · Computer Science 2024-06-18 Vinay Joshi , Prashant Laddha , Shambhavi Sinha , Om Ji Omer , Sreenivas Subramoney

Following the success of dot-product attention in Transformers, numerous approximations have been recently proposed to address its quadratic complexity with respect to the input length. While these variants are memory and compute efficient,…

Computation and Language · Computer Science 2021-06-15 Ankit Gupta , Guy Dar , Shaya Goodman , David Ciprut , Jonathan Berant

Multi-head Latent Attention (MLA), the attention used in DeepSeek-V2/V3, jointly compresses keys and values into a low-rank latent and matches the H100 roofline almost perfectly. Its trained weights, however, expose only one decoding path -…

Machine Learning · Computer Science 2026-05-28 Fanxu Meng

The quadratic computational complexity of standard attention mechanisms presents a severe scalability bottleneck for LLMs in long-context scenarios. While hybrid attention mechanisms combining Full Attention (FA) and Sparse Attention (SA)…

Machine Learning · Computer Science 2026-04-10 Quantong Qiu , Zhiyi Hong , Yi Yang , Haitian Wang , Kebin Liu , Qingqing Dang , Juntao Li , Min Zhang

This paper introduces a novel approach to enhance the capabilities of Large Language Models (LLMs) in processing and understanding extensive text sequences, a critical aspect in applications requiring deep comprehension and synthesis of…

Computation and Language · Computer Science 2023-12-15 Kaiqiang Song , Xiaoyang Wang , Sangwoo Cho , Xiaoman Pan , Dong Yu

Large language model (LLM) agents are constrained by limited context windows, necessitating external memory systems for long-term information understanding. Current memory-augmented agents typically depend on pre-defined instructions and…

Computation and Language · Computer Science 2025-10-01 Yu Wang , Ryuichi Takanobu , Zhiqi Liang , Yuzhen Mao , Yuanzhe Hu , Julian McAuley , Xiaojian Wu