English
Related papers

Related papers: Budgeted Attention Allocation: Cost-Conditioned Co…

200 papers

Identifying words that impact a task's performance more than others is a challenge in natural language processing. Transformers models have recently addressed this issue by incorporating an attention mechanism that assigns greater attention…

Computation and Language · Computer Science 2023-03-15 Neşet Özkan Tan , Alex Yuxuan Peng , Joshua Bensemann , Qiming Bao , Tim Hartill , Mark Gahegan , Michael Witbrock

Self-attention is a key enabler of state-of-art accuracy for various transformer-based Natural Language Processing models. This attention mechanism calculates a correlation score for each word with respect to the other words in a sentence.…

Computation and Language · Computer Science 2022-04-18 Zheng Li , Soroush Ghodrati , Amir Yazdanbakhsh , Hadi Esmaeilzadeh , Mingu Kang

The attention mechanism forms the foundational blocks for transformer language models. Recent approaches show that scaling the model achieves human-level performance. However, with increasing demands for scaling and constraints on hardware…

Computation and Language · Computer Science 2024-07-16 Sai Sena Chinnakonduru , Astarag Mohapatra

Self-attention is central to the success of Transformer architectures; however, learning the query, key, and value projections from random initialization remains challenging and computationally expensive. In this paper, we propose two…

Computer Vision and Pattern Recognition · Computer Science 2026-05-18 Hongyi Pan , Emadeldeen Hamdan , Xin Zhu , Ahmet Enis Cetin , Ulas Bagci

Attention based language models have become a critical component in state-of-the-art natural language processing systems. However, these models have significant computational requirements, due to long training times, dense operations and…

Computation and Language · Computer Science 2021-06-11 Ivan Chelombiev , Daniel Justus , Douglas Orr , Anastasia Dietrich , Frithjof Gressmann , Alexandros Koliousis , Carlo Luschi

Transformer-based large language models (e.g., BERT and GPT) achieve great success, and fine-tuning, which tunes a pre-trained model on a task-specific dataset, is the standard practice to utilize these models for downstream tasks. However,…

Distributed, Parallel, and Cluster Computing · Computer Science 2023-12-19 Yuntao Gui , Xiao Yan , Peiqi Yin , Han Yang , James Cheng

How much information do NLP tasks really need from a transformer's attention mechanism at application-time (inference)? From recent work, we know that there is sparsity in transformers and that the floating-points within its computation can…

Computation and Language · Computer Science 2021-06-03 Tianchu Ji , Shraddhan Jain , Michael Ferdman , Peter Milder , H. Andrew Schwartz , Niranjan Balasubramanian

Transformer encoders are widely deployed in large-scale web services for natural language understanding tasks such as text classification, semantic retrieval, and content ranking. However, their high inference latency and memory consumption…

Machine Learning · Computer Science 2025-12-25 Zeli Su , Ziyin Zhang , Wenzheng Zhang , Zhou Liu , Guixian Xu , Wentao Zhang

With the rise of Transformer models in NLP and CV domain, Multi-Head Attention has been proven to be a game-changer. However, its expensive computation poses challenges to the model throughput and efficiency, especially for the long…

Image and Video Processing · Electrical Eng. & Systems 2024-04-12 Jiing-Ping Wang , Ming-Guang Lin , An-Yeu , Wu

Gating mechanisms have been widely utilized, from early models like LSTMs and Highway Networks to recent state space models, linear attention, and also softmax attention. Yet, existing literature rarely examines the specific effects of…

Computation and Language · Computer Science 2025-05-13 Zihan Qiu , Zekun Wang , Bo Zheng , Zeyu Huang , Kaiyue Wen , Songlin Yang , Rui Men , Le Yu , Fei Huang , Suozhi Huang , Dayiheng Liu , Jingren Zhou , Junyang Lin

Transformers trained on modular arithmetic exhibit sharp transitions between memorization, generalization, and collapse. We show that weight decay acts as a scalar empirical control parameter for these regimes, and introduce two cheap…

Machine Learning · Computer Science 2026-05-21 Lucky Verma

Increasingly expensive training of ever larger models such as Vision Transfomers motivate reusing the vast library of already trained state-of-the-art networks. However, their latency, high computational costs and memory demands pose…

Computer Vision and Pattern Recognition · Computer Science 2026-04-02 Uranik Berisha , Jens Mehnert , Alexandru Paul Condurache

Transformer-based models, such as BERT and GPT, have been widely adopted in natural language processing (NLP) due to their exceptional performance. However, recent studies show their vulnerability to textual adversarial attacks where the…

Computation and Language · Computer Science 2023-12-01 Lujia Shen , Yuwen Pu , Shouling Ji , Changjiang Li , Xuhong Zhang , Chunpeng Ge , Ting Wang

The attention mechanism of a transformer has a quadratic complexity, leading to high inference costs and latency for long sequences. However, attention matrices are mostly sparse, which implies that many entries may be omitted from…

Machine Learning · Computer Science 2025-11-25 Jeffrey Willette , Heejun Lee , Sung Ju Hwang

Transformer attention is typically implemented using softmax normalization, which enforces attention weights with unit sum normalization. While effective in many settings, this constraint can limit flexibility in controlling attention…

Computation and Language · Computer Science 2026-02-27 Jeongin Bae , Baeseong Park , Gunho Park , Minsub Kim , Joonhyung Lee , Junhee Yoo , Sunghyeon Woo , Jiwon Ryu , Se Jung Kwon , Dongsoo Lee

We investigate the integration of human-like working memory constraints into the Transformer architecture and implement several cognitively inspired attention variants, including fixed-width windows based and temporal decay based attention…

Computation and Language · Computer Science 2026-04-24 Pranava Madhyastha , Dagmar Adamcova

Pre-trained language models like BERT and its variants have recently achieved impressive performance in various natural language understanding tasks. However, BERT heavily relies on the global self-attention block and thus suffers large…

Computation and Language · Computer Science 2021-02-03 Zihang Jiang , Weihao Yu , Daquan Zhou , Yunpeng Chen , Jiashi Feng , Shuicheng Yan

Efficient inference on GPUs using large language models remains challenging due to memory bandwidth limitations, particularly during data transfers between High Bandwidth Memory (HBM) and SRAM in attention computations. Approximate…

Machine Learning · Computer Science 2025-06-06 Nirav Koley , Prajwal Singhania , Abhinav Bhatele

As LLM reasoning performance plateau, improving inference-time compute efficiency is crucial to mitigate overthinking and long thinking traces even for simple queries. Prior approaches including length regularization, adaptive routing, and…

Machine Learning · Computer Science 2026-04-15 Neharika Jali , Anupam Nayak , Gauri Joshi

Structured dilated attention has an appealing inference-time efficiency knob: it reduces the FLOPs of attention and the KV cache size by a factor of the dilation size D, while preserving long-range connectivity. While prior work studies it…

Machine Learning · Computer Science 2026-05-29 Xiuying Wei , Caglar Gulcehre