English
Related papers

Related papers: Attention Residuals

200 papers

Large language models (LLMs) often struggle with strict memory, latency, and power demands. To meet these demands, various forms of dynamic sparsity have been proposed that reduce compute on an input-by-input basis. These methods improve…

Computation and Language · Computer Science 2024-04-09 Jordan Dotzel , Yash Akhauri , Ahmed S. AbouElhamayed , Carly Jiang , Mohamed Abdelfattah , Zhiru Zhang

The reasoning pattern of Large language models (LLMs) remains opaque, and Reinforcement learning (RL) typically applies uniform credit across an entire generation, blurring the distinction between pivotal and routine steps. This work…

Computation and Language · Computer Science 2025-10-16 Yang Li , Zhichen Dong , Yuhan Sun , Weixun Wang , Shaopan Xiong , Yijia Luo , Jiashun Liu , Han Lu , Jiamang Wang , Wenbo Su , Bo Zheng , Junchi Yan

Effective attention modules have played a crucial role in the success of Transformer-based large language models (LLMs), but the quadratic time and memory complexities of these attention modules also pose a challenge when processing long…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-06-07 Ao Sun , Weilin Zhao , Xu Han , Cheng Yang , Zhiyuan Liu , Chuan Shi , Maosong Sun

The attention mechanism is the computational core of modern Transformer architectures, but its quadratic complexity in the input sequence length is the bottleneck for large-scale inference. This has motivated a rapidly growing body of work…

Attention matrices are fundamental to transformer research, supporting a broad range of applications including interpretability, visualization, manipulation, and distillation. Yet, most existing analyses focus on individual attention heads…

Machine Learning · Computer Science 2026-01-27 Ido Andrew Atad , Itamar Zimerman , Shahar Katz , Lior Wolf

Modeling long sequences of user behaviors has emerged as a critical frontier in generative recommendation. However, existing solutions face a dilemma: linear attention mechanisms achieve efficiency at the cost of retrieval precision due to…

Information Retrieval · Computer Science 2026-02-23 Lei Xin , Yuhao Zheng , Ke Cheng , Changjiang Jiang , Zifan Zhang , Fanhu Zeng

Benefiting from the vigorous development of deep learning, many CNN-based image super-resolution methods have emerged and achieved better results than traditional algorithms. However, it is difficult for most algorithms to adaptively adjust…

Computer Vision and Pattern Recognition · Computer Science 2022-09-20 Yuxi Cai , Huicheng Lai , Zhenghong Jia

Attention layers -- which map a sequence of inputs to a sequence of outputs -- are core building blocks of the Transformer architecture which has achieved significant breakthroughs in modern artificial intelligence. This paper presents a…

Machine Learning · Computer Science 2023-07-24 Hengyu Fu , Tianyu Guo , Yu Bai , Song Mei

Despite the prevalence of the attention sink phenomenon in Large Language Models (LLMs), where initial tokens disproportionately monopolize attention scores, its structural origins remain elusive. This work provides a \textit{mechanistic…

Machine Learning · Computer Science 2026-05-08 Siquan Li , Kaiqi Jiang , Jiacheng Sun , Tianyang Hu

Very deep convolutional neural networks offer excellent recognition results, yet their computational expense limits their impact for many real-world applications. We introduce BlockDrop, an approach that learns to dynamically choose which…

Computer Vision and Pattern Recognition · Computer Science 2019-01-29 Zuxuan Wu , Tushar Nagarajan , Abhishek Kumar , Steven Rennie , Larry S. Davis , Kristen Grauman , Rogerio Feris

When tasks change over time, meta-transfer learning seeks to improve the efficiency of learning a new task via both meta-learning and transfer-learning. While the standard attention has been effective in a variety of settings, we question…

Machine Learning · Computer Science 2020-06-30 Jaesik Yoon , Gautam Singh , Sungjin Ahn

Linear attention methods offer Transformers $O(N)$ complexity but typically underperform standard softmax attention. We identify two fundamental limitations affecting these approaches: the restriction to convex combinations that only…

Machine Learning · Computer Science 2026-02-06 Jiecheng Lu , Xu Han , Yan Sun , Viresh Pati , Yubin Kim , Siddhartha Somani , Shihao Yang

Res-Tuning introduces a flexible and efficient paradigm for model tuning, showing that tuners decoupled from the backbone network can achieve performance comparable to traditional methods. Existing methods commonly construct the tuner as a…

Computer Vision and Pattern Recognition · Computer Science 2023-12-29 Chaojie Mao , Zeyinzi Jiang

Modeling long-range dependencies in sequential data remains a central challenge in machine learning. Transformers address this challenge through attention mechanisms, but their quadratic complexity with respect to sequence length limits…

Machine Learning · Computer Science 2026-05-14 Hoang-Quan Nguyen , Sankalp Pandey , Khoa Luu

To enhance the efficiency of the attention mechanism within large language models (LLMs), previous works primarily compress the KV cache or group attention heads, while largely overlooking redundancy between layers. Our comprehensive…

Computation and Language · Computer Science 2025-10-20 Yongyu Mu , Yuzhang Wu , Yuchun Fan , Chenglong Wang , Hengyu Li , Jiali Zeng , Qiaozhi He , Murun Yang , Fandong Meng , Jie Zhou , Tong Xiao , Jingbo Zhu

Masked diffusion models (MDMs), which leverage bidirectional attention and a denoising process, are narrowing the performance gap with autoregressive models (ARMs). However, their internal attention mechanisms remain under-explored. This…

Machine Learning · Computer Science 2026-01-14 Xin Dai , Pengcheng Huang , Zhenghao Liu , Shuo Wang , Yukun Yan , Chaojun Xiao , Yu Gu , Ge Yu , Maosong Sun

Practitioners have consistently observed three puzzling phenomena in transformer-based large language models (LLMs): attention sinks, value-state drains, and residual-state peaks, collectively referred to as extreme-token phenomena. These…

Machine Learning · Computer Science 2024-11-08 Tianyu Guo , Druv Pai , Yu Bai , Jiantao Jiao , Michael I. Jordan , Song Mei

The success of deep learning methods led to significant breakthroughs in 3-D point cloud processing tasks with applications in remote sensing. Existing methods utilize convolutions that have some limitations, as they assume a uniform input…

Computer Vision and Pattern Recognition · Computer Science 2021-02-23 Dimple A Shajahan , Mukund Varma T , Ramanathan Muthuganapathy

Residual Network (ResNet) is undoubtedly a milestone in deep learning. ResNet is equipped with shortcut connections between layers, and exhibits efficient training using simple first order algorithms. Despite of the great empirical success,…

Machine Learning · Computer Science 2019-11-05 Tianyi Liu , Minshuo Chen , Mo Zhou , Simon S. Du , Enlu Zhou , Tuo Zhao

Efforts to improve the adversarial robustness of convolutional neural networks have primarily focused on developing more effective adversarial training methods. In contrast, little attention was devoted to analyzing the role of…

Computer Vision and Pattern Recognition · Computer Science 2022-12-22 Shihua Huang , Zhichao Lu , Kalyanmoy Deb , Vishnu Naresh Boddeti