English
Related papers

Related papers: Rectified Sparse Attention

200 papers

Large language models (LLMs) demonstrate strong capabilities across a wide range of complex tasks and are increasingly deployed at scale, placing significant demands on inference efficiency. Prior work typically decomposes inference into…

Computation and Language · Computer Science 2026-04-21 Junhao Hu , Fangze Li , Mingtao Xu , Feifan Meng , Shiju Zhao , Tiancheng Hu , Ting Peng , Anmin Liu , Wenrui Huang , Chenxu Liu , Ziyue Hua , Tao Xie

Large language models (LLMs) face growing challenges in efficient generative inference due to the increasing memory demands of Key-Value (KV) caches, especially for long sequences. Existing eviction methods typically retain KV pairs with…

Computation and Language · Computer Science 2026-05-12 Yongqi An , Chang Lu , Kuan Zhu , Tao Yu , Chaoyang Zhao , Hong Wu , Ming Tang , Jinqiao Wang

Vector-based retrieval systems have become a common staple for academic and industrial search applications because they provide a simple and scalable way of extending the search to leverage contextual representations for documents and…

Information Retrieval · Computer Science 2023-04-04 Daniel Campos , ChengXiang Zhai

Event cameras provide sequential visual data with spatial sparsity and high temporal resolution, making them attractive for low-latency object detection. Existing asynchronous event-based neural networks realize this low-latency advantage…

Computer Vision and Pattern Recognition · Computer Science 2026-03-09 Haiqing Hao , Zhipeng Sui , Rong Zou , Zijia Dai , Nikola Zubić , Davide Scaramuzza , Wenhui Wang

Transformer-based architectures traditionally employ softmax to compute attention weights, which produces dense distributions over all tokens in a sequence. While effective in many settings, this density has been shown to be detrimental for…

Computation and Language · Computer Science 2026-03-03 Pavlo Vasylenko , Hugo Pitorro , André F. T. Martins , Marcos Treviso

Long-context LLMs increasingly rely on extended, reusable prefill prompts for agents and domain Q&A, pushing attention and KV-cache to become the dominant decode-time bottlenecks. While sparse attention reduces computation and transfer…

Machine Learning · Computer Science 2026-04-13 Chuxu Song , Zhencan Peng , Jiuqi Wei , Chuanhui Yang

Handling long-context sequences efficiently remains a significant challenge in large language models (LLMs). Existing methods for token selection in sequence extrapolation either employ a permanent eviction strategy or select tokens by…

Computation and Language · Computer Science 2025-02-21 Haoyu Wang , Tong Teng , Tianyu Guo , An Xiao , Duyu Tang , Hanting Chen , Yunhe Wang

Sparse autoencoders (SAEs) decompose language model representations into a sparse set of linear latent vectors. Recent works have improved SAEs using language model gradients, but these techniques require many expensive backward passes…

Machine Learning · Computer Science 2025-05-28 Matthew Chen , Joshua Engels , Max Tegmark

Large language models (LLMs) rely on key-value (KV) caches for efficient autoregressive decoding; however, cache size grows linearly with context length and model depth, becoming a major bottleneck in long-context inference. Prior KV cache…

Machine Learning · Computer Science 2025-09-22 Dmitry Akulov , Mohamed Sana , Antonio De Domenico , Tareq Si Salem , Nicola Piovesan , Fadhel Ayed

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

This paper introduces DrDiff, a novel framework for long-text generation that overcomes the efficiency-quality trade-off through three core technologies. First, we design a dynamic expert scheduling mechanism that intelligently allocates…

Computation and Language · Computer Science 2025-10-14 Jusheng Zhang , Yijia Fan , Kaitong Cai , Zimeng Huang , Xiaofei Sun , Jian Wang , Chengpei Tang , Keze Wang

Edge acceleration for large language models is crucial for their widespread application; however, achieving fast attention inference and efficient decoding on resource-constrained edge accelerators remains challenging. This paper presents…

Hardware Architecture · Computer Science 2026-01-19 Junming Zhang , Qinyan Zhang , Huajun Sun , Feiyang Gao , Sheng Hu , Rui Nie , Xiangshui Miao

Sequence parallelism (SP) serves as a prevalent strategy to handle long sequences that exceed the memory limit of a single device. However, for linear sequence modeling methods like linear attention, existing SP approaches do not take…

Machine Learning · Computer Science 2025-05-19 Weigao Sun , Zhen Qin , Dong Li , Xuyang Shen , Yu Qiao , Yiran Zhong

This paper presents an efficient speech enhancement (SE) approach that reuses a processing block repeatedly instead of conventional stacking. Rather than increasing the number of blocks for learning deep latent representations, repeating a…

Audio and Speech Processing · Electrical Eng. & Systems 2026-04-01 Jangyeon Kim , Ui-Hyeop Shin , Jaehyun Ko , Hyung-Min Park

Transformer-based large language models (LLMs) excel in natural language processing tasks by capturing long-range dependencies through self-attention mechanisms. However, long-context modeling faces significant computational inefficiencies…

Computation and Language · Computer Science 2025-08-15 Shuhai Zhang , Zeng You , Yaofo Chen , Zhiquan Wen , Qianyue Wang , Zhijie Qiu , Yuanqing Li , Mingkui Tan

While Transformer self-attention offers strong parallelism, the Key-Value (KV) cache grows linearly with sequence length and becomes a bottleneck for inference efficiency. Multi-head latent attention was recently developed to compress the…

Machine Learning · Computer Science 2025-11-04 Keqi Deng , Philip C. Woodland

Visual attention helps achieve robust perception under noise, corruption, and distribution shifts in human vision, which are areas where modern neural networks still fall short. We present VARS, Visual Attention from Recurrent Sparse…

Computer Vision and Pattern Recognition · Computer Science 2022-06-14 Baifeng Shi , Yale Song , Neel Joshi , Trevor Darrell , Xin Wang

Recent diffusion models enable high-quality video generation, but suffer from slow runtimes. The large transformer-based backbones used in these models are bottlenecked by spatiotemporal attention. In this paper, we identify that a…

Computer Vision and Pattern Recognition · Computer Science 2026-03-06 Shai Yehezkel , Shahar Yadin , Noam Elata , Yaron Ostrovsky-Berman , Bahjat Kawar

Self-attention has become an important and widely used neural network component that helped to establish new state-of-the-art results for various applications, such as machine translation and automatic speech recognition (ASR). However, the…

Audio and Speech Processing · Electrical Eng. & Systems 2021-04-08 Niko Moritz , Takaaki Hori , Jonathan Le Roux

Scaling language models to long contexts is often bottlenecked by the size of the key-value (KV) cache. In deployed settings, long contexts are typically managed through compaction in token space via summarization. However, summarization…

Machine Learning · Computer Science 2026-05-28 Adam Zweiger , Xinghong Fu , Han Guo , Yoon Kim
‹ Prev 1 8 9 10 Next ›