English
Related papers

Related papers: Streaming Attention Approximation via Discrepancy …

200 papers

Attention is the dominant source of latency during long-context LLM inference, an increasingly popular workload with reasoning models and RAG. We propose Kascade, a training-free sparse attention method that leverages known observations…

Machine Learning · Computer Science 2025-12-19 Dhruv Deshmukh , Saurabh Goyal , Nipun Kwatra , Ramachandran Ramjee

We present Lightning Attention, the first linear attention implementation that maintains a constant training speed for various sequence lengths under fixed memory consumption. Due to the issue with cumulative summation operations (cumsum),…

Computation and Language · Computer Science 2024-06-21 Zhen Qin , Weigao Sun , Dong Li , Xuyang Shen , Weixuan Sun , Yiran Zhong

Large Language Models (LLMs) are increasingly deployed in long-context tasks such as reasoning, code generation, and multi-turn dialogue. However, inference over extended contexts is bottlenecked by the Key-Value (KV) cache, whose memory…

Computation and Language · Computer Science 2026-05-21 Seonghwan Choi , Beomseok Kang , Dongwon Jo , Jae-Joon Kim

Key-value (KV) caching is critical for efficient inference in large language models (LLMs), yet its memory footprint scales linearly with context length, resulting in a severe scalability bottleneck. Existing approaches largely treat KV…

Computation and Language · Computer Science 2026-04-23 Gradwell Dzikanyanga , Weihao Yang , Hao Huang , Donglei Wu , Shihao Wang , Wen Xia , Sanjeeb K C

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

Understanding how Large Language Models (LLMs) process information from prompts remains a significant challenge. To shed light on this "black box," attention visualization techniques have been developed to capture neuron-level perceptions…

The computational difficulties of large language model (LLM) inference remain a significant obstacle to their widespread deployment. The need for many applications to support long input sequences and process them in large batches typically…

Machine Learning · Computer Science 2024-09-05 Luka Ribar , Ivan Chelombiev , Luke Hudlass-Galley , Charlie Blake , Carlo Luschi , Douglas Orr

Large language models (LLMs) now support extremely long context windows, but the quadratic complexity of vanilla attention results in significantly long Time-to-First-Token (TTFT) latency. Existing approaches to address this complexity…

Computation and Language · Computer Science 2025-09-04 Qianchao Zhu , Jiangfei Duan , Chang Chen , Siran Liu , Guanyu Feng , Xin Lv , Xiao Chuanfu , Dahua Lin , Chao Yang

Transformers have emerged as the architecture of choice for many state-of-the-art AI models, showcasing exceptional performance across a wide range of AI applications. However, the memory demands imposed by Transformers limit their ability…

Computation and Language · Computer Science 2023-11-28 Hao Liu , Matei Zaharia , Pieter Abbeel

In this paper, we propose a streaming model to distinguish voice queries intended for a smart-home device from background speech. The proposed model consists of multiple CNN layers with residual connections, followed by a stacked LSTM…

Audio and Speech Processing · Electrical Eng. & Systems 2020-07-21 Xiaosu Tong , Che-Wei Huang , Sri Harish Mallidi , Shaun Joseph , Sonal Pareek , Chander Chandak , Ariya Rastrow , Roland Maas

This paper addresses the problem of supervised video summarization by formulating it as a sequence-to-sequence learning problem, where the input is a sequence of original video frames, the output is a keyshot sequence. Our key idea is to…

Computer Vision and Pattern Recognition · Computer Science 2018-04-17 Zhong Ji , Kailin Xiong , Yanwei Pang , Xuelong Li

As the demand for processing extended textual data grows, the ability to handle long-range dependencies and maintain computational efficiency is more critical than ever. One of the key issues for long-sequence modeling using attention-based…

Computation and Language · Computer Science 2025-05-26 Aosong Feng , Rex Ying , Leandros Tassiulas

Vision-and-Language Navigation (VLN) in real-world settings requires agents to process continuous visual streams and generate actions with low latency grounded in language instructions. While Video-based Large Language Models (Video-LLMs)…

We introduce a new computational model for data streams: asymptotically exact streaming algorithms. These algorithms have an approximation ratio that tends to one as the length of the stream goes to infinity while the memory used by the…

Data Structures and Algorithms · Computer Science 2014-08-11 Marc Heinrich , Alexander Munteanu , Christian Sohler

Training large language models (LLMs) with increasingly long and varying sequence lengths introduces severe load imbalance challenges in large-scale data-parallel training. Recent frameworks attempt to mitigate these issues through data…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-09-30 Chang Chen , Tiancheng Chen , Jiangfei Duan , Qianchao Zhu , Zerui Wang , Qinghao Hu , Peng Sun , Xiuhong Li , Chao Yang , Torsten Hoefler

Large Language Models (LLMs) rely on the Key-Value (KV) Cache to store token history, enabling efficient decoding of tokens. As the KV-Cache grows, it becomes a major memory and computation bottleneck. However, there is an opportunity to…

Computation and Language · Computer Science 2026-05-18 Yash Akhauri , Ahmed F AbouElhamayed , Yifei Gao , Chi-Chih Chang , Sameh Gobriel , Nilesh Jain , Mohamed S. Abdelfattah

Key-Value (KV) cache remains a major bottleneck for deploying Large Language Models (LLMs) in long-generation tasks. Prior work often applies uniform compression across both prefill and decoding caches, but compressing the prefill cache…

Artificial Intelligence · Computer Science 2026-05-29 Soumyadeep Jana , Sagar Nishad , Sanasam Ranbir Singh

Large vision-language models (VLMs) typically process hundreds or thousands of visual tokens per image or video frame, incurring quadratic attention cost and substantial redundancy. Existing token reduction methods often ignore the textual…

Computer Vision and Pattern Recognition · Computer Science 2025-12-24 Kaitong Cai , Jusheng Zhang , Jing Yang , Yijia Fan , Pengtao Xie , Jian Wang , Keze Wang

We define the Streaming Communication model that combines the main aspects of communication complexity and streaming. We consider two agents that want to compute some function that depends on inputs that are distributed to each agent. The…

Computational Complexity · Computer Science 2016-09-23 Lucas Boczkowski , Iordanis Kerenidis , Frédéric Magniez

Recently, self-attention-based transformers and conformers have been introduced as alternatives to RNNs for ASR acoustic modeling. Nevertheless, the full-sequence attention mechanism is non-streamable and computationally expensive, thus…

Audio and Speech Processing · Electrical Eng. & Systems 2023-09-27 Keyu An , Shiliang Zhang
‹ Prev 1 4 5 6 7 8 10 Next ›