English
Related papers

Related papers: One Pass Streaming Algorithm for Super Long Token …

200 papers

Deploying Large Language Models (LLMs) in streaming applications such as multi-round dialogue, where long interactions are expected, is urgently needed but poses two major challenges. Firstly, during the decoding stage, caching previous…

Computation and Language · Computer Science 2024-04-09 Guangxuan Xiao , Yuandong Tian , Beidi Chen , Song Han , Mike Lewis

As Large Language Models (LLMs) scale to million-token contexts, traditional Mechanistic Interpretability techniques for analyzing attention scale quadratically with context length, demanding terabytes of memory beyond 100,000 tokens. We…

Computation and Language · Computer Science 2026-02-03 J Rosser , José Luis Redondo García , Gustavo Penha , Konstantina Palla , Hugues Bouchard

Large language models (LLMs) have achieved impressive success, but their high memory requirements present challenges for long-context token generation. In this paper we study the streaming complexity of attention approximation, a key…

Machine Learning · Computer Science 2026-03-25 Ekaterina Kochetkova , Kshiteej Sheth , Insu Han , Amir Zandieh , Michael Kapralov

We present an approximate attention mechanism named HyperAttention to address the computational challenges posed by the growing complexity of long contexts used in Large Language Models (LLMs). Recent work suggests that in the worst-case…

Machine Learning · Computer Science 2023-12-04 Insu Han , Rajesh Jayaram , Amin Karbasi , Vahab Mirrokni , David P. Woodruff , Amir Zandieh

The quadratic computational complexity of the attention mechanism in current Large Language Models (LLMs) renders inference with long contexts prohibitively expensive. To address this challenge, various approaches aim to retain critical…

Computation and Language · Computer Science 2024-12-09 Hongyin Tang , Di Xiu , Lanrui Wang , Xiurui Geng , Jingang Wang , Xunliang Cai

Despite rapid advancements in lifelong learning (LLL) research, a large body of research mainly focuses on improving the performance in the existing \textit{static} continual learning (CL) setups. These methods lack the ability to succeed…

Machine Learning · Computer Science 2023-01-30 Soumya Banerjee , Vinay Kumar Verma , Vinay P. Namboodiri

Standard Large Language Models (LLMs) struggle with handling dialogues with long contexts due to efficiency and consistency issues. According to our observation, dialogue contexts are highly structured, and the special token of…

Computation and Language · Computer Science 2024-11-05 Jia-Nan Li , Quan Tu , Cunli Mao , Zhengtao Yu , Ji-Rong Wen , Rui Yan

Finding dense subgraphs is a fundamental algorithmic tool in data mining, community detection, and clustering. In this problem, one aims to find an induced subgraph whose edge-to-vertex ratio is maximized. We study the directed case of this…

Data Structures and Algorithms · Computer Science 2023-11-21 Slobodan Mitrović , Theodore Pan

Video Large Language Models (Video-LLMs) excel at understanding videos in-context, provided they have full access to the video when answering queries. However, these models face challenges in streaming scenarios where hour-long videos must…

Computer Vision and Pattern Recognition · Computer Science 2025-10-21 Vaggelis Dorovatas , Soroush Seifi , Gunshi Gupta , Rahaf Aljundi

Approximating the length of the longest increasing sequence (LIS) of an array is a well-studied problem. We study this problem in the data stream model, where the algorithm is allowed to make a single left-to-right pass through the array…

Data Structures and Algorithms · Computer Science 2013-04-16 Michael Saks , C. Seshadhri

Attention-based models have been gaining popularity recently for their strong performance demonstrated in fields such as machine translation and automatic speech recognition. One major challenge of attention-based models is the need of…

Computation and Language · Computer Science 2020-11-17 Ching-Feng Yeh , Yongqiang Wang , Yangyang Shi , Chunyang Wu , Frank Zhang , Julian Chan , Michael L. Seltzer

In this paper, we propose \textbf{Superlinear attention}, a fully trainable multi-step attention architecture that achieves subquadratic complexity for long sequences while preserving \textbf{random context access} (a.k.a.\ structural…

Machine Learning · Computer Science 2026-01-27 Yufeng Huang

We consider the classic Euclidean $k$-median and $k$-means objective on data streams, where the goal is to provide a $(1+\varepsilon)$-approximation to the optimal $k$-median or $k$-means solution, while using as little memory as possible.…

Data Structures and Algorithms · Computer Science 2023-10-05 Vincent Cohen-Addad , David P. Woodruff , Samson Zhou

Deploying long-context large language models (LLMs) is essential but poses significant computational and memory challenges. Caching all Key and Value (KV) states across all attention heads consumes substantial memory. Existing KV cache…

Computation and Language · Computer Science 2024-10-15 Guangxuan Xiao , Jiaming Tang , Jingwei Zuo , Junxian Guo , Shang Yang , Haotian Tang , Yao Fu , Song Han

Online video understanding is essential for applications like public surveillance and AI glasses. However, applying Multimodal Large Language Models (MLLMs) to this domain is challenging due to the large number of video frames, resulting in…

Computer Vision and Pattern Recognition · Computer Science 2025-12-16 Xinqi Jin , Hanxun Yu , Bohan Yu , Kebin Liu , Jian Liu , Keda Tao , Yixuan Pei , Huan Wang , Fan Dang , Jiangchuan Liu , Weiqiang Wang

Streaming algorithms are generally judged by the quality of their solution, memory footprint, and computational complexity. In this paper, we study the problem of maximizing a monotone submodular function in the streaming setting with a…

Machine Learning · Computer Science 2019-05-14 Ehsan Kazemi , Marko Mitrovic , Morteza Zadimoghaddam , Silvio Lattanzi , Amin Karbasi

Unlike offline processing, streaming video vision-language models face two fundamental constraints: causality and accumulation. Causality prevents access to future frames that offline methods exploit, while accumulation causes tokens to…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Xueyi Chen , Keda Tao , Kele Shao , Huan Wang

Long-context decoding in LLMs is IO-bound: each token re-reads an ever-growing KV cache. Prior accelerations cut bytes via compression, which lowers fidelity, or selection/eviction, which restricts what remains accessible, and both can…

Machine Learning · Computer Science 2026-04-02 Jinghan Yao , Sam Adé Jacobs , Walid Krichene , Masahiro Tanaka , Dhabaleswar K Panda

Scaling the context length of large language models (LLMs) offers significant benefits but is computationally expensive. This expense stems primarily from the self-attention mechanism, whose $O(N^2)$ complexity with respect to sequence…

Computation and Language · Computer Science 2026-05-25 Xinghao Wang , Pengyu Wang , Dong Zhang , Chenkun Tan , Shaojun Zhou , Zhaoxiang Liu , Shiguo Lian , Fangxu Liu , Kai Song , Xipeng Qiu

Linear attention has recently gained significant attention for long-context inference due to its constant decoding cost with respect to context length. However, existing serving systems typically serve linear attention by recurrently…

Machine Learning · Computer Science 2026-05-20 Longwei Zou , Lin Zhong
‹ Prev 1 2 3 10 Next ›