English
Related papers

Related papers: Overcoming Long-Context Limitations of State-Space…

200 papers

Sparse attention improves LLM inference efficiency by selecting a subset of key-value entries, but at the cost of potential accuracy degradation. In particular, omitting critical KV entries can induce substantial errors in model outputs.…

Machine Learning · Computer Science 2026-05-12 Mohsen Dehghankar , Abolfazl Asudeh

The emergence of long-context text applications utilizing large language models (LLMs) has presented significant scalability challenges, particularly in memory footprint. The linear growth of the Key-Value (KV) cache responsible for storing…

Computation and Language · Computer Science 2024-12-17 Hongxuan Zhang , Yao Zhao , Jiaqi Zheng , Chenyi Zhuang , Jinjie Gu , Guihai Chen

The recent surge of large language models (LLMs) highlights their ability to perform in-context learning, i.e., "learning" to perform a task from a few demonstrations in the context without any parameter updates. However, their capabilities…

Computation and Language · Computer Science 2023-07-07 Tianle Cai , Kaixuan Huang , Jason D. Lee , Mengdi Wang

The Transformer architecture model, based on self-attention and multi-head attention, has achieved remarkable success in offline end-to-end Automatic Speech Recognition (ASR). However, self-attention and multi-head attention cannot be…

Computation and Language · Computer Science 2022-10-03 Chendong Zhao , Jianzong Wang , Wen qi Wei , Xiaoyang Qu , Haoqian Wang , Jing Xiao

Self-attention model have shown its flexibility in parallel computation and the effectiveness on modeling both long- and short-term dependencies. However, it calculates the dependencies between representations without considering the…

Computation and Language · Computer Science 2019-02-18 Baosong Yang , Jian Li , Derek Wong , Lidia S. Chao , Xing Wang , Zhaopeng Tu

Existing large language models (LLMs) can only afford fix-sized inputs due to the input length limit, preventing them from utilizing rich long-context information from past inputs. To address this, we propose a framework, Language Models…

Computation and Language · Computer Science 2023-06-13 Weizhi Wang , Li Dong , Hao Cheng , Xiaodong Liu , Xifeng Yan , Jianfeng Gao , Furu Wei

Large Language Models (LLMs) are constrained by their inability to process lengthy inputs, resulting in the loss of critical historical information. To address this limitation, in this paper, we propose the Self-Controlled Memory (SCM)…

Computation and Language · Computer Science 2025-03-19 Bing Wang , Xinnian Liang , Jian Yang , Hui Huang , Shuangzhi Wu , Peihao Wu , Lu Lu , Zejun Ma , Zhoujun Li

Large language models with long context windows can answer complex questions directly from full-length academic, technical, and policy documents, but passing entire documents is often costly, slow, and can degrade answer quality while…

Scaling large language models to long contexts is challenging due to the quadratic computational cost of full attention. Mitigation approaches include KV-cache selection or compression techniques. We instead provide an effective and…

Machine Learning · Computer Science 2026-04-24 Yuzhen Mao , Michael Y. Li , Emily B. Fox

Recently, sparse autoencoders (SAEs) have emerged as a promising technique for interpreting activations in foundation models by disentangling features into a sparse set of concepts. However, identifying the optimal level of sparsity for…

Machine Learning · Computer Science 2026-04-17 Dongsheng Wang , Jinsen Zhang , Dawei Su , Hui Huang

Long-context modeling is one of the critical capabilities of language AI for digesting and reasoning over complex information pieces. In practice, long-context capabilities are typically built into a pre-trained language model~(LM) through…

Computation and Language · Computer Science 2024-10-15 Luyu Gao , Yunyi Zhang , Jamie Callan

Large language models (LLMs) encounter computational challenges during long-sequence inference, especially in the attention pre-filling phase, where the complexity grows quadratically with the prompt length. Previous efforts to mitigate…

Machine Learning · Computer Science 2025-03-03 Xunhao Lai , Jianqiao Lu , Yao Luo , Yiyuan Ma , Xun Zhou

State Space Models (SSMs) have recently enjoyed a rise to prominence in the field of deep learning for sequence modeling, especially as an alternative to Transformers. Their success stems from avoiding two well-known drawbacks of…

Machine Learning · Computer Science 2025-01-22 Stefano Rando , Luca Romani , Matteo Migliarini , Luca Franco , Denis Gudovskiy , Fabio Galasso

State space models (SSMs) have emerged as an efficient alternative to Transformer models for language modeling, offering linear computational complexity and constant memory usage as context length increases. However, despite their…

Computation and Language · Computer Science 2025-04-23 Zhifan Ye , Kejing Xia , Yonggan Fu , Xin Dong , Jihoon Hong , Xiangchi Yuan , Shizhe Diao , Jan Kautz , Pavlo Molchanov , Yingyan Celine Lin

Large Language Models (LLMs) with extended context lengths face significant computational challenges during the pre-filling phase, primarily due to the quadratic complexity of self-attention. Existing methods typically employ dynamic…

Machine Learning · Computer Science 2025-05-30 Yu Zhang , Dong Guo , Fang Wu , Guoliang Zhu , Dian Ding , Yiming Zhang

While sparse attention mitigates the computational bottleneck of long-context LLM training, its distributed training process exhibits extreme heterogeneity in both \textit{1)} sequence length and \textit{2)} sparsity sensitivity, leading to…

Machine Learning · Computer Science 2026-04-27 Hongtao Xu , Jianchao Tan , Yuxuan Hu , Pengju Lu , Hongyu Wang , Pingwei Sun , Yerui Sun , Yuchen Xie , Xunliang Cai , Mingzhen Li , Weile Jia

As an important part of speech recognition technology, automatic speech keyword recognition has been intensively studied in recent years. Such technology becomes especially pivotal under situations with limited infrastructures and…

Machine Learning · Computer Science 2019-07-11 Ruisen Luo , Tianran Sun , Chen Wang , Miao Du , Zuodong Tang , Kai Zhou , Xiaofeng Gong , Xiaomei Yang

Self-attention is a method of encoding sequences of vectors by relating these vectors to each-other based on pairwise similarities. These models have recently shown promising results for modeling discrete sequences, but they are non-trivial…

Computation and Language · Computer Science 2018-06-19 Matthias Sperber , Jan Niehues , Graham Neubig , Sebastian Stüker , Alex Waibel

Training causal transformers at extreme sequence lengths is bottlenecked by the quadratic time and memory of scaled dot-product attention (SDPA). In this work, we propose Lighthouse Attention, a training-only symmetrical selection-based…

Computation and Language · Computer Science 2026-05-08 Bowen Peng , Subho Ghosh , Jeffrey Quesnelle

We argue that neither transformers nor sub-quadratic architectures are well suited to training at long sequence lengths: the cost of processing the context is too expensive in the former, too inexpensive in the latter. Approaches such as…

Machine Learning · Computer Science 2025-07-08 Carles Gelada , Jacob Buckman , Sean Zhang , Txus Bach