English
Related papers

Related papers: Stability Implies Redundancy: Delta Attention Sele…

200 papers

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

Accelerating inference in Large Language Models (LLMs) is critical for real-time interactions, as they have been widely incorporated into real-world services. Speculative decoding, a fully algorithmic solution, has gained attention for…

Computation and Language · Computer Science 2025-02-11 Sukmin Cho , Sangjin Choi , Taeho Hwang , Jeongyeon Seo , Soyeong Jeong , Huije Lee , Hoyun Song , Jong C. Park , Youngjin Kwon

Large Language Models (LLMs) have demonstrated impressive performance on a range of Natural Language Processing (NLP) tasks. Unfortunately, the immense amount of computations and memory accesses required for LLM training makes them…

Machine Learning · Computer Science 2023-03-10 Guo Yang , Daniel Lo , Robert Mullins , Yiren Zhao

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

Modeling ultra-long user behavior sequences is pivotal for capturing evolving and lifelong interests in modern recommendation systems. However, deploying such models in real-time industrial environments faces a strict "Latency Wall",…

Information Retrieval · Computer Science 2026-02-13 Tianhe Lin , Ziwei Xiong , Baoyuan Ou , Yingjie Qin , Lai Xu , Xiaocheng Zhong , Yao Hu , Zhiyong Wang , Tao Zhou , Yubin Xu , Di Wu

Attention Residuals replace standard additive residual connections with learned softmax attention over previous layer outputs, enabling selective cross-layer routing. However, standard Attention Residuals still attend over cumulative hidden…

Machine Learning · Computer Science 2026-05-20 Cheng Luo , Zefan Cai , Junjie Hu

Large Language Models (LLMs) often rely on long chain-of-thought (CoT) reasoning to solve complex tasks. While effective, these trajectories are frequently inefficient, leading to high latency from excessive token generation, or unstable…

Large Language Models (LLMs) often struggle to maintain their original performance when faced with semantically coherent but task-irrelevant contextual information. Although prior studies have explored this issue using fixed-template or…

Computation and Language · Computer Science 2025-09-23 Yanbo Wang , Zixiang Xu , Yue Huang , Chujie Gao , Siyuan Wu , Jiayi Ye , Pin-Yu Chen , Xiuying Chen , Xiangliang Zhang

While Large Language Models (LLMs) demonstrate exceptional performance in surface-level text generation, their nature in handling complex multi-step reasoning tasks often remains one of ``statistical fitting'' rather than systematic logical…

Machine Learning · Computer Science 2026-01-27 Lianlei Shan , Han Chen , Yixuan Wang , Zhenjie Liu , Wei Li

While explicit Chain-of-Thought (CoT) equips Large Language Models (LLMs) with strong reasoning capabilities, it requires models to verbalize every intermediate step in text tokens, constraining the model thoughts to the discrete vocabulary…

Computation and Language · Computer Science 2026-02-12 Weihao Liu , Dehai Min , Lu Cheng

Augmenting large language models (LLMs) with auxiliary tokens has emerged as a promising strategy for enhancing model performance. In this work, we introduce a lightweight method termed latent tokens; these are dummy tokens that may be…

Machine Learning · Computer Science 2025-05-20 Yuchang Sun , Yanxi Chen , Yaliang Li , Bolin Ding

In recent years, Large Language Models (LLMs) have demonstrated remarkable capabilities across a wide array of text-centric tasks. However, their `large' scale introduces significant computational and storage challenges, particularly in…

Computation and Language · Computer Science 2024-07-03 Chaoran Zhang , Lixin Zou , Dan Luo , Min Tang , Xiangyang Luo , Zihao Li , Chenliang Li

Despite the great success of large language models (LLMs), efficiently controlling the length of the output sequence still remains a challenge. In this paper, we propose Hansel, an efficient framework for length control in LLMs without…

Computation and Language · Computer Science 2024-12-19 Seoha Song , Junhyun Lee , Hyeonmok Ko

In the emerging landscape of edge computing, the stochastic and bursty nature of serverless workloads presents a critical challenge for autonomous resource orchestration. Traditional reactive controllers, such as the Kubernetes Horizontal…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-04-01 Faraz Shaikh , Gianluca Reali , Mauro Femminella

Recently, there has been growing interest in collecting reasoning-intensive pretraining data to improve LLMs' complex reasoning ability. Prior approaches typically rely on supervised classifiers to identify such data, which requires…

Computation and Language · Computer Science 2025-05-13 Kai Hua , Steven Wu , Ge Zhang , Ke Shen

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

Large Reasoning Models (LRMs) excel at solving complex problems by explicitly generating a reasoning trace before deriving the final answer. However, these extended generations incur substantial memory footprint and computational overhead,…

Artificial Intelligence · Computer Science 2026-01-27 Zhenyuan Guo , Tong Chen , Wenlong Meng , Chen Gong , Xin Yu , Chengkun Wei , Wenzhi Chen

Speculative decoding is a powerful technique that attempts to circumvent the autoregressive constraint of modern Large Language Models (LLMs). The aim of speculative decoding techniques is to improve the average inference time of a large,…

Computation and Language · Computer Science 2024-10-25 Sudhanshu Agrawal , Wonseok Jeon , Mingu Lee

Recent advancements in large language models (LLMs) have greatly improved their capabilities on complex reasoning tasks through Long Chain-of-Thought (CoT). However, this approach often results in substantial redundancy, impairing…

Computation and Language · Computer Science 2025-08-18 Qiguang Chen , Dengyun Peng , Jinhao Liu , HuiKang Su , Jiannan Guan , Libo Qin , Wanxiang Che

Table images present unique challenges for effective and efficient understanding due to the need for question-specific focus and the presence of redundant background regions. Existing Multimodal Large Language Model (MLLM) approaches often…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Jongha Kim , Minseong Bae , Sanghyeok Lee , Jinsung Yoon , Hyunwoo J. Kim