English
Related papers

Related papers: Magic Pyramid: Accelerating Inference with Early E…

200 papers

Multimodal large language models (MLLMs) demonstrate strong performance across visual tasks, but their efficiency is hindered by significant computational and memory demands from processing long contexts in multimodal inputs. To address…

Computer Vision and Pattern Recognition · Computer Science 2024-12-03 Yingen Liu , Fan Wu , Ruihui Li , Zhuo Tang , Kenli Li

Access to external knowledge is essential for many natural language processing tasks, such as question answering and dialogue. Existing methods often rely on a parametric model that stores knowledge in its parameters, or use a…

Computation and Language · Computer Science 2022-11-01 Yuxiang Wu , Yu Zhao , Baotian Hu , Pasquale Minervini , Pontus Stenetorp , Sebastian Riedel

Inference of Large Language Models (LLMs) across computer clusters has become a focal point of research in recent times, with many acceleration techniques taking inspiration from CPU speculative execution. These techniques reduce…

Computation and Language · Computer Science 2024-11-19 Branden Butler , Sixing Yu , Arya Mazaheri , Ali Jannesari

Learned sparse retrieval systems aim to combine the effectiveness of contextualized language models with the scalability of conventional data structures such as inverted indexes. Nevertheless, the indexes generated by these systems exhibit…

Information Retrieval · Computer Science 2024-05-03 Antonio Mallia , Torten Suel , Nicola Tonellotto

Early Exiting is one of the most popular methods to achieve efficient inference. Current early exiting methods adopt the (weighted) sum of the cross entropy loss of all internal classifiers during training, imposing all these classifiers to…

Computation and Language · Computer Science 2024-04-09 Ziqian Zeng , Yihuai Hong , Hongliang Dai , Huiping Zhuang , Cen Chen

The attention mechanism is becoming increasingly popular in Natural Language Processing (NLP) applications, showing superior performance than convolutional and recurrent architectures. However, attention becomes the compution bottleneck…

Hardware Architecture · Computer Science 2024-07-22 Hanrui Wang , Zhekai Zhang , Song Han

Recently, large language models (LLMs) have demonstrated superior performance across various tasks by adhering to scaling laws, which significantly increase model size. However, the huge computation overhead during inference hinders the…

Computation and Language · Computer Science 2024-12-17 Zekai Li , Jintu Zheng , Ji Liu , Han Liu , Haowei Zhu , Zeping Li , Fuwei Yang , Haiduo Huang , Jinzhang Peng , Dong Li , Lu Tian , Emad Barsoum

Multi-modal Large Language Models (MLLMs) have achieved remarkable success by integrating visual and textual modalities. However, they incur significant computational overhead due to the large number of vision tokens processed, limiting…

Computation and Language · Computer Science 2025-03-11 Yizheng Sun , Yanze Xin , Hao Li , Jingyuan Sun , Chenghua Lin , Riza Batista-Navarro

The breakthrough performance of large language models (LLMs) comes with major computational footprints and high deployment costs. In this paper, we progress towards resolving this problem by proposing a novel structured compression approach…

Machine Learning · Computer Science 2023-10-27 Eldar Kurtic , Elias Frantar , Dan Alistarh

Modern large vision-language models (LVLMs) convert each input image into a large set of tokens that far outnumber the text tokens. Although this improves visual perception, it also introduces severe image token redundancy. Because image…

Computer Vision and Pattern Recognition · Computer Science 2025-12-10 Yanshu Li , Jianjiang Yang , Zhennan Shen , Ligong Han , Haoyan Xu , Ruixiang Tang

Recent large language models have shown promising capabilities in long-form reasoning, following structured chains of thought before arriving at a final answer. However, we observe that these reasoning paths tend to include substantial…

Large language models (LLMs) process entire input contexts indiscriminately, which is inefficient when the information required to answer a query is localized within the context. We present dynamic context cutoff, a novel method enabling…

Computation and Language · Computer Science 2026-02-10 Roy Xie , Junlin Wang , Paul Rosu , Chunyuan Deng , Bolun Sun , Zihao Lin , Bhuwan Dhingra

Large Language Models (LLMs) can enhance reasoning capabilities through test-time scaling by generating multiple traces. However, the combination of lengthy reasoning traces with multiple sampling introduces substantial computation and high…

Machine Learning · Computer Science 2026-04-29 Zhixiang Liang , Beichen Huang , Zheng Wang , Minjia Zhang

Prompt tuning learns soft prompts to condition frozen Pre-trained Language Models (PLMs) for performing downstream tasks in a parameter-efficient manner. While prompt tuning has gradually reached the performance level of fine-tuning as the…

Computation and Language · Computer Science 2022-10-11 Fang Ma , Chen Zhang , Lei Ren , Jingang Wang , Qifan Wang , Wei Wu , Xiaojun Quan , Dawei Song

The rapid increase in the size of large language models (LLMs) has significantly escalated their computational and memory demands, posing challenges for efficient deployment, especially on resource-constrained devices. Structured pruning…

Machine Learning · Computer Science 2025-01-17 Hanyu Hu , Pengxiang Zhao , Ping Li , Yi Zheng , Zhefeng Wang , Xiaoming Yuan

To reduce the latency associated with autoretrogressive LLM inference, speculative decoding has emerged as a novel decoding paradigm, where future tokens are drafted and verified in parallel. However, the practical deployment of speculative…

Computation and Language · Computer Science 2024-12-03 Shwetha Somasundaram , Anirudh Phukan , Apoorv Saxena

Learning a versatile language-image model is computationally prohibitive under a limited computing budget. This paper delves into the \emph{efficient language-image pre-training}, an area that has received relatively little attention…

Computer Vision and Pattern Recognition · Computer Science 2026-01-27 Yangyang Guo , Haoyu Zhang , Yongkang Wong , Liqiang Nie , Mohan Kankanhalli

Human communication heavily relies on laconism and inferential pragmatics, allowing listeners to successfully reconstruct rich meaning from sparse, telegraphic speech. In contrast, large language models (LLMs) owe much of their stellar…

Computation and Language · Computer Science 2026-03-13 Syed Rifat Raiyan , Md Farhan Ishmam , Abdullah Al Imran , Mohammad Ali Moni

Recent advances in fine-tuning large language models (LLMs) have greatly enhanced their usage in domain-specific tasks. Despite the success, fine-tuning continues to rely on repeated and lengthy prompts, which escalate computational…

Computation and Language · Computer Science 2024-10-17 Jiaru Zou , Mengyu Zhou , Tao Li , Shi Han , Dongmei Zhang

We introduce CopySpec, a simple yet effective technique to tackle the inefficiencies LLMs face when generating responses that closely resemble previous outputs or responses that can be verbatim extracted from context. CopySpec identifies…

Computation and Language · Computer Science 2025-05-26 Razvan-Gabriel Dumitru , Minglai Yang , Vikas Yadav , Mihai Surdeanu