English
Related papers

Related papers: Layer-wise Token Compression for Efficient Documen…

200 papers

Long-context inputs in large language models (LLMs) often suffer from the "lost in the middle" problem, where critical information becomes diluted or ignored due to excessive length. Context compression methods aim to address this by…

Computation and Language · Computer Science 2026-02-04 Xuancheng Li , Haitao Li , Yujia Zhou , Qingyao Ai , Yiqun Liu

With the emergence of large model-based agents, widely adopted transformer-based architectures inevitably produce excessively long token embeddings for transmission, which may result in high bandwidth overhead, increased power consumption…

Networking and Internet Architecture · Computer Science 2025-11-04 Junhe Zhang , Wanli Ni , Pengwei Wang , Dongyu Wang

The quadratic complexity of the attention module makes it gradually become the bulk of compute in Transformer-based LLMs during generation. Moreover, the excessive key-value cache that arises when dealing with long inputs also brings severe…

Computation and Language · Computer Science 2023-10-17 Siyu Ren , Qi Jia , Kenny Q. Zhu

Existing visual token compression methods for Multimodal Large Language Models (MLLMs) predominantly operate as post-encoder modules, limiting their potential for efficiency gains. To address this limitation, we propose LaCo (Layer-wise…

Computer Vision and Pattern Recognition · Computer Science 2025-07-04 Juntao Liu , Liqiang Niu , Wenchao Chen , Jie Zhou , Fandong Meng

Long document re-ranking has been a challenging problem for neural re-rankers based on deep language models like BERT. Early work breaks the documents into short passage-like chunks. These chunks are independently mapped to scalar scores or…

Information Retrieval · Computer Science 2022-06-07 Luyu Gao , Jamie Callan

Text embedding models serve as a fundamental component in real-world search applications. By mapping queries and documents into a shared embedding space, they deliver competitive retrieval performance with high efficiency. However, their…

Computation and Language · Computer Science 2025-11-03 Qi Liu , Yanzhao Zhang , Mingxin Li , Dingkun Long , Pengjun Xie , Jiaxin Mao

Large language models (LLMs) have triggered a new stream of research focusing on compressing the context length to reduce the computational cost while ensuring the retention of helpful information for LLMs to answer the given question.…

Computation and Language · Computer Science 2024-12-20 Barys Liskavets , Maxim Ushakov , Shuvendu Roy , Mark Klibanov , Ali Etemad , Shane Luke

Contrastive learning has been the dominant approach to training dense retrieval models. In this work, we investigate the impact of ranking context - an often overlooked aspect of learning dense retrieval models. In particular, we examine…

Information Retrieval · Computer Science 2023-10-24 George Zerveas , Navid Rekabsaz , Daniel Cohen , Carsten Eickhoff

Approaches for compressing large-language models using low-rank decomposition have made strides, particularly with the introduction of activation and loss-aware SVD, which improves the trade-off between decomposition rank and downstream…

Machine Learning · Computer Science 2025-12-17 Sidhant Sundrani , Francesco Tudisco , Pasquale Minervini

Large language models (LLMs) rely on key-value (KV) caches for efficient autoregressive decoding; however, cache size grows linearly with context length and model depth, becoming a major bottleneck in long-context inference. Prior KV cache…

Machine Learning · Computer Science 2025-09-22 Dmitry Akulov , Mohamed Sana , Antonio De Domenico , Tareq Si Salem , Nicola Piovesan , Fadhel Ayed

The low-rank tensor approximation is very promising for the compression of deep neural networks. We propose a new simple and efficient iterative approach, which alternates low-rank factorization with a smart rank selection and fine-tuning.…

Machine Learning · Computer Science 2019-11-18 Julia Gusak , Maksym Kholiavchenko , Evgeny Ponomarev , Larisa Markeeva , Ivan Oseledets , Andrzej Cichocki

Effective token compression remains a critical challenge for scaling models to handle increasingly complex and diverse datasets. A novel mechanism based on contextual reinforcement is introduced, dynamically adjusting token importance…

Computation and Language · Computer Science 2025-08-11 Naderdel Piero , Zacharias Cromwell , Nathaniel Wainwright , Matthias Nethercott

Encoder transformer models compress information from all tokens in a sequence into a single [CLS] token to represent global context. This approach risks diluting fine-grained or hierarchical features, leading to information loss in…

Computation and Language · Computer Science 2025-09-23 Asif Shahriar , Rifat Shahriyar , M Saifur Rahman

BERT based ranking models have achieved superior performance on various information retrieval tasks. However, the large number of parameters and complex self-attention operation come at a significant latency overhead. To remedy this, recent…

Information Retrieval · Computer Science 2021-10-06 Nachshon Cohen , Amit Portnoy , Besnik Fetahu , Amir Ingber

Search engines operate under a strict time constraint as a fast response is paramount to user satisfaction. Thus, neural re-ranking models have a limited time-budget to re-rank documents. Given the same amount of time, a faster re-ranking…

Information Retrieval · Computer Science 2020-02-06 Sebastian Hofstätter , Markus Zlabinger , Allan Hanbury

Dual-encoder-based dense retrieval models have become the standard in IR. They employ large Transformer-based language models, which are notoriously inefficient in terms of resources and latency. We propose Fast-Forward indexes -- vector…

Information Retrieval · Computer Science 2023-11-03 Jurek Leonhardt , Henrik Müller , Koustav Rudra , Megha Khosla , Abhijit Anand , Avishek Anand

Retrieving documents and prepending them in-context at inference time improves performance of language model (LMs) on a wide range of tasks. However, these documents, often spanning hundreds of words, make inference substantially more…

Computation and Language · Computer Science 2023-10-09 Fangyuan Xu , Weijia Shi , Eunsol Choi

The rapid progress of large language models (LLMs) has laid the foundation for multimodal models. However, visual language models (VLMs) still face heavy computational costs when extended from images to videos due to high frame rates and…

Computer Vision and Pattern Recognition · Computer Science 2026-02-10 Peiran Wu , Zhuorui Yu , Yunze Liu , Chi-Hao Wu , Enmin Zhou , Junxiao Shen

Listwise reranking utilizing Large Language Models (LLMs) has achieved state-of-the-art retrieval effectiveness. Recently, reasoning-enhanced models have further pushed these boundaries by employing Chain-of-Thought (CoT) to perform deep…

Information Retrieval · Computer Science 2026-05-15 Danyang Liu , Kan Li

Retrieval with extremely long queries and documents is a well-known and challenging task in information retrieval and is commonly known as Query-by-Document (QBD) retrieval. Specifically designed Transformer models that can handle long…

Information Retrieval · Computer Science 2023-11-03 Arian Askari , Suzan Verberne , Amin Abolghasemi , Wessel Kraaij , Gabriella Pasi