English
Related papers

Related papers: Higher Order Context Transformations

200 papers

Recent state-of-the-art Learned Image Compression methods feature spatial context models, achieving great rate-distortion improvements over hyperprior methods. However, the autoregressive context model requires serial decoding, limiting…

Computer Vision and Pattern Recognition · Computer Science 2023-02-21 Fangzheng Lin , Heming Sun , Jinming Liu , Jiro Katto

Autoregressive Transformers adopted in Large Language Models (LLMs) are hard to scale to long sequences. Despite several works trying to reduce their computational cost, most of LLMs still adopt attention layers between all pairs of tokens…

Computation and Language · Computer Science 2024-06-03 Sotiris Anagnostidis , Dario Pavllo , Luca Biggio , Lorenzo Noci , Aurelien Lucchi , Thomas Hofmann

In recent deep image compression neural networks, the entropy model plays a critical role in estimating the prior distribution of deep image encodings. Existing methods combine hyperprior with local context in the entropy estimation…

Image and Video Processing · Electrical Eng. & Systems 2023-03-16 Yichen Qian , Zhiyu Tan , Xiuyu Sun , Ming Lin , Dongyang Li , Zhenhong Sun , Hao Li , Rong Jin

Today's large language models (LLMs) typically train on short text segments (e.g., <4K tokens) due to the quadratic complexity of their Transformer architectures. As a result, their performance suffers drastically on inputs longer than…

Computation and Language · Computer Science 2024-06-26 Chi Han , Qifan Wang , Hao Peng , Wenhan Xiong , Yu Chen , Heng Ji , Sinong Wang

Leveraging user-provided translation to constrain NMT has practical significance. Existing methods can be classified into two main categories, namely the use of placeholder tags for lexicon words and the use of hard constraints during…

Computation and Language · Computer Science 2019-05-17 Kai Song , Yue Zhang , Heng Yu , Weihua Luo , Kun Wang , Min Zhang

This study evaluates the effectiveness of zero-shot compression techniques on large language models (LLMs) under long-context. We identify the tendency for computational errors to increase under long-context when employing certain…

Computation and Language · Computer Science 2025-02-14 Chenyu Wang , Yihan Wang , Kai Li

Synchronous Context-Free Grammars (SCFGs), also known as syntax-directed translation schemata, are unlike context-free grammars in that they do not have a binary normal form. In general, parsing with SCFGs takes space and time polynomial in…

Formal Languages and Automata Theory · Computer Science 2013-11-27 Pierluigi Crescenzi , Daniel Gildea , Andrea Marino , Gianluca Rossi , Giorgio Satta

In the era of large language models, applying techniques such as Retrieval Augmented Generation can better address Open-Domain Question-Answering problems. Due to constraints including model sizes and computing resources, the length of…

Computation and Language · Computer Science 2024-12-24 Zhuo Chen , Xinyu Wang , Yong Jiang , Pengjun Xie , Fei Huang , Kewei Tu

Context modeling is essential in learned image compression for accurately estimating the distribution of latents. While recent advanced methods have expanded context modeling capacity, they still struggle to efficiently exploit long-range…

Image and Video Processing · Electrical Eng. & Systems 2025-07-28 Yuqi Li , Haotian Zhang , Li Li , Dong Liu

Translating characters instead of words or word-fragments has the potential to simplify the processing pipeline for neural machine translation (NMT), and improve results by eliminating hyper-parameters and manual feature engineering.…

Computation and Language · Computer Science 2018-08-30 Colin Cherry , George Foster , Ankur Bapna , Orhan Firat , Wolfgang Macherey

Most existing large language models (LLMs) are expensive to adapt after deployment, especially when a task requires newly produced information or niche domain knowledge. Recent work has shown that, by manipulating and optimizing their…

Computation and Language · Computer Science 2026-05-15 Zeyu Huang , Adhiguna Kuncoro , Qixuan Feng , Jiajun Shen , Lucio Dery , Arthur Szlam , Marc'Aurelio Ranzato

We introduce a new method for speeding up the inference of deep neural networks. It is somewhat inspired by the reduced-order modeling techniques for dynamical systems.The cornerstone of the proposed method is the maximum volume algorithm.…

Machine Learning · Computer Science 2020-11-26 Julia Gusak , Talgat Daulbaev , Evgeny Ponomarev , Andrzej Cichocki , Ivan Oseledets

Feed-forward CNNs trained for image transformation problems rely on loss functions that measure the similarity between the generated image and a target image. Most of the common loss functions assume that these images are spatially aligned…

Computer Vision and Pattern Recognition · Computer Science 2018-07-19 Roey Mechrez , Itamar Talmi , Lihi Zelnik-Manor

Recent advancements in the field of Natural Language Processing, particularly the development of large-scale language models that are pretrained on vast amounts of knowledge, are creating novel opportunities within the realm of Knowledge…

Computation and Language · Computer Science 2023-10-06 Anisa Rula , Jennifer D'Souza

Large language models have an exceptional capability to incorporate new information in a contextual manner. However, the full potential of such an approach is often restrained due to a limitation in the effective context length. One…

Computation and Language · Computer Science 2023-12-01 Szymon Tworkowski , Konrad Staniszewski , Mikołaj Pacek , Yuhuai Wu , Henryk Michalewski , Piotr Miłoś

Deep Neural network learning for image processing faces major challenges related to changes in distribution across layers, which disrupt model convergence and performance. Activation normalization methods, such as Batch Normalization (BN),…

Computer Vision and Pattern Recognition · Computer Science 2024-09-10 Bilal Faye , Hanane Azzag , Mustapha Lebbah , Djamel Bouchaffra

Large language models (LLMs) exhibit a strong capacity for in-context learning: Given labeled examples, they can generate good predictions without parameter updates. However, many interactive settings go beyond static prediction to online…

Machine Learning · Computer Science 2026-05-12 Emile Anand , Abdullah Ateyeh , Xinyuan Cao , Max Dabagia

Large language models (LMs) are currently trained to predict tokens given document prefixes, enabling them to directly perform long-form generation and prompting-style tasks which can be reduced to document completion. Existing pretraining…

Transformer based re-ranking models can achieve high search relevance through context-aware soft matching of query tokens with document tokens. To alleviate runtime complexity of such inference, previous work has adopted a late interaction…

Information Retrieval · Computer Science 2022-03-30 Yingrui Yang , Yifan Qiao , Tao Yang

Large Language Models (LLMs) face significant computational challenges when processing long contexts due to the quadratic complexity of self-attention. While soft context compression methods, which map input text to smaller latent…

Computation and Language · Computer Science 2025-09-24 Gabriele Berton , Jayakrishnan Unnikrishnan , Son Tran , Mubarak Shah