English
Related papers

Related papers: Texo: Formula Recognition within 20M Parameters

200 papers

We present ReaderLM-v2, a compact 1.5 billion parameter language model designed for efficient web content extraction. Our model processes documents up to 512K tokens, transforming messy HTML into clean Markdown or JSON formats with high…

Computation and Language · Computer Science 2025-03-04 Feng Wang , Zesheng Shi , Bo Wang , Nan Wang , Han Xiao

It is staggering that words of the English language, which are on average represented by 5--6 bytes of ASCII, require as much as 24 kilobytes when served to large language models. We show that there is room for more information in every…

Machine Learning · Computer Science 2024-11-01 Peter Belcak , Roger Wattenhofer

Transformer-based large language models (LLMs) are comprised of billions of parameters arranged in deep and wide computational graphs. Several studies on LLM efficiency optimization argue that it is possible to prune a significant portion…

Computation and Language · Computer Science 2026-04-16 Corentin Kervadec , Iuliia Lysova , Marco Baroni , Gemma Boleda

Researchers are increasingly incorporating numeric high-order data, i.e., numeric tensors, within their practice. Just like the matrix/vector (MV) paradigm, the development of multi-purpose, but high-performance, sparse data structures and…

Mathematical Software · Computer Science 2018-02-09 Adam P. Harrison , Dileepan Joseph

Several recently devised machine learning (ML) algorithms have shown improved accuracy for various predictive problems. Model searches, which explore to find an optimal ML algorithm and hyperparameter values for the target problem, play a…

Distributed, Parallel, and Cluster Computing · Computer Science 2019-08-28 Yoshiki Takahashi , Masato Asahara , Kazuyuki Shudo

Although accuracy and computation benchmarks are widely available to help choose among neural network models, these are usually trained on datasets with many classes, and do not give a good idea of performance for few (< 10) classes. The…

Machine Learning · Computer Science 2024-10-31 Bryan Bo Cao , Abhinav Sharma , Lawrence O'Gorman , Michael Coss , Shubham Jain

We present a general framework based on weighted finite automata and weighted finite-state transducers for describing and implementing speech recognizers. The framework allows us to represent uniformly the information sources and data…

cmp-lg · Computer Science 2008-02-03 Fernando C. N. Pereira , Michael D. Riley

The development of efficient machine learning models for molecular systems representation is becoming crucial in scientific research. We introduce TensorNet, an innovative O(3)-equivariant message-passing neural network architecture that…

Machine Learning · Computer Science 2023-10-31 Guillem Simeon , Gianni de Fabritiis

Diffusion regulates numerous natural processes and the dynamics of many successful generative models. Existing models to learn the diffusion terms from observational data rely on complex bilevel optimization problems and model only the…

Machine Learning · Computer Science 2024-10-21 Antonio Terpin , Nicolas Lanzetti , Martin Gadea , Florian Dörfler

Modelling, parameter identification, and simulation play an important role in systems biology. Usually, the goal is to determine parameter values that minimise the difference between experimental measurement values and model predictions in…

Mathematical Software · Computer Science 2013-04-10 Thomas Dierkes , Susanna Röblitz , Moritz Wade , Peter Deuflhard

Natural language understanding tasks such as open-domain question answering often require retrieving and assimilating factual information from multiple sources. We propose to address this problem by integrating a semi-parametric…

Computation and Language · Computer Science 2022-04-21 Michiel de Jong , Yury Zemlyanskiy , Nicholas FitzGerald , Fei Sha , William Cohen

We present TabH2O, a foundation model for tabular data that performs classification and regression in a single forward pass via in-context learning. TabH2O builds on the TabICL architecture with several key modifications: (1) unified…

This paper addresses the problem of learning the impulse responses characterizing forward models by means of a regularized kernel-based Prediction Error Method (PEM). The common approach to accomplish that is to approximate the system with…

Optimization and Control · Mathematics 2024-09-20 Giulio Fattore , Marco Peruzzo , Giacomo Sartori , Mattia Zorzi

Neural models are known to be over-parameterized, and recent work has shown that sparse text-to-speech (TTS) models can outperform dense models. Although a plethora of sparse methods has been proposed for other domains, such methods have…

Audio and Speech Processing · Electrical Eng. & Systems 2022-09-23 Perry Lam , Huayun Zhang , Nancy F. Chen , Berrak Sisman

We propose a new benchmark corpus to be used for measuring progress in statistical language modeling. With almost one billion words of training data, we hope this benchmark will be useful to quickly evaluate novel language modeling…

Computation and Language · Computer Science 2014-03-05 Ciprian Chelba , Tomas Mikolov , Mike Schuster , Qi Ge , Thorsten Brants , Phillipp Koehn , Tony Robinson

Investors are interested in predicting future success of startup companies, preferably using publicly available data which can be gathered using free online sources. Using public-only data has been shown to work, but there is still much…

Machine Learning · Computer Science 2023-12-12 Emily Gavrilenko , Foaad Khosmood , Mahdi Rastad , Sadra Amiri Moghaddam

Transformer-based models have achieved remarkable success in various Natural Language Processing (NLP) tasks, yet their ability to handle long documents is constrained by computational limitations. Traditional approaches, such as truncating…

Computation and Language · Computer Science 2025-08-21 Yan Li , Soyeon Caren Han , Yue Dai , Feiqi Cao

Time domain identification is studied in this paper for parameters of a continuous-time multi-input multi-output descriptor system, with these parameters affecting system matrices through a linear fractional transformation. Sampling is…

Multiagent Systems · Computer Science 2025-06-17 Tong Zhou

Sentiment analysis (SA) has become an extensive research area in recent years impacting diverse fields including ecommerce, consumer business, and politics, driven by increasing adoption and usage of social media platforms. It is…

Computation and Language · Computer Science 2021-06-03 Sarojadevi Palani , Prabhu Rajagopal , Sidharth Pancholi

Recent works attribute the capability of in-context learning (ICL) in large pre-trained language models to implicitly simulating and fine-tuning an internal model (e.g., linear or 2-layer MLP) during inference. However, such constructions…

Computation and Language · Computer Science 2024-02-09 Abhishek Panigrahi , Sadhika Malladi , Mengzhou Xia , Sanjeev Arora