English
Related papers

Related papers: Kronecker Embeddings: Byte-Level Structured Token …

200 papers

Large language models are trained with tokenizers, and the resulting token distribution is highly imbalanced: a few words dominate the stream while most occur rarely. Recent practice favors ever-larger vocabularies, but it is unclear where…

Computation and Language · Computer Science 2025-12-01 Woojin Chung , Jeonghoon Kim

Small Language Models (SLMs, or on-device LMs) have significantly fewer parameters than Large Language Models (LLMs). They are typically deployed on low-end devices, like mobile phones and single-board computers. Unlike LLMs, which rely on…

Computation and Language · Computer Science 2025-06-17 Mingxue Xu , Yao Lei Xu , Danilo P. Mandic

Federated learning and analytics are often described as collections of separate protocols, even when they share the same mathematical form: client-local tensor computation, mergeable aggregation into shared state, and shared-only…

Large Vision-Language Models (LVLMs) have shown impressive performance across multi-modal tasks by encoding images into thousands of tokens. However, the large number of image tokens results in significant computational overhead, and the…

Computer Vision and Pattern Recognition · Computer Science 2025-10-24 Kaiyuan Li , Xiaoyue Chen , Chen Gao , Yong Li , Xinlei Chen

Byte Pair Encoding (BPE) tokenizers, widely used in Large Language Models, face challenges in multilingual settings, including penalization of non-Western scripts and the creation of tokens with partial UTF-8 sequences. Pretokenization,…

Computation and Language · Computer Science 2025-06-02 Sander Land , Catherine Arnett

Token representation strategies within large-scale neural architectures often rely on contextually refined embeddings, yet conventional approaches seldom encode structured relationships explicitly within token interactions. Self-attention…

Computation and Language · Computer Science 2025-03-27 James Blades , Frederick Somerfield , William Langley , Susan Everingham , Maurice Witherington

Researchers have recently suggested that models share common representations. In our work, we find numerous geometric similarities across the token embeddings of large language models. First, we find ``global'' similarities: token…

Computation and Language · Computer Science 2025-07-16 Andrew Lee , Melanie Weber , Fernanda Viégas , Martin Wattenberg

The success of pretrained transformer language models (LMs) in natural language processing has led to a wide range of pretraining setups. In particular, these models employ a variety of subword tokenization methods, most notably byte-pair…

Computation and Language · Computer Science 2020-10-06 Kaj Bostrom , Greg Durrett

Sentence embeddings are a foundational component for semantic search, clustering, classification, and retrieval-augmented generation. This paper presents embeddingmagibu-200m, a Turkish-focused sentence embedding model that produces…

Computation and Language · Computer Science 2026-05-29 M. Ali Bayram , Banu Diri , Savaş Yıldırım

In this work, we show a fundamental limitation in vocabulary adaptation approaches that use Byte-Pair Encoding (BPE) tokenization scheme for fine-tuning pretrained language models (PLMs) to expert domains. Current approaches trivially…

Computation and Language · Computer Science 2025-04-29 Gunjan Balde , Soumyadeep Roy , Mainack Mondal , Niloy Ganguly

Byte Pair Encoding (BPE) serves as a foundation method for text tokenization in the Natural Language Processing (NLP) field. Despite its wide adoption, the original BPE algorithm harbors an inherent flaw: it inadvertently introduces a…

Computation and Language · Computer Science 2024-11-14 Haoran Lian , Yizhe Xiong , Jianwei Niu , Shasha Mo , Zhenpeng Su , Zijia Lin , Hui Chen , Peng Liu , Jungong Han , Guiguang Ding

Neural Machine Translation (MT) has reached state-of-the-art results. However, one of the main challenges that neural MT still faces is dealing with very large vocabularies and morphologically rich languages. In this paper, we propose a…

Computation and Language · Computer Science 2016-07-01 Marta R. Costa-Jussà , José A. R. Fonollosa

This paper proposes a novel acoustic word embedding called Acoustic Neighbor Embeddings where speech or text of arbitrary length are mapped to a vector space of fixed, reduced dimensions by adapting stochastic neighbor embedding (SNE) to…

Audio and Speech Processing · Electrical Eng. & Systems 2022-01-10 Woojay Jeon

Computing next-token likelihood ratios between two language models (LMs) is a standard task in training paradigms such as knowledge distillation. Since this requires both models to share the same probability space, it becomes challenging…

Computation and Language · Computer Science 2026-05-07 Buu Phan , Ashish Khisti , Karen Ullrich

Large language models solve complex tasks by generating long reasoning chains, achieving higher accuracy at the cost of increased computational cost and reduced ability to isolate functionally relevant reasoning. Prior work on compact…

Computation and Language · Computer Science 2026-04-22 Janvijay Singh , Dilek Hakkani-Tür

Tokenization is an important preprocessing step in the training and inference of large language models (LLMs). While there has been extensive research on the expressive power of the neural achitectures used in LLMs, the impact of…

Computation and Language · Computer Science 2024-12-05 Saibo Geng , Sankalp Gambhir , Chris Wendler , Robert West

Learning neural program embeddings is key to utilizing deep neural networks in program languages research --- precise and efficient program representations enable the application of deep models to a wide range of program analysis tasks.…

Software Engineering · Computer Science 2019-07-12 Ke Wang , Zhendong Su

We re-evaluate the standard practice of sharing weights between input and output embeddings in state-of-the-art pre-trained language models. We show that decoupled embeddings provide increased modeling flexibility, allowing us to…

Computation and Language · Computer Science 2020-10-27 Hyung Won Chung , Thibault Févry , Henry Tsai , Melvin Johnson , Sebastian Ruder

We present a variety of methods for training complex-valued word embeddings, based on the classical Skip-gram model, with a straightforward adaptation simply replacing the real-valued vectors with arbitrary vectors of complex numbers. In a…

Computation and Language · Computer Science 2024-12-19 Carys Harvey , Stephen Clark , Douglas Brown , Konstantinos Meichanetzidis

Feed-forward neural networks can be understood as a combination of an intermediate representation and a linear hypothesis. While most previous works aim to diversify the representations, we explore the complementary direction by performing…

Machine Learning · Computer Science 2019-10-24 Han Zhao , Yao-Hung Hubert Tsai , Ruslan Salakhutdinov , Geoffrey J. Gordon