English
Related papers

Related papers: Scaling Embedding Layers in Language Models

200 papers

Effectively training language models on long inputs poses many technical challenges. As a cost consideration, languages models are pretrained on a fixed sequence length before being adapted to longer sequences. We explore various methods…

Computation and Language · Computer Science 2024-06-21 Petros Karypis , Julian McAuley , George Karypis

Large language models (LLMs) demonstrate strong performance as text embedding models when finetuned with supervised contrastive training. However, their large size balloons inference time and memory requirements. In this paper, we show that…

Computation and Language · Computer Science 2024-10-21 Thennal D K , Tim Fischer , Chris Biemann

Model fine-tuning and adaptation have become a common approach for model specialization for downstream tasks or domains. Fine-tuning the entire model or a subset of the parameters using light-weight adaptation has shown considerable success…

Audio and Speech Processing · Electrical Eng. & Systems 2023-05-25 Fadi Biadsy , Youzheng Chen , Xia Zhang , Oleg Rybakov , Andrew Rosenberg , Pedro J. Moreno

The extensive memory footprint of language model (LM) fine-tuning poses a challenge for both researchers and practitioners. LMs use an embedding matrix to represent extensive vocabularies, forming a substantial proportion of the model…

Computation and Language · Computer Science 2025-03-26 Miles Williams , Nikolaos Aletras

End-to-end acoustic-to-word speech recognition models have recently gained popularity because they are easy to train, scale well to large amounts of training data, and do not require a lexicon. In addition, word models may also be easier to…

Computation and Language · Computer Science 2019-02-20 Shruti Palaskar , Vikas Raunak , Florian Metze

Scaling test-time compute has driven the recent advances in the reasoning capabilities of large language models (LLMs), typically by allocating additional computation for more thorough exploration. However, increased compute often comes at…

Artificial Intelligence · Computer Science 2026-02-20 Mert Cemri , Nived Rajaraman , Rishabh Tiwari , Xiaoxuan Liu , Kurt Keutzer , Ion Stoica , Kannan Ramchandran , Ahmad Beirami , Ziteng Sun

We propose a new finetuning method to provide pre-trained large language models (LMs) the ability to scale test-time compute through the diffusion framework. By increasing the number of diffusion steps, we show our finetuned models achieve…

Computation and Language · Computer Science 2025-06-04 Edoardo Cetin , Tianyu Zhao , Yujin Tang

It is commonly believed that scaling language models should commit a significant space or time cost, by increasing the parameters (parameter scaling) or output tokens (inference-time scaling). We introduce the third and more…

Machine Learning · Computer Science 2025-05-16 Mouxiang Chen , Binyuan Hui , Zeyu Cui , Jiaxi Yang , Dayiheng Liu , Jianling Sun , Junyang Lin , Zhongxin Liu

The design of specialized architectures for accelerating the inference procedure of Deep Neural Networks (DNNs) is a booming area of research nowadays. First-generation rigid proposals have been rapidly replaced by more advanced flexible…

Signal Processing · Electrical Eng. & Systems 2020-06-15 Francisco Muñoz-Martínez , José L. Abellán , Manuel E. Acacio , Tushar Krishna

Many machine learning models, such as logistic regression~(LR) and support vector machine~(SVM), can be formulated as composite optimization problems. Recently, many distributed stochastic optimization~(DSO) methods have been proposed to…

Machine Learning · Statistics 2016-12-13 Shen-Yi Zhao , Ru Xiang , Ying-Hao Shi , Peng Gao , Wu-Jun Li

Training large language models (LLMs) relies on adaptive optimizers such as Adam, which introduce extra operations and require significantly more memory to maintain first- and second-order moments than SGD. While recent works such as…

Machine Learning · Computer Science 2026-05-22 Athanasios Glentis , Jiaxiang Li , Andi Han , Mingyi Hong

When existing retrieval-augmented generation (RAG) solutions are intended to be used for new knowledge domains, it is necessary to update their encoders, which are taken to be pretrained large language models (LLMs). However, fully…

Machine Learning · Computer Science 2025-09-23 Marijan Fofonjka , Shahryar Zehtabi , Alireza Behtash , Tyler Mauer , David Stout

Speculative Decoding has emerged as a popular technique for accelerating inference in Large Language Models. However, most existing approaches yield only modest improvements in production serving systems. Methods that achieve substantial…

Computation and Language · Computer Science 2026-01-08 Michele Marzollo , Jiawei Zhuang , Niklas Roemer , Niklas Zwingenberger , Lorenz K. Müller , Lukas Cavigelli

In this paper, we present an approach to learn multilingual sentence embeddings using a bi-directional dual-encoder with additive margin softmax. The embeddings are able to achieve state-of-the-art results on the United Nations (UN)…

Computation and Language · Computer Science 2019-06-18 Yinfei Yang , Gustavo Hernandez Abrego , Steve Yuan , Mandy Guo , Qinlan Shen , Daniel Cer , Yun-hsuan Sung , Brian Strope , Ray Kurzweil

We propose a novel model architecture and training algorithm to learn bilingual sentence embeddings from a combination of parallel and monolingual data. Our method connects autoencoding and neural machine translation to force the source and…

Computation and Language · Computer Science 2019-06-06 Yunsu Kim , Hendrik Rosendahl , Nick Rossenbach , Jan Rosendahl , Shahram Khadivi , Hermann Ney

Acoustic word embeddings are fixed-dimensional representations of variable-length speech segments. Such embeddings can form the basis for speech search, indexing and discovery systems when conventional speech recognition is not possible. In…

Computation and Language · Computer Science 2021-02-08 Herman Kamper , Yevgen Matusevych , Sharon Goldwater

Modeling instance-level context and object-object relationships is extremely challenging. It requires reasoning about bounding boxes of different classes, locations \etc. Above all, instance-level spatial reasoning inherently requires…

Computer Vision and Pattern Recognition · Computer Science 2017-04-14 Xinlei Chen , Abhinav Gupta

This paper proposes a novel approach to word embeddings in Transformer models by utilizing spinors from geometric algebra. Spinors offer a rich mathematical framework capable of capturing complex relationships and transformations in…

Machine Learning · Computer Science 2024-10-02 Rick White

While paragraph embedding models are remarkably effective for downstream classification tasks, what they learn and encode into a single vector remains opaque. In this paper, we investigate a state-of-the-art paragraph embedding method…

Computation and Language · Computer Science 2019-06-11 Tu Vu , Mohit Iyyer

Deep learning models tend to memorize training data, which hurts their ability to generalize to under-represented classes. We empirically study a convolutional neural network's internal representation of imbalanced image data and measure…

Machine Learning · Computer Science 2022-10-19 Damien Dablain , Colin Bellinger , Bartosz Krawczyk , Nitesh Chawla