English
Related papers

Related papers: Normalized Architectures are Natively 4-Bit

200 papers

Despite the popularity of transformers in practice, their architectures are empirically designed and neither mathematically justified nor interpretable. Moreover, as indicated by many empirical studies, some components of transformer…

Machine Learning · Computer Science 2025-06-05 Peng Wang , Yifu Lu , Yaodong Yu , Druv Pai , Qing Qu , Yi Ma

While deep convolutional architectures have achieved remarkable results in a gamut of supervised applications dealing with images and speech, recent works show that deep untrained non-convolutional architectures can also outperform…

Signal Processing · Electrical Eng. & Systems 2020-03-13 Samuel Rey , Antonio G. Marques , Santiago Segarra

Transformer architecture has been very successful long runner in the field of Deep Learning (DL) and Large Language Models (LLM) because of its powerful attention-based learning and parallel-natured architecture. As the models grow gigantic…

Machine Learning · Computer Science 2026-01-21 Phani Kumar , Nyshadham , Jyothendra Varma , Polisetty V R K , Aditya Rathore

This paper develops alternative hyperparameters for specifying sparse Recurrent Neural Networks (RNNs). These hyperparameters allow for varying sparsity within the trainable weight matrices of the model while improving overall performance.…

Machine Learning · Computer Science 2025-09-19 Quincy Hershey , Randy Paffenroth

Transformers have significantly advanced the field of natural language processing, but comprehending their internal mechanisms remains a challenge. In this paper, we introduce a novel geometric perspective that elucidates the inner…

Computation and Language · Computer Science 2023-09-20 Raul Molina

Recently, pre-trained Transformer based language models, such as BERT, have shown great superiority over the traditional methods in many Natural Language Processing (NLP) tasks. However, the computational cost for deploying these models is…

Machine Learning · Computer Science 2022-03-28 Hanlin Tang , Xipeng Zhang , Kai Liu , Jianchen Zhu , Zhanhui Kang

Neural machine translation (NMT) models are typically trained with fixed-size input and output vocabularies, which creates an important bottleneck on their accuracy and generalization capability. As a solution, various studies proposed…

Computation and Language · Computer Science 2018-05-08 Duygu Ataman , Marcello Federico

Efficient compression of language model weights is increasingly critical as model scale and deployment grow. Yet, most existing methods rely on handcrafted transforms and heuristics, reflecting the limited understanding of weights as a data…

Machine Learning · Computer Science 2026-05-28 Jegwang Ryu , Minkyu Kim , Seungjun Shin , Hee Min Choi , Dokwan Oh , Jaeho Lee

NVFP4 has recently emerged as an efficient 4-bit microscaling format for large language models (LLMs), offering superior numerical fidelity with native hardware support. However, existing methods often yield suboptimal performance due to…

Machine Learning · Computer Science 2026-05-13 Chengzhu Bao , Xianglong Yan , Zhiteng Li , Guangshuo Qin , Guanghua Yu , Yulun Zhang

Reducing the latency and model size has always been a significant research problem for live Automatic Speech Recognition (ASR) application scenarios. Along this direction, model quantization has become an increasingly popular approach to…

Audio and Speech Processing · Electrical Eng. & Systems 2023-03-06 Shaojin Ding , Phoenix Meadowlark , Yanzhang He , Lukasz Lew , Shivani Agrawal , Oleg Rybakov

Nonnegative Matrix Factorization (NMF) is a widely applied technique in the fields of machine learning and data mining. Graph Regularized Non-negative Matrix Factorization (GNMF) is an extension of NMF that incorporates graph regularization…

Machine Learning · Computer Science 2024-03-19 Zhen Wang , Wenwen Min

A neural architecture with randomly initialized weights, in the infinite width limit, is equivalent to a Gaussian Random Field whose covariance function is the so-called Neural Network Gaussian Process kernel (NNGP). We prove that a…

Machine Learning · Computer Science 2024-04-29 Rustem Takhanov

Neural Machine Translation (NMT) models generally perform translation using a fixed-size lexical vocabulary, which is an important bottleneck on their generalization capability and overall translation quality. The standard approach to…

Computation and Language · Computer Science 2019-10-22 Duygu Ataman , Orhan Firat , Mattia A. Di Gangi , Marcello Federico , Alexandra Birch

The advent of large-scale pre-trained language models has contributed greatly to the recent progress in natural language processing. Many state-of-the-art language models are first trained on a large text corpus and then fine-tuned on…

Computation and Language · Computer Science 2023-11-13 Hang Hua , Xingjian Li , Dejing Dou , Cheng-Zhong Xu , Jiebo Luo

Deploying deep neural networks on resource-constrained 6G edge devices demands aggressive compression with minimal accuracy loss. Quantization-Aware Training (QAT) has emerged as a leading compression approach; however, existing…

In recent years, large pre-trained Transformer networks have demonstrated dramatic improvements in many natural language understanding tasks. However, the huge size of these models brings significant challenges to their fine-tuning and…

Computation and Language · Computer Science 2022-07-01 Connor Holmes , Minjia Zhang , Yuxiong He , Bo Wu

As large language models have grown larger, interest has grown in low-precision numerical formats such as NVFP4 as a way to improve speed and reduce memory usage. However, quantizing models to NVFP4 remains challenging as the lack of…

Computation and Language · Computer Science 2026-05-12 Jack Cook , Junxian Guo , Guangxuan Xiao , Yujun Lin , Keith Wyss , Mahdi Nazemi , Asit Mishra , Carlo del Mundo , Tijmen Blankevoort , Song Han

Every commercially available, state-of-the-art neural network consume plain input data, which is a well-known privacy concern. We propose a new architecture based on homomorphic encryption, which allows the neural network to operate on…

Cryptography and Security · Computer Science 2025-02-28 Marcos Florencio , Luiz Alencar , Bianca Lima

We propose WHISPER-GPT: A generative large language model (LLM) for speech and music that allows us to work with continuous audio representations and discrete tokens simultaneously as part of a single architecture. There has been a huge…

Sound · Computer Science 2024-12-20 Prateek Verma

In practice, deep neural networks have been found to be vulnerable to various types of noise, such as adversarial examples and corruption. Various adversarial defense methods have accordingly been developed to improve adversarial robustness…

Machine Learning · Computer Science 2020-12-24 Aishan Liu , Xianglong Liu , Chongzhi Zhang , Hang Yu , Qiang Liu , Dacheng Tao