English
Related papers

Related papers: A Study on Transformer Configuration and Training …

200 papers

In deep learning, models typically reuse the same parameters for all inputs. Mixture of Experts (MoE) defies this and instead selects different parameters for each incoming example. The result is a sparsely-activated model -- with…

Machine Learning · Computer Science 2022-06-20 William Fedus , Barret Zoph , Noam Shazeer

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

Overparameterized transformer networks have obtained state of the art results in various natural language processing tasks, such as machine translation, language modeling, and question answering. These models contain hundreds of millions of…

Machine Learning · Computer Science 2019-09-26 Angela Fan , Edouard Grave , Armand Joulin

It is generally thought that transformer-based large language models benefit from pre-training by learning generic linguistic knowledge that can be focused on a specific task during fine-tuning. However, we propose that much of the benefit…

Computation and Language · Computer Science 2024-06-19 Anna C. Marbut , John W. Chandler , Travis J. Wheeler

We introduce a novel self-supervised learning framework that automatically learns representations from input computer-aided design (CAD) models for downstream tasks, including part classification, modeling segmentation, and machining…

Graphics · Computer Science 2026-03-18 Yifei Li , Kang Wu , Wenming Wu , Xiao-Ming Fu

Pre-trained language models have recently emerged as a powerful tool for fine-tuning a variety of language tasks. Ideally, when models are pre-trained on large amount of data, they are expected to gain implicit knowledge. In this paper, we…

Computation and Language · Computer Science 2023-06-22 Mohamad Ballout , Ulf Krumnack , Gunther Heidemann , Kai-Uwe Kühnberger

We explore deep autoregressive Transformer models in language modeling for speech recognition. We focus on two aspects. First, we revisit Transformer model configurations specifically for language modeling. We show that well configured…

Computation and Language · Computer Science 2019-09-25 Kazuki Irie , Albert Zeyer , Ralf Schlüter , Hermann Ney

We show how bidirectional transformers trained for masked token prediction can be applied to neural image compression to achieve state-of-the-art results. Such models were previously used for image generation by progressivly sampling groups…

Image and Video Processing · Electrical Eng. & Systems 2023-04-18 Fabian Mentzer , Eirikur Agustsson , Michael Tschannen

Deep neural networks are capable of learning powerful representations to tackle complex vision tasks but expose undesirable properties like the over-fitting issue. To this end, regularization techniques like image augmentation are necessary…

Computer Vision and Pattern Recognition · Computer Science 2025-04-17 Haohang Xu , Shuangrui Ding , Manqi Zhao , Dongsheng Jiang

Transformers have gained popularity in the software engineering (SE) literature. These deep learning models are usually pre-trained through a self-supervised objective, meant to provide the model with basic knowledge about a language of…

Software Engineering · Computer Science 2023-02-09 Rosalia Tufano , Luca Pascarella , Gabriele Bavota

Transformer has been widely used for self-supervised pre-training in Natural Language Processing (NLP) and achieved great success. However, it has not been fully explored in visual self-supervised learning. Meanwhile, previous methods only…

Computer Vision and Pattern Recognition · Computer Science 2021-10-26 Zhaowen Li , Zhiyang Chen , Fan Yang , Wei Li , Yousong Zhu , Chaoyang Zhao , Rui Deng , Liwei Wu , Rui Zhao , Ming Tang , Jinqiao Wang

State-of-the-art performance on language understanding tasks is now achieved with increasingly large networks; the current record holder has billions of parameters. Given a language model pre-trained on massive unlabeled text corpora, only…

Computation and Language · Computer Science 2020-04-30 Evani Radiya-Dixit , Xin Wang

Learning with large-scale unlabeled data has become a powerful tool for pre-training Visual Transformers (VTs). However, prior works tend to overlook that, in real-world scenarios, the input data may be corrupted and unreliable.…

Computer Vision and Pattern Recognition · Computer Science 2023-04-13 Tianjiao Li , Lin Geng Foo , Ping Hu , Xindi Shang , Hossein Rahmani , Zehuan Yuan , Jun Liu

Transformers have been recently adapted for large scale image classification, achieving high scores shaking up the long supremacy of convolutional neural networks. However the optimization of image transformers has been little studied so…

Computer Vision and Pattern Recognition · Computer Science 2021-04-08 Hugo Touvron , Matthieu Cord , Alexandre Sablayrolles , Gabriel Synnaeve , Hervé Jégou

Supervised speech enhancement methods have been very successful. However, in practical scenarios, there is a lack of clean speech, and self-supervised learning-based (SSL) speech enhancement methods that offer comparable enhancement…

Sound · Computer Science 2026-02-03 Rajalaxmi Rajagopalan , Ritwik Giri , Zhiqiang Tang , Kyu Han

Speech recognition technologies are gaining enormous popularity in various industrial applications. However, building a good speech recognition system usually requires large amounts of transcribed data, which is expensive to collect. To…

Computation and Language · Computer Science 2019-11-01 Dongwei Jiang , Xiaoning Lei , Wubo Li , Ne Luo , Yuxuan Hu , Wei Zou , Xiangang Li

Transformer-based models attain excellent results and generalize well when trained on sufficient amounts of data. However, constrained by the limited data available in the audio domain, most transformer-based models for audio tasks are…

Sound · Computer Science 2022-04-28 Dading Chong , Helin Wang , Peilin Zhou , Qingcheng Zeng

We empirically demonstrate that a transformer pre-trained on country-scale unlabeled human mobility data learns embeddings capable, through fine-tuning, of developing a deep understanding of the target geography and its corresponding…

Computers and Society · Computer Science 2024-12-13 Alameen Najjar

Transformers have transformed modern machine learning, driving breakthroughs in computer vision, natural language processing, and robotics. At the core of their success lies the attention mechanism, which enables the modeling of global…

Computer Vision and Pattern Recognition · Computer Science 2025-10-07 Hemanth Saratchandran , Simon Lucey

The Transformer architecture deeply changed the natural language processing, outperforming all previous state-of-the-art models. However, well-known Transformer models like BERT, RoBERTa, and GPT-2 require a huge compute budget to create a…

Computation and Language · Computer Science 2021-04-21 Luca Di Liello , Matteo Gabburo , Alessandro Moschitti