English
Related papers

Related papers: FlexiBERT: Are Current Transformer Architectures t…

200 papers

While hardware-software co-design has significantly improved the efficiency of neural network inference, modeling the training phase remains a critical yet underexplored challenge. Training workloads impose distinct constraints,…

Machine Learning · Computer Science 2026-03-17 Jérémy Morlier , Robin Geens , Stef Cuyckens , Arne Symons , Marian Verhelst , Vincent Gripon , Mathieu Léonardon

The BERT model has shown significant success on various natural language processing tasks. However, due to the heavy model size and high computational cost, the model suffers from high latency, which is fatal to its deployments on…

Computation and Language · Computer Science 2021-02-22 Seohyeong Jeong , Nojun Kwak

Transformer-based masked language models such as BERT, trained on general corpora, have shown impressive performance on downstream tasks. It has also been demonstrated that the downstream task performance of such models can be improved by…

Computation and Language · Computer Science 2023-05-04 Zhi Hong , Aswathy Ajith , Gregory Pauloski , Eamon Duede , Kyle Chard , Ian Foster

Recent research has shown that large language models (LLMs) can utilize low-precision floating point (FP) quantization to deliver high efficiency while maintaining original model accuracy. In particular, recent works have shown the…

Hardware Architecture · Computer Science 2025-06-05 Faraz Tahmasebi , Yian Wang , Benji Y. H. Huang , Hyoukjun Kwon

Fine-tuning BERT-based models is resource-intensive in memory, computation, and time. While many prior works aim to improve inference efficiency via compression techniques, e.g., pruning, these works do not explicitly address the…

Computation and Language · Computer Science 2022-08-04 Danilo Vucetic , Mohammadreza Tayaranian , Maryam Ziaeefard , James J. Clark , Brett H. Meyer , Warren J. Gross

Weight-sharing supernets are crucial for performance estimation in cutting-edge neural architecture search (NAS) frameworks. Despite their ability to generate diverse subnetworks without retraining, the quality of these subnetworks is not…

Designing effective architectures is one of the key factors behind the success of deep neural networks. Existing deep architectures are either manually designed or automatically searched by some Neural Architecture Search (NAS) methods.…

Computer Vision and Pattern Recognition · Computer Science 2021-02-23 Yong Guo , Yin Zheng , Mingkui Tan , Qi Chen , Zhipeng Li , Jian Chen , Peilin Zhao , Junzhou Huang

To discover powerful yet compact models is an important goal of neural architecture search. Previous two-stage one-shot approaches are limited by search space with a fixed depth. It seems handy to include an additional skip connection in…

Machine Learning · Computer Science 2021-08-17 Xiangxiang Chu , Bo Zhang , Qingyuan Li , Ruijun Xu , Xudong Li

Transformer architectures based on the attention mechanism have revolutionized natural language processing (NLP), driving major breakthroughs across virtually every NLP task. However, their substantial memory and computational requirements…

Computation and Language · Computer Science 2026-03-25 Riccardo Bravin , Massimo Pavan , Hazem Hesham Yousef Shalby , Fabrizio Pittorino , Manuel Roveri

Large, self-supervised transformer-based language representation models have recently received significant amounts of attention, and have produced state-of-the-art results across a variety of tasks simply by scaling up pre-training on…

Computation and Language · Computer Science 2019-10-25 Alexandre Matton , Luke de Oliveira

Deep learning models have proven to be successful in a wide range of machine learning tasks. Yet, they are often highly sensitive to perturbations on the input data which can lead to incorrect decisions with high confidence, hampering their…

Machine Learning · Computer Science 2023-06-13 Steffen Jung , Jovita Lukasik , Margret Keuper

With the shift towards on-device deep learning, ensuring a consistent behavior of an AI service across diverse compute platforms becomes tremendously important. Our work tackles the emergent problem of reducing predictive inconsistencies…

Computer Vision and Pattern Recognition · Computer Science 2022-09-29 Rahul Duggal , Hao Zhou , Shuo Yang , Jun Fang , Yuanjun Xiong , Wei Xia

Transformers-based models, such as BERT, have dramatically improved the performance for various natural language processing tasks. The clinical knowledge enriched model, namely ClinicalBERT, also achieved state-of-the-art results when…

Computation and Language · Computer Science 2022-04-18 Yikuan Li , Ramsey M. Wehbe , Faraz S. Ahmad , Hanyin Wang , Yuan Luo

Hypergraphs are characterized by complex topological structure, representing higher-order interactions among multiple entities through hyperedges. Lately, hypergraph-based deep learning methods to learn informative data representations for…

Machine Learning · Computer Science 2024-09-30 Adrián Bazaga , Pietro Liò , Gos Micklem

Adapting language models to new data distributions by simple finetuning is challenging. This is due to the rigidity of their subword tokenizers, which typically remain unchanged during adaptation. This inflexibility often leads to…

Computation and Language · Computer Science 2026-05-14 Abraham Toluwase Owodunni , Orevaoghene Ahia , Sachin Kumar

A surrogate-based topology optimisation algorithm for linear elastic structures under parametric loads and boundary conditions is proposed. Instead of learning the parametric solution of the state (and adjoint) problems or the optimisation…

Numerical Analysis · Mathematics 2025-11-04 Matteo Giacomini , Antonio Huerta

Transformer based architectures have become de-facto models used for a range of Natural Language Processing tasks. In particular, the BERT based models achieved significant accuracy gain for GLUE tasks, CoNLL-03 and SQuAD. However, BERT…

Computation and Language · Computer Science 2021-04-21 Sheng Shen , Zhen Dong , Jiayu Ye , Linjian Ma , Zhewei Yao , Amir Gholami , Michael W. Mahoney , Kurt Keutzer

Transformer-based language models utilize the attention mechanism for substantial performance improvements in almost all natural language processing (NLP) tasks. Similar attention structures are also extensively studied in several other…

Computation and Language · Computer Science 2023-05-17 Nurullah Sevim , Ege Ozan Özyedek , Furkan Şahinuç , Aykut Koç

Recent advances in autoregressive neural surrogate models have enabled orders-of-magnitude speedups in simulating dynamical systems. However, autoregressive models are generally prone to distribution drift: compounding errors in…

Machine Learning · Computer Science 2026-03-19 Qi Liu , Laure Zanna , Joan Bruna

Time-intensive performance evaluations significantly impede progress in Neural Architecture Search (NAS). To address this, neural predictors leverage surrogate models trained on proxy datasets, allowing for direct performance predictions…

Machine Learning · Computer Science 2025-09-24 Jindi Lv , Yuhao Zhou , Yuxin Tian , Qing Ye , Wentao Feng , Jiancheng Lv
‹ Prev 1 3 4 5 6 7 10 Next ›