English
Related papers

Related papers: SuperShaper: Task-Agnostic Super Pre-training of B…

200 papers

Industrial design evaluation often relies on high-fidelity simulations of governing partial differential equations (PDEs). While accurate, these simulations are computationally expensive, making dense exploration of design spaces…

Machine Learning · Computer Science 2025-10-01 Zhizhou Zhang , Youjia Wu , Kaixuan Zhang , Yanjia Wang

Task vector composition has emerged as a promising paradigm for editing pre-trained models, enabling model merging through addition and unlearning through subtraction. Fine-tuning in the tangent space of a pre-trained model (linear…

Machine Learning · Computer Science 2026-05-25 Thomas Sommariva , Francesca Morandi , Simone Calderara , Angelo Porrello

We propose and demonstrate a generative deep learning approach for the shape recognition of an arbitrary object from its acoustic scattering properties. The strategy exploits deep neural networks to learn the mapping between the latent…

Sound · Computer Science 2022-07-13 W. W. Ahmed , M. Farhat , P. -Y. Chen , X. Zhang , Y. Wu

Deep pre-trained Transformer models have achieved state-of-the-art results over a variety of natural language processing (NLP) tasks. By learning rich language knowledge with millions of parameters, these models are usually…

Computation and Language · Computer Science 2020-11-10 Zhengyan Zhang , Fanchao Qi , Zhiyuan Liu , Qun Liu , Maosong Sun

Sparse neural networks are important for achieving better generalization and enhancing computation efficiency. This paper proposes a novel learning approach to obtain sparse fully connected layers in neural networks (NNs) automatically. We…

Machine Learning · Computer Science 2021-04-28 Mengqiao Han , Xiabi Liu , Zhaoyang Hai , Zhengwen Li

Neural Architecture Search (NAS) has emerged as a key tool in identifying optimal configurations of deep neural networks tailored to specific tasks. However, training and assessing numerous architectures introduces considerable…

Machine Learning · Computer Science 2024-04-25 Haoming Zhang , Ran Cheng

Though deep learning methods have shown great success in 3D point cloud part segmentation, they generally rely on a large volume of labeled training data, which makes the model suffer from unsatisfied generalization abilities to unseen…

Computer Vision and Pattern Recognition · Computer Science 2021-10-12 Yu Hao , Yi Fang

Task arithmetic has recently emerged as a cost-effective and scalable approach to edit pre-trained models directly in weight space: By adding the fine-tuned weights of different tasks, the model's performance can be improved on these tasks,…

Machine Learning · Computer Science 2023-11-22 Guillermo Ortiz-Jimenez , Alessandro Favero , Pascal Frossard

Deep neural networks are typically trained under a supervised learning framework where a model learns a single task using labeled data. Instead of relying solely on labeled data, practitioners can harness unlabeled or related data to…

Machine Learning · Computer Science 2020-07-03 Huanru Henry Mao

Anomaly detection tools and methods present a key capability in modern cyberphysical and failure prediction systems. Despite the fast-paced development in deep learning architectures for anomaly detection, model optimization for a given…

Machine Learning · Computer Science 2023-05-29 Marcin Pietron , Dominik Zurek , Kamil Faber , Roberto Corizzo

Neural networks are trained by choosing an architecture and training the parameters. The choice of architecture is often by trial and error or with Neural Architecture Search (NAS) methods. While NAS provides some automation, it often…

Machine Learning · Computer Science 2024-10-14 Zitong Huang , Mansooreh Montazerin , Ajitesh Srivastava

Large pretrained language models are widely used in downstream NLP tasks via task-specific fine-tuning, but such procedures can be costly. Recently, Parameter-Efficient Fine-Tuning (PEFT) methods have achieved strong task performance while…

Computation and Language · Computer Science 2024-01-30 Han Zhou , Xingchen Wan , Ivan Vulić , Anna Korhonen

Weight sharing, as an approach to speed up architecture performance estimation has received wide attention. Instead of training each architecture separately, weight sharing builds a supernet that assembles all the architectures as its…

Machine Learning · Computer Science 2021-05-06 Yuge Zhang , Quanlu Zhang , Yaming Yang

Deep neural networks have emerged as powerful tools for learning operators defined over infinite-dimensional function spaces. However, existing theories frequently encounter difficulties related to dimensionality and limited…

Machine Learning · Computer Science 2026-05-12 Jianfei Li , Shuo Huang , Han Feng , Ding-Xuan Zhou , Gitta Kutyniok

Though the transformer architectures have shown dominance in many natural language understanding tasks, there are still unsolved issues for the training of transformer models, especially the need for a principled way of warm-up which has…

Computation and Language · Computer Science 2021-06-01 Wei Zhu , Xiaoling Wang , Xipeng Qiu , Yuan Ni , Guotong Xie

Neural architecture search (NAS) has fostered various fields of machine learning. Despite its prominent dedications, many have criticized the intrinsic limitations of high computational cost. We aim to ameliorate this by proposing a…

Machine Learning · Computer Science 2021-03-16 Kwanghee Choi , Minyoung Choe , Hyelee Lee

The simulation of nanophotonic structures relies on electromagnetic solvers, which play a crucial role in understanding their behavior. However, these solvers often come with a significant computational cost, making their application in…

Machine Learning · Computer Science 2024-05-22 Liang Cheng , Prashant Singh , Francesco Ferranti

Many hardware-aware neural architecture search (NAS) methods have been developed to optimize the topology of neural networks (NN) with the joint objectives of higher accuracy and lower latency. Recently, both accuracy and latency predictors…

Machine Learning · Computer Science 2023-06-06 Yash Akhauri , Mohamed S. Abdelfattah

Machine-learned surrogate models to accelerate lengthy computer simulations are becoming increasingly important as engineers look to streamline the product design cycle. In many cases, these approaches offer the ability to predict relevant…

Machine Learning · Computer Science 2024-10-10 Kevin Ferguson , Yu-hsuan Chen , Yiming Chen , Andrew Gillman , James Hardin , Levent Burak Kara

Neural Architecture Search (NAS) has been widely studied for designing discriminative deep learning models such as image classification, object detection, and semantic segmentation. As a large number of priors have been obtained through the…

Computer Vision and Pattern Recognition · Computer Science 2019-06-07 Jie An , Haoyi Xiong , Jinwen Ma , Jiebo Luo , Jun Huan