Results 1 to 10 of about 388,430 (95)

Nerfstudio: A Modular Framework for Neural Radiance Field Development [PDF]

International Conference on Computer Graphics and Interactive Techniques, 2023
Neural Radiance Fields (NeRF) are a rapidly growing area of research with wide-ranging applications in computer vision, graphics, robotics, and more. In order to streamline the development and deployment of NeRF research, we propose a modular PyTorch ...
Matthew Tancik, Ethan Weber, Evonne Ng, Ruilong Li, Brent Yi, J. Kerr, Terrance Wang, Alexander Kristoffersen, J. Austin, Kamyar Salahi, A. Ahuja, David McAllister, Angjoo Kanazawa   +12 more
semanticscholar   +1 more source

Decomposed Prompting: A Modular Approach for Solving Complex Tasks [PDF]

International Conference on Learning Representations, 2022
Few-shot prompting is a surprisingly powerful way to use Large Language Models (LLMs) to solve various tasks. However, this approach struggles as the task complexity increases or when the individual reasoning steps of the task themselves are hard to ...
Tushar Khot, H. Trivedi, Matthew Finlayson, Yao Fu, Kyle Richardson, Peter Clark, Ashish Sabharwal   +6 more
semanticscholar   +1 more source

Modular Deep Learning [PDF]

Trans. Mach. Learn. Res., 2023
Transfer learning has recently become the dominant paradigm of machine learning. Pre-trained models fine-tuned for downstream tasks achieve better performance with fewer labelled examples.
Jonas Pfeiffer, Sebastian Ruder, Ivan Vulic, E. Ponti   +3 more
semanticscholar   +1 more source

DEMix Layers: Disentangling Domains for Modular Language Modeling [PDF]

North American Chapter of the Association for Computational Linguistics, 2021
We introduce a new domain expert mixture (DEMix) layer that enables conditioning a language model (LM) on the domain of the input text. A DEMix layer includes a collection of expert feedforward networks, each specialized to a domain, that makes the LM ...
Suchin Gururangan, Michael Lewis, Ari Holtzman, Noah A. Smith, Luke Zettlemoyer   +4 more
semanticscholar   +1 more source

Deep Modular Co-Attention Networks for Visual Question Answering [PDF]

Computer Vision and Pattern Recognition, 2019
Visual Question Answering (VQA) requires a fine-grained and simultaneous understanding of both the visual content of images and the textual content of questions.
Zhou Yu, Jun Yu, Yuhao Cui, D. Tao, Q. Tian   +4 more
semanticscholar   +1 more source

MAttNet: Modular Attention Network for Referring Expression Comprehension [PDF]

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018
In this paper, we address referring expression comprehension: localizing an image region described by a natural language expression. While most recent work treats expressions as a single unit, we propose to decompose them into three modular components ...
Licheng Yu, Zhe L. Lin, Xiaohui Shen, Jimei Yang, Xin Lu, Mohit Bansal, Tamara L. Berg   +6 more
semanticscholar   +1 more source

Modular Multilevel Converters: Recent Achievements and Challenges

IEEE Open Journal of the Industrial Electronics Society, 2021
The modular multilevel converter (MMC) is currently one of the power converter topologies which has attracted more research and development worldwide. Its features, such as high quality of voltages and currents, high modularity and high voltage rating ...
M. Pérez, S. Ceballos, G. Konstantinou, J. Pou, R. Aguilera   +4 more
semanticscholar   +1 more source

FIRE6: Feynman Integral REduction with modular arithmetic [PDF]

Computer Physics Communications, 2019
FIRE is a program performing reduction of Feynman integrals to master integrals. The C++ version of FIRE was presented in 2014. There have been multiple changes and upgrades since then including the possibility to use multiple computers for one reduction
Alexander V. Smirnov, Alexander V. Smirnov, F. S. Chukharev   +2 more
semanticscholar   +1 more source

Analyticity and the Unruh effect: a study of local modular flow [PDF]

Journal of High Energy Physics
The Unruh effect can be formulated as the statement that the Minkowski vacuum in a Rindler wedge has a boost as its modular flow. In recent years, other examples of states with geometrically local modular flow have played important roles in understanding
J. Sorce
semanticscholar   +1 more source

Industrialització i nou disseny de la construcció

Temes de Disseny, 2012
Compact Habit es una empresa que, mitjançant una resposta dinàmica i una labor basada en la innovació, ha generat un nou paradigma a partir de la industrialització i un nou disseny de la construcció.
Miguel Morte
doaj   +4 more sources