Zobrazeno 1 - 10
of 29
pro vyhledávání: '"Esperança, Pedro M."'
LoRA-Guard: Parameter-Efficient Guardrail Adaptation for Content Moderation of Large Language Models
Guardrails have emerged as an alternative to safety alignment for content moderation of large language models (LLMs). Existing model-based guardrails have not been designed for resource-constrained computational portable devices, such as mobile phone
Externí odkaz:
http://arxiv.org/abs/2407.02987
Searching for the architecture cells is a dominant paradigm in NAS. However, little attention has been devoted to the analysis of the cell-based search spaces even though it is highly important for the continual development of NAS. In this work, we c
Externí odkaz:
http://arxiv.org/abs/2203.08887
Autor:
Parisot, Sarah, Esperanca, Pedro M., McDonagh, Steven, Madarasz, Tamas J., Yang, Yongxin, Li, Zhenguo
In this work, we introduce a novel strategy for long-tail recognition that addresses the tail classes' few-shot problem via training-free knowledge transfer. Our objective is to transfer knowledge acquired from information-rich common classes to sema
Externí odkaz:
http://arxiv.org/abs/2112.06741
The standard paradigm in Neural Architecture Search (NAS) is to search for a fully deterministic architecture with specific operations and connections. In this work, we instead propose to search for the optimal operation distribution, thus providing
Externí odkaz:
http://arxiv.org/abs/2111.04670
State-of-the-art results in deep learning have been improving steadily, in good part due to the use of larger models. However, widespread use is constrained by device hardware limitations, resulting in a substantial performance gap between state-of-t
Externí odkaz:
http://arxiv.org/abs/2111.03555
Neural Architecture Search (NAS) is an exciting new field which promises to be as much as a game-changer as Convolutional Neural Networks were in 2012. Despite many great works leading to substantial improvements on a variety of tasks, comparison bet
Externí odkaz:
http://arxiv.org/abs/1912.12522
Autor:
Lopes, Vasco, Carlucci, Fabio Maria, Esperança, Pedro M, Singh, Marco, Gabillon, Victor, Yang, Antoine, Xu, Hang, Chen, Zewei, Wang, Jun
The Neural Architecture Search (NAS) problem is typically formulated as a graph search problem where the goal is to learn the optimal operations over edges in order to maximise a graph-level global objective. Due to the large architecture parameter s
Externí odkaz:
http://arxiv.org/abs/1909.01051
Autor:
Esperança, Pedro M.
Advances in technology have now made it possible to monitor heart rate, body temperature and sleep patterns; continuously track movement; record brain activity; and sequence DNA in the jungle --- all using devices that fit in the palm of a hand. The
Externí odkaz:
https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.724894
Information that is stored in an encrypted format is, by definition, usually not amenable to statistical analysis or machine learning methods. In this paper we present detailed analysis of coordinate and accelerated gradient descent algorithms which
Externí odkaz:
http://arxiv.org/abs/1703.00839
We present two new statistical machine learning methods designed to learn on fully homomorphic encrypted (FHE) data. The introduction of FHE schemes following Gentry (2009) opens up the prospect of privacy preserving statistical machine learning anal
Externí odkaz:
http://arxiv.org/abs/1508.06845