Zobrazeno 1 - 10
of 2 920
pro vyhledávání: '"Suau, A."'
Autor:
Rodriguez, Pau, Blaas, Arno, Klein, Michal, Zappella, Luca, Apostoloff, Nicholas, Cuturi, Marco, Suau, Xavier
The increasing capabilities of large generative models and their ever more widespread deployment have raised concerns about their reliability, safety, and potential misuse. To address these issues, recent works have proposed to control model generati
Externí odkaz:
http://arxiv.org/abs/2410.23054
Autor:
Suau, Xavier, Delobelle, Pieter, Metcalf, Katherine, Joulin, Armand, Apostoloff, Nicholas, Zappella, Luca, Rodríguez, Pau
An important issue with Large Language Models (LLMs) is their undesired ability to generate toxic language. In this work, we show that the neurons responsible for toxicity can be determined by their power to discriminate toxic sentences, and that tox
Externí odkaz:
http://arxiv.org/abs/2407.12824
Publikováno v:
Airlines and the COVID-19 Pandemic
Parallelization techniques have become ubiquitous for accelerating inference and training of deep neural networks. Despite this, several operations are still performed in a sequential manner. For instance, the forward and backward passes are executed
Externí odkaz:
http://arxiv.org/abs/2309.16318
Autor:
Busbridge, Dan, Ramapuram, Jason, Ablin, Pierre, Likhomanenko, Tatiana, Dhekane, Eeshan Gunesh, Suau, Xavier, Webb, Russ
Preserving training dynamics across batch sizes is an important tool for practical machine learning as it enables the trade-off between batch size and wall-clock time. This trade-off is typically enabled by a scaling rule, for example, in stochastic
Externí odkaz:
http://arxiv.org/abs/2307.13813
Autor:
Rodríguez-Gálvez, Borja, Blaas, Arno, Rodríguez, Pau, Goliński, Adam, Suau, Xavier, Ramapuram, Jason, Busbridge, Dan, Zappella, Luca
The mechanisms behind the success of multi-view self-supervised learning (MVSSL) are not yet fully understood. Contrastive MVSSL methods have been studied through the lens of InfoNCE, a lower bound of the Mutual Information (MI). However, the relatio
Externí odkaz:
http://arxiv.org/abs/2307.10907
Autor:
Suau, Xavier, Danieli, Federico, Keller, T. Anderson, Blaas, Arno, Huang, Chen, Ramapuram, Jason, Busbridge, Dan, Zappella, Luca
Multiview Self-Supervised Learning (MSSL) is based on learning invariances with respect to a set of input transformations. However, invariance partially or totally removes transformation-related information from the representations, which might harm
Externí odkaz:
http://arxiv.org/abs/2306.16058
Reinforcement learning agents tend to develop habits that are effective only under specific policies. Following an initial exploration phase where agents try out different actions, they eventually converge onto a particular policy. As this occurs, th
Externí odkaz:
http://arxiv.org/abs/2306.02419
Autor:
Sneha Vishwanath, George William Carnell, Martina Billmeier, Luis Ohlendorf, Patrick Neckermann, Benedikt Asbach, Charlotte George, Maria Suau Sans, Andrew Chan, Joey Olivier, Angalee Nadesalingam, Sebastian Einhauser, Nigel Temperton, Diego Cantoni, Joe Grove, Ingo Jordan, Volker Sandig, Paul Tonks, Johannes Geiger, Christian Dohmen, Verena Mummert, Anne Rosalind Samuel, Christian Plank, Rebecca Kinsley, Ralf Wagner, Jonathan Luke Heeney
Publikováno v:
npj Vaccines, Vol 9, Iss 1, Pp 1-9 (2024)
Abstract Updates of SARS-CoV-2 vaccines are required to generate immunity in the population against constantly evolving SARS-CoV-2 variants of concerns (VOCs). Here we describe three novel in-silico designed spike-based antigens capable of inducing n
Externí odkaz:
https://doaj.org/article/82ef274560d34dc98c35687c198efcf5
Lack of diversity in data collection has caused significant failures in machine learning (ML) applications. While ML developers perform post-collection interventions, these are time intensive and rarely comprehensive. Thus, new methods to track & man
Externí odkaz:
http://arxiv.org/abs/2301.10319