Zobrazeno 1 - 10
of 461
pro vyhledávání: '"Vidal, Rene"'
In this paper, we focus on a matrix factorization-based approach for robust low-rank and asymmetric matrix recovery from corrupted measurements. We address the challenging scenario where the rank of the sought matrix is unknown and employ an overpara
Externí odkaz:
http://arxiv.org/abs/2410.16826
The goal of continual learning (CL) is to train a model that can solve multiple tasks presented sequentially. Recent CL approaches have achieved strong performance by leveraging large pre-trained models that generalize well to downstream tasks. Howev
Externí odkaz:
http://arxiv.org/abs/2410.00645
Autor:
Deldjoo, Yashar, He, Zhankui, McAuley, Julian, Korikov, Anton, Sanner, Scott, Ramisa, Arnau, Vidal, Rene, Sathiamoorthy, Maheswaran, Kasrizadeh, Atoosa, Milano, Silvia, Ricci, Francesco
Generative models are a class of AI models capable of creating new instances of data by learning and sampling from their statistical distributions. In recent years, these models have gained prominence in machine learning due to the development of app
Externí odkaz:
http://arxiv.org/abs/2409.15173
Autor:
Ramisa, Arnau, Vidal, Rene, Deldjoo, Yashar, He, Zhankui, McAuley, Julian, Korikov, Anton, Sanner, Scott, Sathiamoorthy, Mahesh, Kasrizadeh, Atoosa, Milano, Silvia, Ricci, Francesco
Many recommendation systems limit user inputs to text strings or behavior signals such as clicks and purchases, and system outputs to a list of products sorted by relevance. With the advent of generative AI, users have come to expect richer levels of
Externí odkaz:
http://arxiv.org/abs/2409.10993
Autor:
Korikov, Anton, Sanner, Scott, Deldjoo, Yashar, He, Zhankui, McAuley, Julian, Ramisa, Arnau, Vidal, Rene, Sathiamoorthy, Mahesh, Kasrizadeh, Atoosa, Milano, Silvia, Ricci, Francesco
While previous chapters focused on recommendation systems (RSs) based on standardized, non-verbal user feedback such as purchases, views, and clicks -- the advent of LLMs has unlocked the use of natural language (NL) interactions for recommendation.
Externí odkaz:
http://arxiv.org/abs/2408.10946
Advancing representation learning in specialized fields like medicine remains challenging due to the scarcity of expert annotations for text and images. To tackle this issue, we present a novel two-stage framework designed to extract high-quality fac
Externí odkaz:
http://arxiv.org/abs/2407.01948
Autor:
Luo, Jinqi, Ding, Tianjiao, Chan, Kwan Ho Ryan, Thaker, Darshan, Chattopadhyay, Aditya, Callison-Burch, Chris, Vidal, René
Large Language Models (LLMs) are being used for a wide variety of tasks. While they are capable of generating human-like responses, they can also produce undesirable output including potentially harmful information, racist or sexist language, and hal
Externí odkaz:
http://arxiv.org/abs/2406.04331
Autor:
Min, Hancheng, Vidal, René
The implicit bias of gradient-based training algorithms has been considered mostly beneficial as it leads to trained networks that often generalize well. However, Frei et al. (2023) show that such implicit bias can harm adversarial robustness. Specif
Externí odkaz:
http://arxiv.org/abs/2405.15942
Recent work in adversarial robustness suggests that natural data distributions are localized, i.e., they place high probability in small volume regions of the input space, and that this property can be utilized for designing classifiers with improved
Externí odkaz:
http://arxiv.org/abs/2405.14176
Given an input set of $3$D point pairs, the goal of outlier-robust $3$D registration is to compute some rotation and translation that align as many point pairs as possible. This is an important problem in computer vision, for which many highly accura
Externí odkaz:
http://arxiv.org/abs/2404.00915