Zobrazeno 1 - 10
of 10 752
pro vyhledávání: '"Sokol, P"'
Continuous attractors offer a unique class of solutions for storing continuous-valued variables in recurrent system states for indefinitely long time intervals. Unfortunately, continuous attractors suffer from severe structural instability in general
Externí odkaz:
http://arxiv.org/abs/2408.00109
Autor:
Watts, Jake R., Sokol, Joel
This paper proposes a new method for preventing unsafe or otherwise low quality large language model (LLM) outputs, by leveraging the stochasticity of LLMs. We propose a system whereby LLM checkers vote on the acceptability of a generated output, reg
Externí odkaz:
http://arxiv.org/abs/2407.16994
Avoiding systemic discrimination requires investigating AI models' potential to propagate stereotypes resulting from the inherent biases of training datasets. Our study investigated how text-to-image models unintentionally perpetuate non-rational bel
Externí odkaz:
http://arxiv.org/abs/2407.16292
Autor:
Judge, Arnaud, Judge, Thierry, Duchateau, Nicolas, Sandler, Roman A., Sokol, Joseph Z., Bernard, Olivier, Jodoin, Pierre-Marc
Performance of deep learning segmentation models is significantly challenged in its transferability across different medical imaging domains, particularly when aiming to adapt these models to a target domain with insufficient annotated data for effec
Externí odkaz:
http://arxiv.org/abs/2406.17902
Publikováno v:
(2017) Applied Soft Computing, 60, 752-762
The categorization of retail products is essential for the business decision-making process. It is a common practice to classify products based on their quantitative and qualitative characteristics. In this paper we use a purely data-driven approach.
Externí odkaz:
http://arxiv.org/abs/2405.05218
Graph embeddings have emerged as a powerful tool for representing complex network structures in a low-dimensional space, enabling the use of efficient methods that employ the metric structure in the embedding space as a proxy for the topological stru
Externí odkaz:
http://arxiv.org/abs/2404.10784
Autor:
Sokol, Kacper, Vogt, Julia E.
Despite significant progress, evaluation of explainable artificial intelligence remains elusive and challenging. In this paper we propose a fine-grained validation framework that is not overly reliant on any one facet of these sociotechnical systems,
Externí odkaz:
http://arxiv.org/abs/2403.12730
Should prediction models always deliver a prediction? In the pursuit of maximum predictive performance, critical considerations of reliability and fairness are often overshadowed, particularly when it comes to the role of uncertainty. Selective regre
Externí odkaz:
http://arxiv.org/abs/2402.16300
Autor:
Krämer, Mathias, Favelukis, Bar, Sokol, Maxim, Rosen, Brian A., Eliaz, Noam, Kim, Se-Ho, Gault, Baptiste
2D materials are emerging as promising nanomaterials for applications in energy storage and catalysis. In the wet chemical synthesis of MXenes, these 2D transition metal carbides and nitrides are terminated with a variety of functional groups, and ca
Externí odkaz:
http://arxiv.org/abs/2311.18688
Automated decision-making systems are becoming increasingly ubiquitous, motivating an immediate need for their explainability. However, it remains unclear whether users know what insights an explanation offers and, more importantly, what information
Externí odkaz:
http://arxiv.org/abs/2309.08438