Zobrazeno 1 - 10
of 2 944
pro vyhledávání: '"Hofmann Thomas"'
Recent advances in text-to-image customization have enabled high-fidelity, context-rich generation of personalized images, allowing specific concepts to appear in a variety of scenarios. However, current methods struggle with combining multiple perso
Externí odkaz:
http://arxiv.org/abs/2412.09622
We propose MegaPortrait. It's an innovative system for creating personalized portrait images in computer vision. It has three modules: Identity Net, Shading Net, and Harmonization Net. Identity Net generates learned identity using a customized model
Externí odkaz:
http://arxiv.org/abs/2411.04357
Autor:
Joudaki, Amir, Hofmann, Thomas
Understanding how neural networks transform input data across layers is fundamental to unraveling their learning and generalization capabilities. Although prior work has used insights from kernel methods to study neural networks, a global analysis of
Externí odkaz:
http://arxiv.org/abs/2410.20107
Text generation, a key component in applications such as dialogue systems, relies on decoding algorithms that sample strings from a language model distribution. Traditional methods, such as top-$k$ and top-$\pi$, apply local normalisation to the mode
Externí odkaz:
http://arxiv.org/abs/2410.10810
Autor:
Stefanache, Stefan, Pérez, Lluís Pastor, Watanabe, Julen Costa, Tejedor, Ernesto Sanchez, Hofmann, Thomas, Simsar, Enis
Evaluating diffusion-based image-editing models is a crucial task in the field of Generative AI. Specifically, it is imperative to assess their capacity to execute diverse editing tasks while preserving the image content and realism. While recent dev
Externí odkaz:
http://arxiv.org/abs/2410.05710
At a time when the influence of generative Artificial Intelligence on visual arts is a highly debated topic, we raise the attention towards a more subtle phenomenon: the algorithmic censorship of artistic nudity online. We analyze the performance of
Externí odkaz:
http://arxiv.org/abs/2409.17156
Continual learning is the problem of integrating new information in a model while retaining the knowledge acquired in the past. Despite the tangible improvements achieved in recent years, the problem of continual learning is still an open one. A bett
Externí odkaz:
http://arxiv.org/abs/2407.16611
Autor:
Singh, Sidak Pal, Adilova, Linara, Kamp, Michael, Fischer, Asja, Schölkopf, Bernhard, Hofmann, Thomas
The presence of linear paths in parameter space between two different network solutions in certain cases, i.e., linear mode connectivity (LMC), has garnered interest from both theoretical and practical fronts. There has been significant research that
Externí odkaz:
http://arxiv.org/abs/2406.16300
Language Modelling has been a central part of Natural Language Processing for a very long time and in the past few years LSTM-based language models have been the go-to method for commercial language modeling. Recently, it has been shown that when loo
Externí odkaz:
http://arxiv.org/abs/2406.10256
Publikováno v:
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (2024)
Understanding memorisation in language models has practical and societal implications, e.g., studying models' training dynamics or preventing copyright infringements. Prior work defines memorisation as the causal effect of training with an instance o
Externí odkaz:
http://arxiv.org/abs/2406.04327