From f21354605a3fdd58725f910724f16482aaf44301 Mon Sep 17 00:00:00 2001 From: Kristian Kersting Date: Fri, 20 Sep 2024 09:35:42 +0200 Subject: [PATCH] Update references.bib --- references.bib | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/references.bib b/references.bib index a45b373..70f7f7a 100644 --- a/references.bib +++ b/references.bib @@ -26,7 +26,7 @@ @misc{brack2024communityoscar title={Community OSCAR: A Community Effort for Multilingual Web Data}, author={Manuel Brack and Malte Ostendorff and Pedro Ortiz Suarez and José Javier Saiz and Iñaki Lacunza Castilla and Jorge Palomar-Giner and Patrick Schramowski and Georg Rehm and Marta Villegas and Kristian Kersting}, year={2024}, - Howpublished={preprint}, + Howpublished={Technical Report / Preprint}, Keywords={Large-scale Data, Dataset, LLM training, LLM, Multilingual}, Note={The development of large language models (LLMs) relies heavily on extensive, high-quality datasets. Publicly available datasets focus predominantly on English, leaving other language communities behind. To address this issue, we introduce Community OSCAR, a multilingual dataset initiative designed to address the gap between English and non-English data availability. Through a collective effort, Community OSCAR covers over 150 languages with 45 billion documents, totaling over 345 TiB of data. Initial results indicate that Community OSCAR provides valuable raw data for training LLMs and enhancing the performance of multilingual models. This work aims to contribute to the ongoing advancements in multilingual NLP and to support a more inclusive AI ecosystem by making high-quality, multilingual data more accessible to those working with low-resource languages.}, Anote={./images/brack2024communityoscar.png}, @@ -50,7 +50,7 @@ @misc{brack2024unleashing title={Unleashing Creativity: Generalizing Semantic Control for Text-to-Image Diffusion Models}, author={Manuel Brack and Marlon May and Linoy Tsaban and Felix Friedrich and Patrick Schramowski and Apolinaros Passos and Kristian Kersting }, year={2024}, - Howpublished={preprint}, + Howpublished={Technical Report / Preprint}, Keywords={Text-to-Image Synthesis, Text-Guided Image Generation, SEGA, Semantic Control, Diffusion Transformers}, Note={The recent surge in popularity of text-to-image diffusion models (DMs) can largely be attributed to the versatile, expressive, and intuitive user interfaces provided through textual prompts. These models enable inexperienced people to explore artistic ventures easily and provide exciting new opportunities to experienced artists. However, the semantic control offered through text prompts alone is limited and rather fragile, and overall lacks the fine granularity necessary for creative applications. The majority of methods addressing this issue are restricted to specific DM architectures, severely limiting the creative workflow instead of generalizing it to arbitrary models. In contrast, we demonstrate that semantic guidance (SEGA) generalizes to any DM architecture. Importantly, SEGA is natively compatible with state-of-the-art diffusion transformers. Our empirical results show strong model-agnostic performance, and we highlight new creative possibilities enabled by SEGA, such as enhanced typographic manipulations. This work underscores SEGA’s potential to provide consistent, high-quality semantic guidance in a rapidly evolving generative model landscape.}, Anote={./images/brack2024unleashing.png},