Zobrazeno 1 - 10
of 2 789
pro vyhledávání: '"P. Staab"'
Predicting answers to queries over knowledge graphs is called a complex reasoning task because answering a query requires subdividing it into subqueries. Existing query embedding methods use this decomposition to compute the embedding of a query as t
Externí odkaz:
http://arxiv.org/abs/2410.22105
Autor:
Zhou, Hongkuan, Halilaj, Lavdim, Monka, Sebastian, Schmid, Stefan, Zhu, Yuqicheng, Xiong, Bo, Staab, Steffen
Despite the remarkable success of deep neural networks (DNNs) in computer vision, they fail to remain high-performing when facing distribution shifts between training and testing data. In this paper, we propose Knowledge-Guided Visual representation
Externí odkaz:
http://arxiv.org/abs/2410.15981
Autor:
Gregucci, Cosimo, Xiong, Bo, Hernandez, Daniel, Loconte, Lorenzo, Minervini, Pasquale, Staab, Steffen, Vergari, Antonio
Complex query answering (CQA) on knowledge graphs (KGs) is gaining momentum as a challenging reasoning task. In this paper, we show that the current benchmarks for CQA are not really complex, and the way they are built distorts our perception of prog
Externí odkaz:
http://arxiv.org/abs/2410.12537
Autor:
Guldimann, Philipp, Spiridonov, Alexander, Staab, Robin, Jovanović, Nikola, Vero, Mark, Vechev, Velko, Gueorguieva, Anna, Balunović, Mislav, Konstantinov, Nikola, Bielik, Pavol, Tsankov, Petar, Vechev, Martin
The EU's Artificial Intelligence Act (AI Act) is a significant step towards responsible AI development, but lacks clear technical interpretation, making it difficult to assess models' compliance. This work presents COMPL-AI, a comprehensive framework
Externí odkaz:
http://arxiv.org/abs/2410.07959
Retrieval-Augmented Generation (RAG) improves LLMs by enabling them to incorporate external data during generation. This raises concerns for data owners regarding unauthorized use of their content in RAG systems. Despite its importance, the challenge
Externí odkaz:
http://arxiv.org/abs/2410.03537
LLM watermarks stand out as a promising way to attribute ownership of LLM-generated text. One threat to watermark credibility comes from spoofing attacks, where an unauthorized third party forges the watermark, enabling it to falsely attribute arbitr
Externí odkaz:
http://arxiv.org/abs/2410.02693
In autonomous driving, High Definition (HD) maps provide a complete lane model that is not limited by sensor range and occlusions. However, the generation and upkeep of HD maps involves periodic data collection and human annotations, limiting scalabi
Externí odkaz:
http://arxiv.org/abs/2409.12409
Attention mechanisms and Transformer architectures have revolutionized Natural Language Processing (NLP) by enabling exceptional modeling of long-range dependencies and capturing intricate linguistic patterns. However, their inherent reliance on line
Externí odkaz:
http://arxiv.org/abs/2409.12175
Autor:
Zhu, Yuqicheng, Potyka, Nico, Pan, Jiarong, Xiong, Bo, He, Yunjie, Kharlamov, Evgeny, Staab, Steffen
Knowledge graph embeddings (KGE) apply machine learning methods on knowledge graphs (KGs) to provide non-classical reasoning capabilities based on similarities and analogies. The learned KG embeddings are typically used to answer queries by ranking a
Externí odkaz:
http://arxiv.org/abs/2408.08248
Autor:
Zhu, Yuqicheng, Potyka, Nico, Nayyeri, Mojtaba, Xiong, Bo, He, Yunjie, Kharlamov, Evgeny, Staab, Steffen
Knowledge graph embedding (KGE) models are often used to predict missing links for knowledge graphs (KGs). However, multiple KG embeddings can perform almost equally well for link prediction yet give conflicting predictions for unseen queries. This p
Externí odkaz:
http://arxiv.org/abs/2408.08226