Zobrazeno 51 - 60
of 510 414
pro vyhledávání: '"Computer Science - Artificial Intelligence"'
The discourse on risks from advanced AI systems ("AIs") typically focuses on misuse, accidents and loss of control, but the question of AIs' moral status could have negative impacts which are of comparable significance and could be realised within si
Externí odkaz:
http://arxiv.org/abs/2408.04771
Autor:
Farkya, Saurabh, Daniels, Zachary Alan, Raghavan, Aswin, van der Wal, Gooitzen, Isnardi, Michael, Piacentino, Michael, Zhang, David
Recent advancements in sensors have led to high resolution and high data throughput at the pixel level. Simultaneously, the adoption of increasingly large (deep) neural networks (NNs) has lead to significant progress in computer vision. Currently, vi
Externí odkaz:
http://arxiv.org/abs/2408.04767
We introduce uncertainty-aware object instance segmentation (UncOS) and demonstrate its usefulness for embodied interactive segmentation. To deal with uncertainty in robot perception, we propose a method for generating a hypothesis distribution of ob
Externí odkaz:
http://arxiv.org/abs/2408.04760
Autor:
Vaughan, Anna, Mateo-Garcia, Gonzalo, Irakulis-Loitxate, Itziar, Watine, Marc, Fernandez-Poblaciones, Pablo, Turner, Richard E., Requeima, James, Gorroño, Javier, Randles, Cynthia, Caltagirone, Manfredi, Cifarelli, Claudio
Mitigating methane emissions is the fastest way to stop global warming in the short-term and buy humanity time to decarbonise. Despite the demonstrated ability of remote sensing instruments to detect methane plumes, no system has been available to ro
Externí odkaz:
http://arxiv.org/abs/2408.04745
We share observations and challenges from an ongoing effort to implement Explainable AI (XAI) in a domain-specific workflow for cybersecurity analysts. Specifically, we briefly describe a preliminary case study on the use of XAI for source code class
Externí odkaz:
http://arxiv.org/abs/2408.04746
Transformers have made significant strides across various artificial intelligence domains, including natural language processing, computer vision, and audio processing. This success has naturally garnered considerable interest from both academic and
Externí odkaz:
http://arxiv.org/abs/2408.04723
Autor:
Ding, Zifeng, Li, Yifeng, He, Yuan, Norelli, Antonio, Wu, Jingcheng, Tresp, Volker, Ma, Yunpu, Bronstein, Michael
Learning useful representations for continuous-time dynamic graphs (CTDGs) is challenging, due to the concurrent need to span long node interaction histories and grasp nuanced temporal details. In particular, two problems emerge: (1) Encoding longer
Externí odkaz:
http://arxiv.org/abs/2408.04713
Autor:
Huang, Jiawei, Zhang, Chen, Ren, Yi, Jiang, Ziyue, Ye, Zhenhui, Liu, Jinglin, He, Jinzheng, Yin, Xiang, Zhao, Zhou
Voice conversion aims to modify the source speaker's voice to resemble the target speaker while preserving the original speech content. Despite notable advancements in voice conversion these days, multi-lingual voice conversion (including both monoli
Externí odkaz:
http://arxiv.org/abs/2408.04708
Visual analytics is essential for studying large time series due to its ability to reveal trends, anomalies, and insights. DeepVATS is a tool that merges Deep Learning (Deep) with Visual Analytics (VA) for the analysis of large time series data (TS).
Externí odkaz:
http://arxiv.org/abs/2408.04692
Autor:
Wretblad, Niklas, Holmström, Oskar, Larsson, Erik, Wiksäter, Axel, Söderlund, Oscar, Öhman, Hjalmar, Pontén, Ture, Forsberg, Martin, Sörme, Martin, Heintz, Fredrik
Relational databases often suffer from uninformative descriptors of table contents, such as ambiguous columns and hard-to-interpret values, impacting both human users and Text-to-SQL models. This paper explores the use of large language models (LLMs)
Externí odkaz:
http://arxiv.org/abs/2408.04691