Zobrazeno 1 - 10
of 26 615
pro vyhledávání: '"A. Schoen"'
Autor:
Meinke, Alexander, Schoen, Bronson, Scheurer, Jérémy, Balesni, Mikita, Shah, Rusheb, Hobbhahn, Marius
Frontier models are increasingly trained and deployed as autonomous agent. One safety concern is that AI agents might covertly pursue misaligned goals, hiding their true capabilities and objectives - also known as scheming. We study whether models ha
Externí odkaz:
http://arxiv.org/abs/2412.04984
Autor:
Liu, Ruiping, Zhang, Jiaming, Schön, Angela, Müller, Karin, Zheng, Junwei, Yang, Kailun, Gerling, Kathrin, Stiefelhagen, Rainer
Assistive technology can be leveraged by blind people when searching for objects in their daily lives. We created ObjectFinder, an open-vocabulary interactive object-search prototype, which combines object detection with scene description and navigat
Externí odkaz:
http://arxiv.org/abs/2412.03118
Monocular geometric scene understanding combines panoptic segmentation and self-supervised depth estimation, focusing on real-time application in autonomous vehicles. We introduce MGNiceNet, a unified approach that uses a linked kernel formulation fo
Externí odkaz:
http://arxiv.org/abs/2411.11466
Depth estimation is an essential task toward full scene understanding since it allows the projection of rich semantic information captured by cameras into 3D space. While the field has gained much attention recently, datasets for depth estimation lac
Externí odkaz:
http://arxiv.org/abs/2411.11455
Autor:
Shi, Jiaojian, Heide, Christian, Xu, Haowei, Huang, Yijing, Shen, Yuejun, Guzelturk, Burak, Henstridge, Meredith, Schön, Carl Friedrich, Mangu, Anudeep, Kobayashi, Yuki, Peng, Xinyue, Zhang, Shangjie, May, Andrew F., Reddy, Pooja Donthi, Shautsova, Viktoryia, Taghinejad, Mohammad, Luo, Duan, Hughes, Eamonn, Brongersma, Mark L., Mukherjee, Kunal, Trigo, Mariano, Heinz, Tony F., Li, Ju, Nelson, Keith A., Baldini, Edoardo, Zhou, Jian, Ghimire, Shambhu, Wuttig, Matthias, Reis, David A., Lindenberg, Aaron M.
Important advances have recently been made in the search for materials with complex multi-phase landscapes that host photoinduced metastable collective states with exotic functionalities. In almost all cases so far, the desired phases are accessed by
Externí odkaz:
http://arxiv.org/abs/2411.10131
Autor:
Krauß, Veronika, McGill, Mark, Kosch, Thomas, Thiel, Yolanda, Schön, Dominik, Gugenheimer, Jan
With the recent advancements in Large Language Models (LLMs), web developers increasingly apply their code-generation capabilities to website design. However, since these models are trained on existing designerly knowledge, they may inadvertently rep
Externí odkaz:
http://arxiv.org/abs/2411.03108
For the validation and verification of automotive radars, datasets of realistic traffic scenarios are required, which, how ever, are laborious to acquire. In this paper, we introduce radar scene synthesis using GANs as an alternative to the real data
Externí odkaz:
http://arxiv.org/abs/2410.13526
Adversarial training can be used to learn models that are robust against perturbations. For linear models, it can be formulated as a convex optimization problem. Compared to methods proposed in the context of deep learning, leveraging the optimizatio
Externí odkaz:
http://arxiv.org/abs/2410.12677
Image monitoring and guidance during medical examinations can aid both diagnosis and treatment. However, the sampling frequency is often too low, which creates a need to estimate the missing images. We present a probabilistic motion model for sequent
Externí odkaz:
http://arxiv.org/abs/2410.11491
Since neural networks can make wrong predictions even with high confidence, monitoring their behavior at runtime is important, especially in safety-critical domains like autonomous driving. In this paper, we combine ideas from previous monitoring app
Externí odkaz:
http://arxiv.org/abs/2410.06051