Zobrazeno 1 - 10
of 623
pro vyhledávání: '"Kersting, Kristian"'
Tokenizers are crucial for encoding information in Large Language Models, but their development has recently stagnated, and they contain inherent weaknesses. Major limitations include computational overhead, ineffective vocabulary use, and unnecessar
Externí odkaz:
http://arxiv.org/abs/2406.19223
Autor:
Kaufmann, Timo, Blüml, Jannis, Wüst, Antonia, Delfosse, Quentin, Kersting, Kristian, Hüllermeier, Eyke
Properly defining a reward signal to efficiently train a reinforcement learning (RL) agent is a challenging task. Designing balanced objective functions from which a desired behavior can emerge requires expert knowledge, especially for complex enviro
Externí odkaz:
http://arxiv.org/abs/2406.16748
Employing Unmanned Aircraft Systems (UAS) beyond visual line of sight (BVLOS) is an endearing and challenging task. While UAS have the potential to significantly enhance today's logistics and emergency response capabilities, unmanned flying objects a
Externí odkaz:
http://arxiv.org/abs/2406.15088
The challenge in object-based visual reasoning lies in generating descriptive yet distinct concept representations. Moreover, doing this in an unsupervised fashion requires human users to understand a model's learned concepts and potentially revise f
Externí odkaz:
http://arxiv.org/abs/2406.09949
Reinforcement learning (RL) has proven to be a powerful tool for training agents that excel in various games. However, the black-box nature of neural network models often hinders our ability to understand the reasoning behind the agent's actions. Rec
Externí odkaz:
http://arxiv.org/abs/2406.06107
We introduce LlavaGuard, a family of VLM-based safeguard models, offering a versatile framework for evaluating the safety compliance of visual content. Specifically, we designed LlavaGuard for dataset annotation and generative model safeguarding. To
Externí odkaz:
http://arxiv.org/abs/2406.05113
Artificial agents' adaptability to novelty and alignment with intended behavior is crucial for their effective deployment. Reinforcement learning (RL) leverages novelty as a means of exploration, yet agents often struggle to handle novel situations,
Externí odkaz:
http://arxiv.org/abs/2406.03997
Advanced Air Mobility (AAM) is a growing field that demands a deep understanding of legal, spatial and temporal concepts in navigation. Hence, any implementation of AAM is forced to deal with the inherent uncertainties of human-inhabited spaces. Enab
Externí odkaz:
http://arxiv.org/abs/2406.03454
Autor:
Hintersdorf, Dominik, Struppek, Lukas, Kersting, Kristian, Dziedzic, Adam, Boenisch, Franziska
Diffusion models (DMs) produce very detailed and high-quality images. Their power results from extensive training on large amounts of data, usually scraped from the internet without proper attribution or consent from content creators. Unfortunately,
Externí odkaz:
http://arxiv.org/abs/2406.02366
Deep reinforcement learning agents are prone to goal misalignments. The black-box nature of their policies hinders the detection and correction of such misalignments, and the trust necessary for real-world deployment. So far, solutions learning inter
Externí odkaz:
http://arxiv.org/abs/2405.14956