Zobrazeno 11 - 20
of 624
pro vyhledávání: '"Kersting, Kristian"'
Autor:
Tedeschi, Simone, Friedrich, Felix, Schramowski, Patrick, Kersting, Kristian, Navigli, Roberto, Nguyen, Huu, Li, Bo
When building Large Language Models (LLMs), it is paramount to bear safety in mind and protect them with guardrails. Indeed, LLMs should never generate content promoting or normalizing harmful, illegal, or unethical behavior that may contribute to ha
Externí odkaz:
http://arxiv.org/abs/2404.08676
Autor:
Poli, Michael, Thomas, Armin W, Nguyen, Eric, Ponnusamy, Pragaash, Deiseroth, Björn, Kersting, Kristian, Suzuki, Taiji, Hie, Brian, Ermon, Stefano, Ré, Christopher, Zhang, Ce, Massaroli, Stefano
The development of deep learning architectures is a resource-demanding process, due to a vast design space, long prototyping times, and high compute costs associated with at-scale model training and evaluation. We set out to simplify this process by
Externí odkaz:
http://arxiv.org/abs/2403.17844
Autor:
Sidheekh, Sahil, Tenali, Pranuthi, Mathur, Saurabh, Blasch, Erik, Kersting, Kristian, Natarajan, Sriraam
We consider the problem of late multi-modal fusion for discriminative learning. Motivated by noisy, multi-source domains that require understanding the reliability of each data source, we explore the notion of credibility in the context of multi-moda
Externí odkaz:
http://arxiv.org/abs/2403.03281
In natural language processing and vision, pretraining is utilized to learn effective representations. Unfortunately, the success of pretraining does not easily carry over to time series due to potential mismatch between sources and target. Actually,
Externí odkaz:
http://arxiv.org/abs/2402.15404
Autor:
Shindo, Hikaru, Brack, Manuel, Sudhakaran, Gopika, Dhami, Devendra Singh, Schramowski, Patrick, Kersting, Kristian
Large-scale, pre-trained neural networks have demonstrated strong capabilities in various tasks, including zero-shot image segmentation. To identify concrete objects in complex scenes, humans instinctively rely on deictic descriptions in natural lang
Externí odkaz:
http://arxiv.org/abs/2402.14123
The reliability of deep time series models is often compromised by their tendency to rely on confounding factors, which may lead to incorrect outputs. Our newly recorded, naturally confounded dataset named P2S from a real mechanical production line e
Externí odkaz:
http://arxiv.org/abs/2402.12921
The proliferation of large language models (LLMs) has sparked widespread and general interest due to their strong language generation capabilities, offering great potential for both industry and research. While previous research delved into the secur
Externí odkaz:
http://arxiv.org/abs/2402.09132
Autor:
Derstroff, Cedric, Brugger, Jannis, Blüml, Jannis, Mezini, Mira, Kramer, Stefan, Kersting, Kristian
Monte-Carlo tree search (MCTS) is an effective anytime algorithm with a vast amount of applications. It strategically allocates computational resources to focus on promising segments of the search tree, making it a very attractive search algorithm in
Externí odkaz:
http://arxiv.org/abs/2402.08511
Autor:
Wüst, Antonia, Stammer, Wolfgang, Delfosse, Quentin, Dhami, Devendra Singh, Kersting, Kristian
The challenge in learning abstract concepts from images in an unsupervised fashion lies in the required integration of visual perception and generalizable relational reasoning. Moreover, the unsupervised nature of this task makes it necessary for hum
Externí odkaz:
http://arxiv.org/abs/2402.08280
Autor:
Busch, Florian Peter, Kamath, Roshni, Mitchell, Rupert, Stammer, Wolfgang, Kersting, Kristian, Mundt, Martin
A dataset is confounded if it is most easily solved via a spurious correlation, which fails to generalize to new data. In this work, we show that, in a continual learning setting where confounders may vary in time across tasks, the challenge of mitig
Externí odkaz:
http://arxiv.org/abs/2402.06434