Zobrazeno 1 - 10
of 4 513
pro vyhledávání: '"A. Schwinn"'
Comprehensive evaluation of Large Language Models (LLMs) is an open research problem. Existing evaluations rely on deterministic point estimates generated via greedy decoding. However, we find that deterministic evaluations fail to capture the whole
Externí odkaz:
http://arxiv.org/abs/2410.03523
Recent advancements in generative modeling, particularly diffusion models, have opened new directions for time series modeling, achieving state-of-the-art performance in forecasting and synthesis. However, the reliance of diffusion-based models on a
Externí odkaz:
http://arxiv.org/abs/2410.03024
Autor:
Zanca, Dario, Zugarini, Andrea, Dietz, Simon, Altstidl, Thomas R., Ndjeuha, Mark A. Turban, Schwinn, Leo, Eskofier, Bjoern
Understanding human attention is crucial for vision science and AI. While many models exist for free-viewing, less is known about task-driven image exploration. To address this, we introduce CapMIT1003, a dataset with captions and click-contingent im
Externí odkaz:
http://arxiv.org/abs/2408.09948
Autor:
Schwinn, Leo, Geisler, Simon
Over the past decade, adversarial training has emerged as one of the few reliable methods for enhancing model robustness against adversarial attacks [Szegedy et al., 2014, Madry et al., 2018, Xhonneux et al., 2024], while many alternative approaches
Externí odkaz:
http://arxiv.org/abs/2407.15902
Existing studies have shown that Graph Neural Networks (GNNs) are vulnerable to adversarial attacks. Even though Graph Transformers (GTs) surpassed Message-Passing GNNs on several benchmarks, their adversarial robustness properties are unexplored. Ho
Externí odkaz:
http://arxiv.org/abs/2407.11764
Their vulnerability to small, imperceptible attacks limits the adoption of deep learning models to real-world systems. Adversarial training has proven to be one of the most promising strategies against these attacks, at the expense of a substantial i
Externí odkaz:
http://arxiv.org/abs/2406.13283
Transformer architectures have shown promising results in time series processing. However, despite recent advances in subquadratic attention mechanisms or state-space models, processing very long sequences still imposes significant computational requ
Externí odkaz:
http://arxiv.org/abs/2405.17951
Large language models (LLMs) are vulnerable to adversarial attacks that can bypass their safety guardrails. In many domains, adversarial training has proven to be one of the most promising methods to reliably improve robustness against such attacks.
Externí odkaz:
http://arxiv.org/abs/2405.15589
When applying deep learning models in open-world scenarios, active learning (AL) strategies are crucial for identifying label candidates from a nearly infinite amount of unlabeled data. In this context, robust out-of-distribution (OOD) detection mech
Externí odkaz:
http://arxiv.org/abs/2405.11337
Collision detection is one of the most time-consuming operations during motion planning. Thus, there is an increasing interest in exploring machine learning techniques to speed up collision detection and sampling-based motion planning. A recent line
Externí odkaz:
http://arxiv.org/abs/2402.15281