Zobrazeno 1 - 10
of 77 142
pro vyhledávání: '"A. Selim"'
Combining large language models during training or at inference time has shown substantial performance gain over component LLMs. This paper presents LLM-TOPLA, a diversity-optimized LLM ensemble method with three unique properties: (i) We introduce t
Externí odkaz:
http://arxiv.org/abs/2410.03953
Autor:
Brandstetter, Sandra, Heintze, Carl, Subramanian, Keerthan, Hill, Paul, Preiss, Philipp M., Gałka, Maciej, Jochim, Selim
Understanding many body systems is a key challenge in physics. Single atom resolved imaging techniques have unlocked access to microscopic correlations in ultracold quantum gases. However they cannot be used when the relevant length scales are obscur
Externí odkaz:
http://arxiv.org/abs/2409.18954
Recent research demonstrates that the nascent fine-tuning-as-a-service business model exposes serious safety concerns -- fine-tuning over a few harmful data uploaded by the users can compromise the safety alignment of the model. The attack, known as
Externí odkaz:
http://arxiv.org/abs/2409.18169
Signal Processing (SP) and Machine Learning (ML) rely on good math and coding knowledge, in particular, linear algebra, probability, and complex numbers. A good grasp of these relies on scalar algebra learned in middle school. The ability to understa
Externí odkaz:
http://arxiv.org/abs/2409.17304
Autor:
Kartal, Enise, Selcuk, Yunus, Kaynak, Batuhan E., Yildiz, M. Taha, Yanik, Cenk, Hanay, M. Selim
Reservoir computing offers an energy-efficient alternative to deep neural networks (DNNs) by replacing complex hidden layers with a fixed nonlinear system and training only the final layer. This work investigates nanoelectromechanical system (NEMS) r
Externí odkaz:
http://arxiv.org/abs/2409.16805
This paper considers the minimization of a continuously differentiable function over a cardinality constraint. We focus on smooth and relatively smooth functions. These smoothness criteria result in new descent lemmas. Based on the new descent lemmas
Externí odkaz:
http://arxiv.org/abs/2409.12343
Autor:
Piozin, Corentin, Bouarroudj, Lisa, Audran, Jean-Yves, Lavrard, Brice, Simon, Catherine, Waszak, Florian, Eskiizmirliler, Selim
Decoding multiple movements from the same limb using electroencephalographic (EEG) activity is a key challenge with applications for controlling prostheses in upper-limb amputees. This study investigates the classification of four hand movements to c
Externí odkaz:
http://arxiv.org/abs/2409.07207
Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturbation
Harmful fine-tuning issue \citep{qi2023fine} poses serious safety concerns for Large language models' fine-tuning-as-a-service. While existing defenses \citep{huang2024vaccine,rosati2024representation} have been proposed to mitigate the issue, their
Externí odkaz:
http://arxiv.org/abs/2409.01586
This paper introduces the parallel network-based spoofing-aware speaker verification (SASV) system developed by BTU Speech Group for the ASVspoof5 Challenge. The SASV system integrates ASV and CM systems to enhance security against spoofing attacks.
Externí odkaz:
http://arxiv.org/abs/2408.15877
Recent analyses highlight challenges in autonomous vehicle technologies, particularly failures in decision-making under dynamic or emergency conditions. Traditional automated driving systems recalculate the entire trajectory in a changing environment
Externí odkaz:
http://arxiv.org/abs/2408.10622