Zobrazeno 1 - 10
of 50 122
pro vyhledávání: '"OR, İlhan"'
Autor:
Aslan, Ilhan
Innovations in interaction design are increasingly driven by progress in machine learning fields. Automatic speech emotion recognition (SER) is such an example field on the rise, creating well performing models, which typically take as input a speech
Externí odkaz:
http://arxiv.org/abs/2412.07722
Anthropogenic climate change has increased the probability, severity, and duration of heat waves and droughts, subsequently escalating the risk of wildfires. Mathematical and computational models can enhance our understanding of wildfire propagation
Externí odkaz:
http://arxiv.org/abs/2412.04517
Alignment of pretrained LLMs using instruction-based datasets is critical for creating fine-tuned models that reflect human preference. A growing number of alignment-based fine-tuning algorithms and benchmarks emerged recently, fueling the efforts on
Externí odkaz:
http://arxiv.org/abs/2411.17792
The integration of Inverter-Based Resource (IBR) model into phasor-domain short circuit (SC) solvers challenges their numerical stability. To address the challenge, this paper proposes a solver that improves numerical stability by employing the Newto
Externí odkaz:
http://arxiv.org/abs/2411.12006
Autor:
Karaman, Bilal, Basturk, Ilhan, Taskin, Sezai, Zeydan, Engin, Kara, Ferdi, Beyazit, Esra Aycan, Camelo, Miguel, Björnson, Emil, Yanikomeroglu, Halim
As natural disasters become more frequent and severe, ensuring a resilient communications infrastructure is of paramount importance for effective disaster response and recovery. This disaster-resilient infrastructure should also respond to sustainabi
Externí odkaz:
http://arxiv.org/abs/2410.13977
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
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
Autor:
Black, William, Manlove, Alexander, Pennington, Jack, Marchini, Andrea, Ilhan, Ercument, Markeviciute, Vilda
For users navigating travel e-commerce websites, the process of researching products and making a purchase often results in intricate browsing patterns that span numerous sessions over an extended period of time. The resulting clickstream data chroni
Externí odkaz:
http://arxiv.org/abs/2409.12972
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
Neural network models for audio tasks, such as automatic speech recognition (ASR) and acoustic scene classification (ASC), are susceptible to noise contamination for real-life applications. To improve audio quality, an enhancement module, which can b
Externí odkaz:
http://arxiv.org/abs/2408.06264