Zobrazeno 1 - 10
of 66 953
pro vyhledávání: '"GÜL, A."'
Recent advances in large language models have demonstrated promising capabilities in following simple instructions through instruction tuning. However, real-world tasks often involve complex, multi-step instructions that remain challenging for curren
Externí odkaz:
http://arxiv.org/abs/2410.18529
Autor:
Gebeşçe, Ali, Şahin, Gözde Gül
Sophisticated grammatical error detection/correction tools are available for a small set of languages such as English and Chinese. However, it is not straightforward -- if not impossible -- to adapt them to morphologically rich languages with complex
Externí odkaz:
http://arxiv.org/abs/2410.12350
Autor:
Soykan, Gürkan, Şahin, Gözde Gül
Multilingual language models often perform unevenly across different languages due to limited generalization capabilities for some languages. This issue is significant because of the growing interest in making universal language models that work well
Externí odkaz:
http://arxiv.org/abs/2410.07809
Autor:
Safa, Abdulfattah, Şahin, Gözde Gül
Dialogue State Tracking (DST) is crucial for understanding user needs and executing appropriate system actions in task-oriented dialogues. Majority of existing DST methods are designed to work within predefined ontologies and assume the availability
Externí odkaz:
http://arxiv.org/abs/2409.15861
Fundamental Measure Theory (FMT) is a successful and versatile approach for describing the properties of the hard-sphere fluid and hard-sphere mixtures within the framework of classical density functional theory (DFT). Lutsko [Phys. Rev. E 102, 06213
Externí odkaz:
http://arxiv.org/abs/2409.01750
Autor:
Linden, Alex, Gül, Betül
Postselection is an operation that allows the selection of specific measurement outcomes. It serves as a powerful theoretical tool for enhancing the performance of existing quantum algorithms. Despite recent developments such as time reversal in quan
Externí odkaz:
http://arxiv.org/abs/2409.03785
The ever-evolving landscape of wireless communication technologies has led to the development of 5G-NR (5G New Radio) networks promising higher data rates and lower latency. However, with these advancements come challenges in managing intra-cell and
Externí odkaz:
http://arxiv.org/abs/2408.14097
In this paper, we present a novel approach to interference detection in 5G New Radio (5G-NR) networks using Convolutional Neural Networks (CNN). Interference in 5G networks challenges high-quality service due to dense user equipment deployment and in
Externí odkaz:
http://arxiv.org/abs/2408.11659
The focus of this paper is on 3D motion editing. Given a 3D human motion and a textual description of the desired modification, our goal is to generate an edited motion as described by the text. The key challenges include the scarcity of training dat
Externí odkaz:
http://arxiv.org/abs/2408.00712
Autor:
Xie, Junyu, Han, Tengda, Bain, Max, Nagrani, Arsha, Varol, Gül, Xie, Weidi, Zisserman, Andrew
Our objective is to generate Audio Descriptions (ADs) for both movies and TV series in a training-free manner. We use the power of off-the-shelf Visual-Language Models (VLMs) and Large Language Models (LLMs), and develop visual and text prompting str
Externí odkaz:
http://arxiv.org/abs/2407.15850