Zobrazeno 1 - 10
of 3 321
pro vyhledávání: '"Stamou A"'
Autor:
Kantarelis, Spyridon, Thomas, Konstantinos, Lyberatos, Vassilis, Dervakos, Edmund, Stamou, Giorgos
Chord progressions encapsulate important information about music, pertaining to its structure and conveyed emotions. They serve as the backbone of musical composition, and in many cases, they are the sole information required for a musician to play a
Externí odkaz:
http://arxiv.org/abs/2410.22046
Autor:
Xypolopoulos, Christos, Shang, Guokan, Fei, Xiao, Nikolentzos, Giannis, Abdine, Hadi, Evdaimon, Iakovos, Chatzianastasis, Michail, Stamou, Giorgos, Vazirgiannis, Michalis
Large language models have evolved to process multiple modalities beyond text, such as images and audio, which motivates us to explore how to effectively leverage them for graph machine learning tasks. The key question, therefore, is how to transform
Externí odkaz:
http://arxiv.org/abs/2410.19494
Autor:
Theodoropoulos, Nikitas, Filandrianos, Giorgos, Lyberatos, Vassilis, Lymperaiou, Maria, Stamou, Giorgos
We describe our contribution to the Strict and Strict-Small tracks of the 2nd iteration of the BabyLM Challenge. The shared task is centered around efficient pre-training given data constraints motivated by human development. In response, we study th
Externí odkaz:
http://arxiv.org/abs/2410.15365
Riddle-solving requires advanced reasoning skills, pushing LLMs to engage in abstract thinking and creative problem-solving, often revealing limitations in their cognitive abilities. In this paper, we examine the riddle-solving capabilities of LLMs u
Externí odkaz:
http://arxiv.org/abs/2409.16383
Autor:
Thomas, Konstantinos, Filandrianos, Giorgos, Lymperaiou, Maria, Zerva, Chrysoula, Stamou, Giorgos
Equivocation and ambiguity in public speech are well-studied discourse phenomena, especially in political science and analysis of political interviews. Inspired by the well-grounded theory on equivocation, we aim to resolve the closely related proble
Externí odkaz:
http://arxiv.org/abs/2409.13879
Autor:
Mastromichalakis, Orfeas Menis, Filandrianos, Giorgos, Tsouparopoulou, Eva, Parsanoglou, Dimitris, Symeonaki, Maria, Stamou, Giorgos
Gender bias in machine translation (MT) systems poses significant challenges that often result in the reinforcement of harmful stereotypes. Especially in the labour domain where frequently occupations are inaccurately associated with specific genders
Externí odkaz:
http://arxiv.org/abs/2409.10989
Multimodal models are critical for music understanding tasks, as they capture the complex interplay between audio and lyrics. However, as these models become more prevalent, the need for explainability grows-understanding how these systems make decis
Externí odkaz:
http://arxiv.org/abs/2409.10496
The surge of state-of-the-art Transformer-based models has undoubtedly pushed the limits of NLP model performance, excelling in a variety of tasks. We cast the spotlight on the underexplored task of Natural Language Inference (NLI), since models trai
Externí odkaz:
http://arxiv.org/abs/2409.07423
Autor:
Argyrou, Georgia, Dimitriou, Angeliki, Lymperaiou, Maria, Filandrianos, Giorgos, Stamou, Giorgos
Despite the rapid evolution and increasing efficacy of language and vision generative models, there remains a lack of comprehensive datasets that bridge the gap between personalized fashion needs and AI-driven design, limiting the potential for truly
Externí odkaz:
http://arxiv.org/abs/2409.06442
In the rapidly evolving fields of natural language processing and computer vision, Visual Word Sense Disambiguation (VWSD) stands as a critical, yet challenging task. The quest for models that can seamlessly integrate and interpret multimodal data is
Externí odkaz:
http://arxiv.org/abs/2408.06040