4 papers
SGPA: Spectrogram-Guided Phonetic Alignment for Feasible Shapley Value Explanations in Multimodal Large Language Models
Paweł Pozorski, Jakub Muszyński, Maria Ganzha
Explaining the behavior of end-to-end audio language models via Shapley value attribution is intractable under native tokenization: a typical utterance yields over encoder fr…
RAI: Flexible Agent Framework for Embodied AI
Kajetan Rachwał, Maciej Majek, Bartłomiej Boczek +4
With an increase in the capabilities of generative language models, a growing interest in embodied AI has followed. This contribution introduces RAI - a framework for creating embo…
Representing and querying data tensors in RDF and SPARQL
Piotr Marciniak, Piotr Sowinski, Maria Ganzha
Embedding tensors in databases has recently gained in significance, due to the rapid proliferation of machine learning methods (including LLMs) which produce embeddings in the form…
ReReLRP -- Remembering and Recognizing Tasks with LRP
Karolina Bogacka, Maximilian Höfler, Maria Ganzha +2
Deep neural networks have revolutionized numerous research fields and applications. Despite their widespread success, a fundamental limitation known as catastrophic forgetting rema…