Zobrazeno 1 - 10
of 191
pro vyhledávání: '"Potamianos Alexandros"'
In-context Learning (ICL) has become the primary method for performing natural language tasks with Large Language Models (LLMs). The knowledge acquired during pre-training is crucial for this few-shot capability, providing the model with task priors.
Externí odkaz:
http://arxiv.org/abs/2410.13776
Despite the continuous progress of Large Language Models (LLMs) across various tasks, their performance on mathematical problems and reasoning tasks remains limited. This limitation can be attributed, among other factors, to the inherent difficulty o
Externí odkaz:
http://arxiv.org/abs/2410.04094
We introduce Label-Combination Prototypical Networks (LC-Protonets) to address the problem of multi-label few-shot classification, where a model must generalize to new classes based on only a few available examples. Extending Prototypical Networks, L
Externí odkaz:
http://arxiv.org/abs/2409.11264
In this work, we introduce Y-Drop, a regularization method that biases the dropout algorithm towards dropping more important neurons with higher probability. The backbone of our approach is neuron conductance, an interpretable measure of neuron impor
Externí odkaz:
http://arxiv.org/abs/2409.09088
Autor:
Charalampopoulos, Andreas, Chatzis, Nikolas, Ntoulas-Panagiotopoulos, Foivos, Papaioannou, Charilaos, Potamianos, Alexandros
Fast feedforward networks (FFFs) are a class of neural networks that exploit the observation that different regions of the input space activate distinct subsets of neurons in wide networks. FFFs partition the input space into separate sections using
Externí odkaz:
http://arxiv.org/abs/2405.16836
In-context Learning (ICL) has emerged as a powerful paradigm for performing natural language tasks with Large Language Models (LLM) without updating the models' parameters, in contrast to the traditional gradient-based finetuning. The promise of ICL
Externí odkaz:
http://arxiv.org/abs/2403.17125
Multimodal sentiment analysis (MSA) leverages heterogeneous data sources to interpret the complex nature of human sentiments. Despite significant progress in multimodal architecture design, the field lacks comprehensive regularization methods. This p
Externí odkaz:
http://arxiv.org/abs/2312.12334
Autor:
Jo, Yohan, Zhao, Xinyan, Biswas, Arijit, Basiou, Nikoletta, Auvray, Vincent, Malandrakis, Nikolaos, Metallinou, Angeliki, Potamianos, Alexandros
While most task-oriented dialogues assume conversations between the agent and one user at a time, dialogue systems are increasingly expected to communicate with multiple users simultaneously who make decisions collaboratively. To facilitate developme
Externí odkaz:
http://arxiv.org/abs/2310.20479
Recent developments in MIR have led to several benchmark deep learning models whose embeddings can be used for a variety of downstream tasks. At the same time, the vast majority of these models have been trained on Western pop/rock music and related
Externí odkaz:
http://arxiv.org/abs/2307.09795
In this paper, we study the problem of producing a comprehensive video summary following an unsupervised approach that relies on adversarial learning. We build on a popular method where a Generative Adversarial Network (GAN) is trained to create repr
Externí odkaz:
http://arxiv.org/abs/2307.08145