4 papers
AILS-NTUA at SemEval-2026 Task 3: Efficient Dimensional Aspect-Based Sentiment Analysis
Stavros Gazetas, Giorgos Filandrianos, Maria Lymperaiou +3
In this paper, we present AILS-NTUA system for Track-A of SemEval-2026 Task 3 on Dimensional Aspect-Based Sentiment Analysis (DimABSA), which encompasses three complementary proble…
Sparse Computations in Deep Learning Inference
Ioanna Tasou, Panagiotis Mpakos, Angelos Vlachos +25
The computational demands of modern Deep Neural Networks (DNNs) are immense and constantly growing. While training costs usually capture public attention, inference demands are als…
Rethinking Affect Analysis: A Protocol for Ensuring Fairness and Consistency
Guanyu Hu, Dimitrios Kollias, Eleni Papadopoulou +3
Evaluating affect analysis methods presents challenges due to inconsistencies in database partitioning and evaluation protocols, leading to unfair and biased results. Previous stud…
U-Sketch: An Efficient Approach for Sketch to Image Diffusion Models
Ilias Mitsouras, Eleftherios Tsonis, Paraskevi Tzouveli +1
Diffusion models have demonstrated remarkable performance in text-to-image synthesis, producing realistic and high resolution images that faithfully adhere to the corresponding tex…