6 papers
Knowledge Knows, Verbalization Tells: Disentangling Latent Directions for Mathematical Solvability in LLMs
Nikolaos Xiros, Maria-Eleni Zoumpoulidi, Georgios Paraskevopoulos
Although LLMs have made significant progress in mathematical reasoning, determining whether a mathematical problem is solvable remains a fundamental yet challenging capability. Whi…
Auto-Compressing Networks
Vaggelis Dorovatas, Georgios Paraskevopoulos, Alexandros Potamianos
Deep neural networks with short residual connections have demonstrated remarkable success across domains, but increasing depth often introduces computational redundancy without cor…
Masked Diffusion Language Models with Frequency-Informed Training
Despoina Kosmopoulou, Efthymios Georgiou, Vaggelis Dorovatas +2
We present a masked diffusion language modeling framework for data-efficient training for the BabyLM 2025 Challenge. Our approach applies diffusion training objectives to language…
BloomWise: Enhancing Problem-Solving capabilities of Large Language Models using Bloom's-Taxonomy-Inspired Prompts
Maria-Eleni Zoumpoulidi, Georgios Paraskevopoulos, Alexandros Potamianos
Despite the remarkable capabilities of large language models (LLMs) across a range of tasks, mathematical reasoning remains a challenging frontier. Motivated by the observation tha…
MSDA: Combining Pseudo-labeling and Self-Supervision for Unsupervised Domain Adaptation in ASR
Dimitrios Damianos, Georgios Paraskevopoulos, Alexandros Potamianos
In this work, we investigate the Meta PL unsupervised domain adaptation framework for Automatic Speech Recognition (ASR). We introduce a Multi-Stage Domain Adaptation pipeline (MSD…
Y-Drop: A Conductance based Dropout for fully connected layers
Efthymios Georgiou, Georgios Paraskevopoulos, Alexandros Potamianos
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 ap…