6 papers
Instruction Mining From Images: Constructing a Synthetic Dataset for Multimodal Learning ILSP DCVLR Competition Submission
Eleni E. Kasoura, Dimitrios Damianos, Georgios Paraskevopoulos +1
This work presents a compact and reproducible pipeline for synthesizing and curating image-based instruction-response pairs for DCVLR. We draw from the Cauldron collection and use…
Automatic Lyric Transcription for Greek Songs: Scaling and Task Composition Effects in Whisper Adaptation
Maria Frangiadaki, Dimitrios Damianos, Kosmas Kritsis +1
Automatic Lyric Transcription (ALT) remains substantially more challenging than speech recognition due to melodic variability, rhythmic irregularity, and accompaniment interference…
Beyond Magnitude: Contrastive Routing for Modular Mixture-of-Experts
Nikolaos Xiros, Dimitrios Damianos, Maria-Eleni Zoumpoulidi +3
In current Mixture-of-Experts architectures, routing is performed based on representations dominated by structure shared across all tokens, limiting expert specialization. We show…
Transcoders Trace Visual Grounding and Hallucinations in Vision-Language Models
Dimitrios Damianos, Leon Voukoutis, Georgios Skyrianos +2
Generative Vision-Language Models (VLMs) perform well on multimodal reasoning, but how visual inputs are transformed to text remains poorly understood. Existing interpretability wo…
VOX-KRIKRI: Unifying Speech and Language through Continuous Fusion
Dimitrios Damianos, Leon Voukoutis, Georgios Paraskevopoulos +1
We present a multimodal fusion framework that bridges pre-trained decoder-based large language models (LLM) and acoustic encoder-decoder architectures such as Whisper, with the aim…
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…