Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Andreas Triantafyllopoulos

Andreas Triantafyllopoulos

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

Sound×1Multimedia×1AI×1NLP×1Vision×1HCI×1

Frequent co-authors

Björn W. Schuller2×
Marius Moldovan1×
Anton Batliner1×
Thomas M. Berghaus1×
Iosif Tsangko1×
George Margetis1×

Research Timeline

2026
A Pilot Study on Curator-Guided Multilingual Art Description for Blind and Low-Vision Audiences with Small Vision-Language Models

This pilot study evaluates curator-guided multilingual art description using a small, on-premise VLM (Qwen2.5-VL-3B-Instruct) for German, Romanian, and Serbian, finding that language-specific adapters offer better controllability and visual grounding for certain languages.

CoughPhase-CLR: Designing an acoustics-informed foundation model for coughing sound classification

This paper introduces CoughPhase-CLR, a self-supervised learning framework for cough representation learning using physiological phases, outperforming standard techniques on five downstream tasks.

Highlighted terms show continued research focus across papers

Papers

cs.SDEmpiricalRecentJun 19, 2026

CoughPhase-CLR: Designing an acoustics-informed foundation model for coughing sound classification

Marius Moldovan, Anton Batliner, Thomas M. Berghaus, Björn W. Schuller +1 more

This paper introduces CoughPhase-CLR, a self-supervised learning framework for cough representation learning using physiological phases, outperforming standard techniques on five downstream tasks.

View →
cs.MMcs.AIcs.CLRecent
May 29, 2026

A Pilot Study on Curator-Guided Multilingual Art Description for Blind and Low-Vision Audiences with Small Vision-Language Models

Iosif Tsangko, Andreas Triantafyllopoulos, George Margetis, Ioana Crihana +1 more

This pilot study evaluates curator-guided multilingual art description using a small, on-premise VLM (Qwen2.5-VL-3B-Instruct) for German, Romanian, and Serbian, finding that language-specific adapters…

View →