Panagiotis Kaliosis — accepted AI-conference papers

2025

LVLMs are Bad at Overhearing Human Referential Communication

Zhengxiang Wang, Weiling Li, Panagiotis Kaliosis, Owen Rambow, Susan Brennan

EMNLP 2025

During spontaneous conversations, speakers collaborate on novel referring expressions, which they can then re-use in subsequent conversations. Understanding such referring expressions is an important ability for an embodied agent, so that it can carry out tasks in the real world. This requires integ

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

Learning to Align: Addressing Character Frequency Distribution Shifts in Handwritten Text Recognition

Panagiotis Kaliosis, John Pavlopoulos

EMNLP 2025

Handwritten text recognition aims to convert visual input into machine-readable text, and it remains challenging due to the evolving and context-dependent nature of handwriting. Character sets change over time, and character frequency distributions shift across historical periods or regions, often c

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗