4 papers
Can Humans Dream of Electric Sheep? Human-Written Samples for Fine-Grained Vision-and-Language Hallucination Benchmarking
Timothee Mickus, Claudio Savelli, Eduardo Calò +10
In an age of rapid model turnover, how do we make hallucination evaluation more perennial? We explore whether human-written hallucination samples could take the place of model-gene…
CLOSP: A Unified Semantic Space for SAR, MSI, and Text in Remote Sensing
Daniele Rege Cambrin, Lorenzo Vaiani, Giuseppe Gallipoli +2
Retrieving relevant imagery from vast satellite archives is crucial for applications like disaster response and long-term climate monitoring. However, most text-to-image retrieval…
3MVRD: Multimodal Multi-task Multi-teacher Visually-Rich Form Document Understanding
Yihao Ding, Lorenzo Vaiani, Caren Han +4
This paper presents a groundbreaking multimodal, multi-task, multi-teacher joint-grained knowledge distillation model for visually-rich form document understanding. The model is de…
Benchmarking Representations for Speech, Music, and Acoustic Events
Moreno La Quatra, Alkis Koudounas, Lorenzo Vaiani +4
Limited diversity in standardized benchmarks for evaluating audio representation learning (ARL) methods may hinder systematic comparison of current methods' capabilities. We presen…