6 papers
EmbodimentSemantic: A Spatial Scene-Graph Dataset and Benchmark for Vision-Language Models on Embodied Manipulation Trajectories
Hassan Jaber, Refinath S N, Luca Cagliero +2
Spatial grounding remains a key limitation of vision-language-action (VLA) systems for robotic manipulation. While current models can recognize objects and follow language instruct…
Benchmarking Visual LLMs Resilience to Unanswerable Questions on Visually Rich Documents
Davide Napolitano, Luca Cagliero, Fabrizio Battiloro
The evolution of Visual Large Language Models (VLLMs) has revolutionized the automatic understanding of Visually Rich Documents (VRDs), which contain both textual and visual elemen…
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…
Beyond Accuracy Optimization: Computer Vision Losses for Large Language Model Fine-Tuning
Daniele Rege Cambrin, Giuseppe Gallipoli, Irene Benedetto +2
Large Language Models (LLMs) have demonstrated impressive performance across various tasks. However, current training approaches combine standard cross-entropy loss with extensive…
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…
BONES: a Benchmark fOr Neural Estimation of Shapley values
Davide Napolitano, Luca Cagliero
Shapley Values are concepts established for eXplainable AI. They are used to explain black-box predictive models by quantifying the features' contributions to the model's outcomes.…