activity
20242026
collaborators

8 papers

cs.CL2026

Benchmarking Deflection and Hallucination in Large Vision-Language Models

Nicholas Moratelli, Christopher Davis, Leonardo F. R. Ribeiro +2

Large Vision-Language Models (LVLMs) increasingly rely on retrieval to answer knowledge-intensive multimodal questions. Existing benchmarks overlook conflicts between visual and te…

cs.CV2025

Mitigating Hallucinations in Multimodal LLMs via Object-aware Preference Optimization

Alberto Compagnoni, Davide Caffagni, Nicholas Moratelli +3

Multimodal Large Language Models (MLLMs) emerge as a unified interface to address a multitude of tasks, ranging from NLP to computer vision. Despite showcasing state-of-the-art res…

cs.CV2025

LLaVA-MORE: A Comparative Study of LLMs and Visual Backbones for Enhanced Visual Instruction Tuning

Federico Cocchi, Nicholas Moratelli, Davide Caffagni +4

Recent progress in Multimodal Large Language Models (MLLMs) has highlighted the critical roles of both the visual backbone and the underlying language model. While prior work has p…

cs.CV2025

Positive-Augmented Contrastive Learning for Vision-and-Language Evaluation and Training

Sara Sarto, Nicholas Moratelli, Marcella Cornia +2

Despite significant advancements in caption generation, existing evaluation metrics often fail to capture the full quality or fine-grained details of captions. This is mainly due t…

cs.CV2025

TUNA: Comprehensive Fine-grained Temporal Understanding Evaluation on Dense Dynamic Videos

Fanheng Kong, Jingyuan Zhang, Hongzhi Zhang +7

Videos are unique in their integration of temporal elements, including camera, scene, action, and attribute, along with their dynamic relationships over time. However, existing ben…

cs.CV2025

Causal Graphical Models for Vision-Language Compositional Understanding

Fiorenzo Parascandolo, Nicholas Moratelli, Enver Sangineto +2

Recent work has empirically shown that Vision-Language Models (VLMs) struggle to fully understand the compositional properties of the human language, usually modeling an image capt…