activity
20242026
collaborators
Showing cs.CVShow all

8 papers · 1 filter

cs.CV2026

Mind the Heads: Topological Representation Alignment for Multimodal LLMs

Davide Caffagni, Alberto Compagnoni, Federico Melis +5

Representation alignment has emerged as an effective approach to improve Multimodal Large Language Models (MLLMs) by regularizing their internal representations toward those of an…

cs.CV2025

Seeing Beyond Words: Self-Supervised Visual Learning for Multimodal Large Language Models

Davide Caffagni, Sara Sarto, Marcella Cornia +5

Multimodal Large Language Models (MLLMs) have recently demonstrated impressive capabilities in connecting vision and language, yet their proficiency in fundamental visual reasoning…

cs.CV2025

ReAG: Reasoning-Augmented Generation for Knowledge-based Visual Question Answering

Alberto Compagnoni, Marco Morini, Sara Sarto +5

Multimodal Large Language Models (MLLMs) have shown impressive capabilities in jointly understanding text, images, and videos, often evaluated via Visual Question Answering (VQA).…

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

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

Recurrence-Enhanced Vision-and-Language Transformers for Robust Multimodal Document Retrieval

Davide Caffagni, Sara Sarto, Marcella Cornia +2

Cross-modal retrieval is gaining increasing efficacy and interest from the research community, thanks to large-scale training, novel architectural and learning designs, and its app…