13 papers
Few Channels Draw The Whole Picture: Revealing Massive Activations in Diffusion Transformers
Evelyn Turri, Davide Bucciarelli, Sara Sarto +2
Diffusion Transformers (DiTs) and related flow-based architectures are now among the strongest text-to-image generators, yet the internal mechanisms through which prompts shape ima…
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…
Do Models Share Safety Representations? Cross-Model Steering for Safe Visual Generation
Tobia Poppi, Silvia Cappelletti, Sara Sarto +5
Recent progress in generative modeling has made safety control a central challenge, yet existing approaches remain largely model-specific, requiring retraining or tailored interven…
RaTA-Tool: Retrieval-based Tool Selection with Multimodal Large Language Models
Gabriele Mattioli, Evelyn Turri, Sara Sarto +3
Tool learning with foundation models aims to endow AI systems with the ability to invoke external resources -- such as APIs, computational utilities, and specialized models -- to s…
Look Twice: Training-Free Evidence Highlighting for Knowledge-based Visual Question Answering
Marco Morini, Sara Sarto, Marcella Cornia +2
Knowledge-based Visual Question Answering (KB-VQA) requires Multimodal Large Language Models (MLLMs) to identify and combine fine-grained visual cues with retrieved textual evidenc…
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).…