478 citations · 905 across the 72 of their papers we have counts for
15 papers · 1 filter
ShieldCLIP: Selective Safety Alignment for Harmful Content Mitigation in Multimodal Foundation Models
Tobia Poppi, Silvia Cappelletti, Samuele Poppi +4
Multimodal encoders such as CLIP underlie many downstream systems, but their web-scale training data embed harmful associations that safety alignment must suppress without unnecess…
DocAttriBench: Benchmarking Answer Grounding in Document Visual Question Answering
Luca De Grandis, Silvia Cappelletti, William Raccagni +3
Answer grounding in document visual question answering remains an open challenge: most benchmarks lack grounding annotations or provide limited-quality labels, while constructing g…
SPARK: Input-Conditioned Sparse Activation Modulation for Frozen DiT-based Super-Resolution
Federico Putamorsi, Leonardo Zini, Marcella Cornia +1
Real-world image super-resolution (SR) increasingly relies on Diffusion Transformer (DiT) backbones, whose internal activations can be dominated by a small number of massive channe…
SVG-Score: Human-Aligned Evaluation of Text-to-SVG Generation
Marco Cipriano, Leonardo Zini, Alexandra Schild +5
Scalable Vector Graphics (SVG) generation is attracting increasing attention as generative models improve in expressiveness and controllability. Progress, however, is held back by…
Segmenting, Fast and Slow: Real-Time Open-Vocabulary Video Instance Segmentation with Dual-Path Processing
Luca Barsellotti, Martin Sundermeyer, Mattia Segu +5
Object-centric models inspired by DETR have become the dominant paradigm for open-vocabulary video instance segmentation (OV-VIS). While recent efforts have reduced the computation…
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…
Diffusion Language Models: An Experimental Analysis
Thomas Bertolani, Davide Bucciarelli, Leonardo Zini +2
Large Language Models (LLMs) have revolutionized language modeling through autoregressive generation, enabling strong performance across a wide range of tasks. Recently, Diffusion…
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…
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…
GramSR: Visual Feature Conditioning for Diffusion-Based Super-Resolution
Fabio D'Oronzio, Federico Putamorsi, Leonardo Zini +2
Despite recent advances, single-image super-resolution (SR) remains challenging, especially in real-world scenarios with complex degradations. Diffusion-based SR methods, particula…
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…
Tiny Inference-Time Scaling with Latent Verifiers
Davide Bucciarelli, Evelyn Turri, Lorenzo Baraldi +2
Inference-time scaling has emerged as an effective way to improve generative models at test time by using a verifier to score and select candidate outputs. A common choice is to em…
Dress-ED: Instruction-Guided Editing for Virtual Try-On and Try-Off
Davide Lobba, Fulvio Sanguigni, Bin Ren +3
Recent advances in Virtual Try-On (VTON) and Virtual Try-Off (VTOFF) have greatly improved photo-realistic fashion synthesis and garment reconstruction. However, existing datasets…
CounterVid: Counterfactual Video Generation for Mitigating Action and Temporal Hallucinations in Video-Language Models
Tobia Poppi, Burak Uzkent, Amanmeet Garg +7
Video-language models (VLMs) achieve strong multimodal understanding but remain prone to hallucinations, especially when reasoning about actions and temporal order. Existing mitiga…