34 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…
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…
SLU-2K: A Question-Based Benchmark for Semantic Evaluation of Sign Language Translation
Zeno Testa, Antonino Furnari, Lorenzo Baraldi +1
Sign Language Translation (SLT) is typically evaluated with surface-form metrics such as BLEU and ROUGE, which reward lexical overlap but do not directly measure whether a translat…
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…
Harnessing Self-Supervised Features for Art Classification
Federico Melis, Davide Bilardello, Emanuele Prato +2
Classifying artworks presents a significant challenge due to the complex interplay of fine-grained details and abstract features that condition the style or genre of an artwork. Th…