4 papers
Improving Diffusion Posterior Samplers with Lagged Temporal Corrections for Image Restoration
Davide Evangelista, Elena Morotti, Francesco Pivi +1
Diffusion-based posterior sampling (PS) is a leading framework for imaging inverse problems, combining learned priors with measurement constraints. Yet, its standard formulations r…
BlenderRAG: High-Fidelity 3D Object Generation via Retrieval-Augmented Code Synthesis
Massimo Rondelli, Francesco Pivi, Maurizio Gabbrielli
Automatic generation of executable Blender code from natural language remains challenging, with state-of-the-art LLMs producing frequent syntactic errors and geometrically inconsis…
The CompMath-MCQ Dataset: Are LLMs Ready for Higher-Level Math?
Bianca Raimondi, Francesco Pivi, Davide Evangelista +1
The evaluation of Large Language Models (LLMs) on mathematical reasoning has largely focused on elementary problems, competition-style questions, or formal theorem proving, leaving…
On the flow matching interpretability
Francesco Pivi, Simone Gazza, Davide Evangelista +2
Generative models based on flow matching have demonstrated remarkable success in various domains, yet they suffer from a fundamental limitation: the lack of interpretability in the…