Matteo Migliarini — accepted AI-conference papers

2026

Human Motion Unlearning

Edoardo De Matteis, Matteo Migliarini, Alessio Sampieri, Indro Spinelli, Fabio Galasso

AAAI 2026technical

We introduce Human Motion Unlearning and motivate it through the concrete task of preventing violent 3D motion synthesis, an important safety requirement given that popular text-to-motion datasets (HumanML3D and Motion-X) contain from 7% to 15% violent sequences spanning both atomic gestures (e.g.,

Cited by 0 Source ↗PDF ↗Scholar ↗

2026

Video Unlearning via Low-Rank Refusal Vector

Simone Facchiano, Stefano Saravalle, Matteo Migliarini, Edoardo De Matteis, Alessio Sampieri, Andrea Pilzer +4

ICLR 2026poster

Video generative models achieve high-quality synthesis from natural-language prompts by leveraging large-scale web data. However, this training paradigm inherently exposes them to unsafe biases and harmful concepts, introducing the risk of generating undesirable or illicit content. To mitigate unsaf…

Cited by 0 Source ↗code ↗Scholar ↗