7 papers
Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks
Nobin Sarwar, Shubhashis Roy Dipta, Zheyuan Liu +1
With the growing adoption of VLMs, DMs, LLMs, and AFMs, these multimodal foundation models can inadvertently encode sensitive, copyrighted, biased, or unsafe cross-modal associatio…
A mathematical framework for centromere-aware evaluation of human genome assemblies
Luca Franco, Matteo Migliarini, Matteo Tommaso Ungaro +6
Accurate evaluation of genome assemblies within highly repetitive regions, such as centromeres, remains a major open challenge in genomics. Conventional benchmarking relies on sequ…
Quantifying Self-Preservation Bias in Large Language Models
Matteo Migliarini, Joaquin Pereira Pizzini, Luca Moresca +3
Instrumental convergence predicts that sufficiently advanced AI agents will resist shutdown, yet current safety training (RLHF) may obscure this risk by teaching models to deny sel…
@GrokSet: multi-party Human-LLM Interactions in Social Media
Matteo Migliarini, Berat Ercevik, Oluwagbemike Olowe +5
Large Language Models (LLMs) are increasingly deployed as active participants on public social media platforms, yet their behavior in these unconstrained social environments remain…
Video Unlearning via Low-Rank Refusal Vector
Simone Facchiano, Stefano Saravalle, Matteo Migliarini +7
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…
Human Motion Unlearning
Edoardo De Matteis, Matteo Migliarini, Alessio Sampieri +2
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…