https://arxiv.org/abs/2601.04778
Tobia Poppi
tobi1modna
AI & ML interests
My research focuses on advancing Generative AI and Multimodal Architectures, aiming to bridge the gap between cutting-edge deep learning technologies and ethical alignment with human values. Passionate about leveraging AI to solve complex societal challenges, I am dedicated to ensuring AI systems are safe, transparent, and aligned with responsible principles, driving innovation with a human-centric approach.
Recent Activity
authored a paper 1 day ago
Do Models Share Safety Representations? Cross-Model Steering for Safe Visual Generation authored a paper 1 day ago
Improving LLM First-Token Predictions in Multiple-Choice Question Answering via Output Prefilling