Abstract: Recent advancements in generative models, such as generative adversarial networks (GANs) and diffusion-based models, have greatly improved the generation of realistic and diverse remote ...

As LLMs and diffusion models power more applications, their safety alignment becomes critical. Our research shows that even minimal downstream fine‑tuning can weaken safeguards, raising a key question ...

A relatively simple experiment involving asking a generative AI to compare two objects of very different sizes allows us to ...

Abstract: Diffusion-based generative models have achieved remarkable success in image restoration by learning to iteratively refine noisy data toward clean signals. Inspired by this progress, recent ...