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 ...

Don't just texture one mesh at a time! StableGen is designed to apply textures to all visible mesh objects in your scene simultaneously from your defined camera viewpoints. Achieve a cohesive look ...

Abstract: Generative steganography, a novel paradigm in information hiding, has garnered considerable attention for its potential to withstand steganalysis. However, existing generative steganography ...

This project provides a complete pipeline for latent diffusion models, covering image dataset encoding into latents, training three different models with two distinct noise schedules, and sampling ...

Abstract: Ensuring the availability of child facial datasets is essential for advancing AI applications, yet legal, ethical, and data scarcity concerns pose significant challenges. Current generative ...