6 papers
The Tokens Strike Back: Safety-Aware Denoising with Directional Embedding-based Revision
Amman Yusuf, Jiwoo Shin, Ruizhi Deng +3
The Safety-Aware Denoiser (SAD) is a recent, training-free, safety-guidance framework for text diffusion models. During inference, SAD steers text samples toward safe regions of th…
Bayesian Entropy-based Reordering for Calibrated Diffusion Language Models
Zhejun Jiang, Mijung Park
Masked Diffusion Language Models (MDLMs) generate sequences by iteratively replacing masked tokens with model predictions. At each denoising step, the decoder chooses which positio…
The Safety-Aware Denoiser for Text Diffusion Models
Amman Yusuf, Zhejun Jiang, Mijung Park
Recent work on text diffusion models offers a promising alternative to autoregressive generation, but controlling their safety remains underexplored. Existing safety approaches are…
Safety-Guided Flow (SGF): A Unified Framework for Negative Guidance in Safe Generation
Mingyu Kim, Young-Heon Kim, Mijung Park
Safety mechanisms for diffusion and flow models have recently been developed along two distinct paths. In robot planning, control barrier functions are employed to guide generative…
Bayesian Principles Improve Prompt Learning In Vision-Language Models
Mingyu Kim, Jongwoo Ko, Mijung Park
Prompt learning is a popular fine-tuning method for vision-language models due to its efficiency. It requires a small number of additional learnable parameters while significantly…
Training-Free Safe Denoisers for Safe Use of Diffusion Models
Mingyu Kim, Dongjun Kim, Amman Yusuf +2
There is growing concern over the safety of powerful diffusion models (DMs), as they are often misused to produce inappropriate, not-safe-for-work (NSFW) content or generate copyri…