May 14, 2024, 4:43 a.m. | Masane Fuchi, Tomohiro Takagi

cs.LG updates on

arXiv:2405.07288v1 Announce Type: cross
Abstract: Generating images from text has become easier because of the scaling of diffusion models and advancements in the field of vision and language. These models are trained using vast amounts of data from the Internet. Hence, they often contain undesirable content such as copyrighted material. As it is challenging to remove such data and retrain the models, methods for erasing specific concepts from pre-trained models have been investigated. We propose a novel concept-erasure method that …

abstract arxiv become concepts cs.lg data diffusion diffusion models few-shot image image diffusion images internet language material scaling text text-to-image type unlearning vast vision

Software Engineer for AI Training Data (School Specific)

@ G2i Inc | Remote

Software Engineer for AI Training Data (Python)

@ G2i Inc | Remote

Software Engineer for AI Training Data (Tier 2)

@ G2i Inc | Remote

Data Engineer

@ | Remote: Europe, LATAM, Canada, UK, Asia, Oceania

Artificial Intelligence – Bioinformatic Expert

@ University of Texas Medical Branch | Galveston, TX

Intern - Robotics Industrial Engineer Summer 2024

@ Vitesco Technologies | Seguin, US