🏢 Brown University
Speak Easy: Eliciting Harmful Jailbreaks from LLMs with Simple Interactions
·6016 words·29 mins·
loading
·
loading
AI Generated
🤗 Daily Papers
Natural Language Processing
Large Language Models
🏢 Brown University
Simple interactions can easily elicit harmful outputs from LLMs, which are often overlooked. The SPEAK EASY framework and HARMSCORE metric expose this vulnerability and provide tools for better safet…
The GAN is dead; long live the GAN! A Modern GAN Baseline
·2531 words·12 mins·
loading
·
loading
AI Generated
🤗 Daily Papers
Computer Vision
Image Generation
🏢 Brown University
R3GAN: A modernized GAN baseline achieves state-of-the-art results with a simple, stable loss function and modern architecture, debunking the myth that GANs are hard to train.