safety-lora

safety-lora's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts

vinid 

authored 6 papers 7 months ago

Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scale

Paper • 2211.03759 • Published Nov 7, 2022

Contrastive Language-Image Pre-training for the Italian Language

Paper • 2108.08688 • Published Aug 19, 2021 • 2

XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models

Paper • 2308.01263 • Published Aug 2, 2023

Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions

Paper • 2309.07875 • Published Sep 14, 2023

When and why vision-language models behave like bags-of-words, and what to do about it?

Paper • 2210.01936 • Published Oct 4, 2022

TextGrad: Automatic "Differentiation" via Text

Paper • 2406.07496 • Published Jun 11, 2024 • 28