SafeLMM

AI & ML interests

Synthetic Augmented data, Fair and Extreme-scaled Large Multimodal Model (SafeLMM) * Multilingual, Multimodal, Multidomain data * Synthetic data * Safety-by-design

Recent Activity

huu-ontocord  authored a paper 8 months ago

ALERT: A Comprehensive Benchmark for Assessing Large Language Models' Safety through Red Teaming

tanmaylaud  authored a paper 9 months ago

Aurora-M: The First Open Source Multilingual Language Model Red-teamed according to the U.S. Executive Order

tanmaylaud  authored a paper 9 months ago

ClimaBench: A Benchmark Dataset For Climate Change Text Understanding in English

View all activity

Team members 2