I'm an aspiring research scientist from Brazil, and currently a Research Scholar at Cohere for AI where I study toxicity mitigation in Large Language Models. I'm also writing my master's dissertation on the same topic at Recod.ai @ Unicamp (#5 LatAm).
I also enjoy learning about probabilistic learning, data efficiency and generative modeling!
Don't hesitate sending me an email: luiza.pozzobon@gmail.com!