Wannan (Winnie) Yang

Welcome to My Corner of the Web! 👋

I’m Winnie, a PhD candidate at New York University (NYU)’s Buzsakilab, where I decode the content of ‘dream’ (replay) to unravel the mechanism of memory consolidation during sleep (my work was recently published in Science 🥳).

From Neuroscience to AI

Recent advancements in Large Language Models (LLMs) have sparked a profound shift in my research focus. I’ve come to recognize that ensuring the safety of artificial intelligence is one of the most critical challenges of our time!

I am also passionate about applying insight from my neuroscience research to build innovative AI-powered human-machine interfaces.

Current Focus

I’ve started the exciting journey of transitioning from neuroscience to AI research. My current interests include:

• Interpretability for AI safety
• Adversarial robustness

NEWS

- [2024-10-01]: Our ‘LLM lying’ paper was submitted to ICLR.

- [2024-05-21]: Our ‘ripple-tagging’ paper was covered in the Quanta Magzine.

- [2024-03-28]: Our ‘ripple-tagging’ paper was published in Science.