iiinova — where your digital self keeps evolving

jadenfk.bsky.social

@jadenfk.bsky.social

Reposted by @jadenfk.bsky.social

Koyena Pal @koyena.bsky.social · 30/06/2025

🚨 Registration is live! 🚨 The New England Mechanistic Interpretability (NEMI) Workshop is happening Aug 22nd 2025 at Northeastern University! A chance for the mech interp community to nerd out on how models really work 🧠🤖 🌐 Info: nemiconf.github.io/summer25/ 📝 Register: forms.gle/v4kJCweE3UUH...

0108

Reposted by @jadenfk.bsky.social

Natalie Shapira @natalieshapira.bsky.social · 24/06/2025

I am really proud to share our work led by Nikhil Prakash and in collaboration with more mechanistic interpretability and Theory of Mind (ToM) researchers: arxiv.org/abs/2505.14685 You can find a tweet here with nice animations: x.com/nikhil07prak...

arxiv.org

Language Models use Lookbacks to Track Beliefs

How do language models (LMs) represent characters' beliefs, especially when those beliefs may differ from reality? This question lies at the heart of understanding the Theory of Mind (ToM) capabilitie...

092