I think Bisky :)

When I first started reading papers in ~2007 we would wait for someone who attended the conference to bring back the conference booklet and tell us what to read. We’d read them. And then spend the next three months reading old papers or working cuz 🤷 It was a great way to grow up.

👋 Time is a weird thing :) maybe I should try and convince the department to force you to give a talk sometime — though ideally with @spandanagella.bsky.social too ;)

Just use your own domain name?

3. How to Train Your Fact Verifier: Knowledge Transfer with Multimodal Open Models
^^ includes @skgabrie.bsky.social who is just starting up her lab at UCLA!

2. Gradient Localization Improves Lifelong Pretraining of Language Models
TL;DR - Gradient norms tell you where your knowledge is stored and if it conflicts with what you already know.