Michael Lepori(@Michael_Lepori) 's Twitter Profileg
Michael Lepori

@Michael_Lepori

CS PhD Student at Brown interested in the intersection of machine learning and cognitive science, but more interested in playing guitar. He/Him.

ID:1351322069221445632

linkhttp://lepori.xyz calendar_today19-01-2021 00:14:27

64 Tweets

306 Followers

477 Following

Apoorv Khandelwal(@apoorvkh) 's Twitter Profile Photo

Calling all academic AI researchers! 🚨
We are conducting a survey on compute resources. We want to help the community better understand our capabilities+needs. We hope that this will help us all advocate for the resources we need!

Please contribute at: forms.gle/3hEie4hj999fiS…

account_circle
Carney Institute for Brain Science(@CarneyInstitute) 's Twitter Profile Photo

Mechanistic interpreters: Aaron Traylor and Jack Merullo of the LUNAR Lab got under the hood of a ChatGPT-like AI to show that this type of AI can adopt some of the same processes the human brain uses. bit.ly/Carneyfabcollab Franklab_LNCC Brown NLP Aaron Traylor Jack Merullo

Mechanistic interpreters: Aaron Traylor and Jack Merullo of the LUNAR Lab got under the hood of a ChatGPT-like AI to show that this type of AI can adopt some of the same processes the human brain uses. bit.ly/Carneyfabcollab @LnccBrown @Brown_NLP @attraylor @jack_merullo_
account_circle
Catherine Chen(@catherineschen) 's Twitter Profile Photo

Super excited to share our perspective/full papers that were accepted at !

1. 'Axiomatic Causal Interventions for Reverse Engineering Relevance Computation in Neural Retrieval Models' w/Jack Merullo Health NLP proposes a new method for IR interpretability

account_circle
Thomas Fel(@Napoolar) 's Twitter Profile Photo

👋👨‍🍳🍵 After a year of cooking up a secret project, I'm thrilled to officially reveal:

The 𝐋𝐄𝐍𝐒 𝐏𝐫𝐨𝐣𝐞𝐜𝐭.

By combining modern tools of Explainable AI, how much can we explain a ResNet50?

🧶

account_circle
Guy Davidson(@guyd33) 's Twitter Profile Photo

New paper alert! There's a wealth of evidence that infants categorize spatial relations starting from 3-4 months onward. Can we evaluate neural networks in similar paradigms to babies, without special relational training? If so, what do we learn? 1/N

sciencedirect.com/science/articl…

account_circle
Jack Merullo(@jack_merullo_) 's Twitter Profile Photo

Our paper was accepted as a spotlight: We look at whether language models reuse attention heads for functionally similar processes across different tasks. Basically, whether LMs implement reusable ‘functions’ in their weights

Our #ICLR2024 paper was accepted as a spotlight: We look at whether language models reuse attention heads for functionally similar processes across different tasks. Basically, whether LMs implement reusable ‘functions’ in their weights
account_circle
Michael Lepori(@Michael_Lepori) 's Twitter Profile Photo

I had a great time working on this project with superstar undergrad Enyan Zhang 张恩言! Take a look at his thread if you're interested in controlling the inductive biases of neural nets. Also, Enyan is applying to PhDs right now - look out for his application!

account_circle