Stanford AI Lab Blog

DECEMBER 6, 2021

We’re excited to share all the work from SAIL that’s being presented at the main conference , at the Datasets and Benchmarks track and the various workshops , and you’ll find links to papers, videos and blogs below.

Contact 40

Contact Learning Theory Authoring Offline 40

The AI Alignment Forum

FEBRUARY 7, 2025

Interpretability benchmarks: Wed like to support more benchmarks for interpretability research. A benchmark should consist of a set of tasks that good interpretability methods should be able to solve. on targeted attack success rate (i.e., This criterion has some commonalities with the focus in Debenedetti et al.

Research 52

Research Fund Open Technique 52

Google Research AI blog

NOVEMBER 28, 2022

Woodruff * , Fred Zhang * , Qiuyi Zhang Papers From Gradient Flow on Population Loss to Learning with Stochastic Gradient Descent Ayush Sekhari, Satyen Kale , Jason D. Goodman Stochastic Online Learning with Feedback Graphs: Finite-Time and Asymptotic Optimality Teodor V.

Google 52

Google Language Tutorial Offline 52

The AI Alignment Forum

MARCH 28, 2025

In this episode, I speak with Jason Gross about his agenda to benchmark interpretability in this way, and his exploration of the intersection of proofs and modern machine learning. Or according to our singular learning theory friends, the local learning coefficients should be small and that implies this thing about this.

Model 52

Model Network Train Training 52