Our work
We prepare in-depth reviews of proven and emerging techniques, illustrate and benchmark them with best-practices playbooks and code, and communicate them with visually rich showcases and trainings. We also maintain a blog with introductory material and paper reviews, and hold a weekly seminar where we cover both the foundations and recent advances in AI.
Our areas of interest
Explore everything
What we are reading:
Paper pills
Denoising Diffusion and Score Based Generative Models
Progressive Distillation for Fast Sampling of Diffusion Models
Comparing Distributions by Measuring Differences that Affect Decision Making
Score-Based Generative Modeling with Critically-Damped Langevin Diffusion
Neural Collapse in deep classifiers during Terminal Phase of Training
Come to our seminar
Data (e)valuation and model interpretation: a game theoretic approach
Bayesian optimal experiment design (2 of 2)