inFERENCe

Discrete Diffusion: Continuous-Time Markov Chains

We may finally crack Maths. But should we?

Mortal Komputation: On Hinton's argument for superhuman AI.

Autoregressive Models, OOD Prompts and the Interpolation Regime

We May be Surprised Again: Why I take LLMs seriously.

Implicit Bayesian Inference in Large Language Models

Eastern European Guide to Writing Reference Letters

Causal inference 4: Causal Diagrams, Markov Factorization, Structural Equation Models

On Information Theoretic Bounds for SGD

Notes on the Origin of Implicit Regularization in SGD

An information maximization view on the $\beta$-VAE objective

Some Intuition on the Neural Tangent Kernel

Notes on Causally Correct Partial Models

Meta-Learning Millions of Hyper-parameters using the Implicit Function Theorem

The secular Bayesian: Using belief distributions without really believing