The $k$-server conjecture states that a deterministic online algorithm can achieve competitive ratio $k$ on every metric space. We prove the conjecture. Specifically, we show that the work function al...

New research indicates that AI agents learn compressible models of data, which don’t have enough space to enable memorization.

New research indicates that AI agents learn compressible models of data, which don’t have enough space to enable memorization.

Course topics and reading list.

Talk recordings from FORC 2026

An ICML 2026 tutorial on making probabilistic predictions trustworthy for downstream decision-making and collaboration.

An ICML 2026 tutorial on making probabilistic predictions trustworthy for downstream decision-making and collaboration.

What machine learning theorists learned using AI agents to generate proofs — and what comes next.

What machine learning theorists learned using AI agents to generate proofs — and what comes next.

What machine learning theorists learned using AI agents to generate proofs — and what comes next.