World Modeling: Evaluation and State Computation

Simons Institute for the Theory of Computing · Intermediate ·🚀 Entrepreneurship & Startups ·3w ago

About this lesson

Yoav Artzi (Cornell University) https://simons.berkeley.edu/talks/yoav-artzi-cornell-university-2026-06-11 Topics in Intelligence: World Models and Social Reasoning This talk briefly describes three projects. The first two focus on evaluating world modeling capabilities in frontier models through the evaluation of dual perspective reasoning and knot manipulation. The third part describes the state separation hypothesis, which posits that mechanically separating prediction from state computation in LLMs benefits performance.

Original Description

Yoav Artzi (Cornell University) https://simons.berkeley.edu/talks/yoav-artzi-cornell-university-2026-06-11 Topics in Intelligence: World Models and Social Reasoning This talk briefly describes three projects. The first two focus on evaluating world modeling capabilities in frontier models through the evaluation of dual perspective reasoning and knot manipulation. The third part describes the state separation hypothesis, which posits that mechanically separating prediction from state computation in LLMs benefits performance.
Watch on YouTube ↗ (saves to browser)
Sign in to unlock AI tutor explanation · ⚡30

Related Reads

Up next
Watch this before applying for jobs as a developer.
Tech With Tim
Watch →