Sonia Joseph launches World Mechanics, a neolab for interpretable physical-world foundation models

soniajoseph_ · x · 2026-09-15

Researcher Sonia Joseph is building the founding research team at World Mechanics, a frontier neolab for interpretable models of the physical world. Her thesis: physical AI offers a time-sensitive window to make interpretability and safety first-class objectives from the earliest pretraining stages, using the physical world's ground truth—unlike language—to develop methods capturing causal dynamics directly. Goal: inherently interpretable and controllable foundation models for robotics, autonomous driving, and manufacturing.

Related event: Interpretability researcher Sonia Joseph founds World Mechanics lab(5 posts)→

Original post →

More from Companies & People

Companies & People channel →