Topic: human models

Investigate how detailed human models reconstructed from multiple videos can be rigged and animated. Review recent methods, propose model or architecture improvements, enhance training datasets and implement a proof of concept for comparative evaluation. Join the KINETIX team at Inria Grenoble. The advertised start is 1 November 2026; remuneration starts at EUR 2,692 depending on qualifications and experience.

Jon Kleinberg examines how AI world models differ from human models and how these differences affect joint decision-making. Examples from chess, navigation and generative systems show that competence alone may fail to support a weaker human partner or accommodate unexpected changes. The talk also considers theoretical cases where successful generation does not imply that an agent can identify the model generating its observations.