What 30,000 Hours of Ego-centric Video Does Not Teach
The authors scale Cosmos 3 ego-centric video world models from 300 to 30,000 hours and directly measure interaction fidelity (agent hands/body and manipulated objects) on an out-of-distribution benchmark. Data scaling improves both but unevenly: agent fidelity saturates early and conditioning can reach its ceiling with far less data, while object fidelity remains far lower and improves slowly. They introduce object-centric adaptive noise scheduling to improve object dynamics, with a remaining gap.
