Sergey Zakharov

Ego-centric video scaling saturates agent modeling long before object interaction fidelity, revealing a fundamental bottleneck in current world model training paradigms.

Achieving long-range consistency in video generation is now feasible with a hierarchical token approach that balances detail and computational efficiency.

Achieve state-of-the-art 3D scene reconstruction from sparse views with 80% less training data by learning to generate, not just match, 3D structures.