Search papers, labs, and topics across Lattice.
3
0
5
Achieving long-range consistency in video generation is now feasible with a hierarchical token approach that balances detail and computational efficiency.
By enabling robots to learn from synthesized data in novel contexts without additional motion data, RoboDream transforms the landscape of robot learning efficiency.
Fine-tuning Vision-Language Model planners for robotic manipulation is now significantly more efficient and safer thanks to a novel framework that leverages video world models to simulate real-world physics.
