Search papers, labs, and topics across Lattice.
Affiliation:
3
1
6
7
WorldCrafter is a video world model that learns a camera-queryable implicit 3D-aware memory that enables streaming scene exploration from a single input image or text prompt and shows substantial gains in long-horizon consistency and camera-control accuracy while preserving visual quality during minute-scale exploration.
Achieving photorealistic novel view synthesis from sparse monocular inputs, UniWorld-View revolutionizes how we generate immersive content in dynamic environments.
LingBot-Video bridges the gap between digital creativity and physical actuation, achieving unprecedented efficiency in video pretraining for embodied intelligence.
