Search papers, labs, and topics across Lattice.
4
1
5
12
LingBot-VA 2.0 achieves few-shot generalization in complex robot manipulation tasks, outperforming traditional video generative models.
LingBot-Video bridges the gap between digital creativity and physical actuation, achieving unprecedented efficiency in video pretraining for embodied intelligence.
Explore new worlds with unprecedented fidelity: OmniRoam lets you wander through long-horizon, high-resolution panoramic videos generated from a single image or video.
Forget geometric LODs: tokenizing 3D shapes by semantic salience unlocks SOTA reconstruction and efficient autoregressive generation with 10x-1000x fewer tokens.
