Search papers, labs, and topics across Lattice.
6
0
5
0
Video diffusion models can revolutionize hand motion reconstruction, achieving unprecedented accuracy without relying on traditional detection or optimization techniques.
DRIVE-CHOREO achieves unprecedented multi-view consistency and BEV mAP by choreographing latent tokens across diverse modalities in autonomous driving.
Incorporating egocentric human video data into robotic training can lead to substantial performance gains, with ACE-EGO-0 setting new benchmarks in VLA tasks.
Dynamic identity memory and large-scale counterfactual self-supervision enable Argus to outperform previous methods in subject-preserving video generation, achieving unprecedented robustness against occlusion and viewpoint changes.
Vision-based tactile signals in the VTOUCH dataset significantly enhance bimanual manipulation capabilities, paving the way for more effective robotic interactions.
Ditching depth sensors, GeoLoco achieves robust zero-shot sim-to-real humanoid locomotion from RGB images alone by cleverly encoding 3D geometric priors from a visual foundation model.
