Search papers, labs, and topics across Lattice.
6
196
6
8
Achieving state-of-the-art multimodal performance with only 208.62 million unique images and a theoretical training cost of just $400K challenges the notion that larger datasets and budgets are always necessary for success.
EgoCS-400K bridges the gap between passive video datasets and costly real-world data, offering a scalable solution for training interactive world models.
Forget tedious optimization – LightHarmony3D generates realistic lighting and shadows for inserted 3D objects in a single pass, making scene augmentation feel truly real.
Achieve state-of-the-art outlier robustness and threshold resilience in geometric estimation with a surprisingly efficient branch-and-bound approach.
Achieve higher accuracy in dual-arm robot calibration by unifying coordinate and kinematic parameter estimation within a single Lie-algebraic framework, eliminating artificial error separation.
Open-source 3D asset generation just leveled up: Hunyuan3D 2.0 delivers high-resolution, textured 3D models that outperform both open and closed-source alternatives.
