Search papers, labs, and topics across Lattice.
8
37
7
12
GRAIL achieves an impressive 84% success rate in real-world object pick-up tasks using only synthetic data, revolutionizing humanoid robot training.
Cosmos 3 sets a new benchmark for omnimodal models, outperforming existing state-of-the-art in both Text-to-Image and Image-to-Video tasks.
Generating synthetic data for humanoid robots can boost loco-manipulation performance by 20% compared to relying solely on real-world data.
Forget clunky animation pipelines – MotionBricks lets you assemble real-time, high-quality character motions like LEGOs, even controlling robots.
Co-training's success hinges on a delicate balance: aligning representations across domains while preserving each domain's unique characteristics.
Forget synthetic data—scaling up human egocentric video by 20x unlocks surprisingly effective dexterous robot manipulation, even transferring to robots with different hand configurations.
Forget painstakingly engineering robot behaviors: DreamZero learns directly from video of other robots or even humans, adapting to new tasks and bodies with just minutes of data.
Forget synthetic data that looks like it came from a PS2 game: NVIDIA's new Cosmos-Predict2.5 generates high-fidelity videos for training embodied AI, opening the door to more realistic and reliable simulations.
