Search papers, labs, and topics across Lattice.
5
0
7
Action flow transforms robot control by allowing models to learn from diverse data without task-specific demonstrations, achieving unprecedented accuracy in motion prediction.
REAR transforms how we achieve user preference alignment in LLMs, enabling scalable realignment without costly retraining.
Grounded verification in TEXEDO enables humanoid robots to execute complex motions that are both semantically aligned with text prompts and physically feasible.
Continuous loco-manipulation is now achievable, allowing humanoids to perform dexterous tasks like grasping and carrying without stopping.
Forget clunky animation pipelines – MotionBricks lets you assemble real-time, high-quality character motions like LEGOs, even controlling robots.