Search papers, labs, and topics across Lattice.
4
36
6
12
One model to control them all: Qwen-VLA achieves impressive zero-shot generalization across diverse robotic tasks and embodiments by unifying vision-language-action modeling.
Forget robot-specific fine-tuning: a unified diffusion model can now learn policies across diverse robot embodiments, boosting performance by 15% and opening doors to truly generalizable robotic agents.
Stop averaging over noisy robot data: PTR selectively trusts training samples based on how well their post-action consequences align with learned representations, leading to more robust offline policy learning.
Forget synthetic data and limited teleoperation: Being-H0 leverages the dexterity and scalability of human hand videos for VLA pretraining, unlocking superior performance in complex manipulation tasks.
