Search papers, labs, and topics across Lattice.
7
0
9
60
Synthesizing 48,000 interaction trajectories without human input enables a humanoid robot to learn complex loco-manipulation tasks effectively.
The ABC framework empowers researchers with the largest open-source teleoperation dataset and a complete toolkit to accelerate advancements in behavior cloning for robotic manipulation.
Playful learning strategies enable robots to acquire skills that boost performance on new tasks by over 20%, transforming how we approach robotic skill acquisition.
Surflo revolutionizes 3D surface reconstruction by enabling arbitrary-resolution outputs from a single global state, outperforming traditional methods in both speed and accuracy.
Unlock 36% better video depth estimation and 20% better camera pose estimation by simply letting your model learn from its own unlabeled video predictions.
Human-level 3D perception can emerge from a surprisingly simple, scalable learning objective using multi-view images, finally closing the gap between AI and human performance on this fundamental visual task.
Humanoid robots can now perform vision-based parkour, chaining together dynamic skills like climbing, vaulting, and rolling, adapting to real-time obstacle changes.
