Search papers, labs, and topics across Lattice.
4
0
5
4
Bridging the gap between online trajectory estimation and offline image synthesis, this framework achieves unprecedented realism in handwritten text generation.
VibeAct reveals that leveraging real-time vibro-acoustic feedback can drastically enhance robotic dexterity in contact-rich environments, outperforming traditional proprioception methods.
Forget expensive tactile sensors – microphones and a lightweight CNN can give you accurate, real-time in-hand slip estimation.
Unlock slider-style control over video attributes like motion magnitude and effect intensity without retraining your text-to-video model – just nudge the spatiotemporal tokens.
