Search papers, labs, and topics across Lattice.
The University of Manchester
2
0
2
A single quadrupedal locomotion policy can dynamically adapt its gait and performance across stability, energy, and tracking objectives solely through runtime preference inputs, achieving up to 59% reduction in peak attitude deviation.
GACTGAN offers a computationally cheaper and more effective Bayesian GAN for tabular data synthesis, outperforming CTGAN in utility and privacy.
