Search papers, labs, and topics across Lattice.
2
48
6
44
Robots can now perceive objects more like humans, even experiencing cross-modal illusions, thanks to a new visuo-tactile fusion model that learns and infers physical properties over time.
Forget RNNs for modeling dynamics: a Kalman filter-VAE hybrid can learn state-space representations that disentangle static and dynamic features, outperforming previous models in prediction accuracy and system identification.
