Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
D convolutions on projected point cloud representations, avoiding the cost of
2
0
4
SNNs can now achieve comparable accuracy to CNNs on complex 3D object detection tasks while slashing energy consumption, thanks to learned spike representations and end-to-end training.
Autonomous vehicles can now better adapt to the messy, ever-changing real world thanks to a new motion forecasting method that learns new object classes on the fly without forgetting old ones.