Search papers, labs, and topics across Lattice.
3
1
7
116
Generate more realistic and diverse safety-critical autonomous vehicle scenarios by using conditional latent flow matching to bridge the gap between real-world and simulated data.
Achieve SE(2)-equivariance in transformer-based agent modeling without the quadratic computational cost, unlocking scalability for self-driving applications.
Vision foundation models can be effectively adapted to significantly improve the detection of rare, safety-critical objects in 3D autonomous driving scenarios, even with limited training data.
