Search papers, labs, and topics across Lattice.
Affiliation:
5
0
6
5
DESCENT achieves unprecedented accuracy in airport surface movement prediction by leveraging adaptive context sampling to navigate complex operational environments.
Get pixel-perfect attribution maps for vision transformers without the computational cost of perturbation or the biases of propagation methods.
Streaming motion forecasting can now handle variable observation lengths without sacrificing accuracy, unlocking more robust real-world performance.
A lightweight transformer can accurately forecast diverse aircraft trajectories in complex airspace, outperforming prior methods and enabling real-time safety applications.
Achieve state-of-the-art trajectory prediction with significantly reduced latency by anchoring future predictions on past trajectory endpoints.
