Search papers, labs, and topics across Lattice.
5
0
6
7
Future scene geometry, not pixel data, is the key to unlocking superior driving policies in autonomous systems.
TraVEL boosts motion-centric video retrieval performance by up to 9.8 points in mAP, proving that trajectory-guided learning can outperform traditional methods without complex rule systems.
Forget training from scratch: surprisingly, off-the-shelf 2D diffusion models can unlock generalizable style control in 3D generation models, even for out-of-distribution styles.
Agents can now "hallucinate" optimal viewpoints for reasoning by storing and re-rendering scenes with 3D Gaussian Splatting, enabling recovery from initial observation failures.
Explicitly reconstructing 3D scenes with Gaussian Splatting unlocks state-of-the-art BEV perception, proving that geometric understanding is key to accurate spatial reasoning.
