Track new results across pure and applied mathematics.
Search papers, labs, and topics across Lattice.
Affiliation:
4
1
5
3
Autonomous driving VLAs can achieve low-latency inference and SOTA planning by generating actions before CoT, with CoT solely supervising action generation.
VGGD achieves superior rendering quality and geometric consistency by integrating pretrained visual geometry priors into the reconstruction process.
Visual-Geometric Gaussians redefine occupancy prediction by integrating geometric insights with traditional image features, leading to unprecedented accuracy in 3D scene understanding.
End-to-end autonomous driving gets a boost with a new framework that links perception, prediction, and planning in a unified chain of thought, outperforming fragmented approaches.