Search papers, labs, and topics across Lattice.
3
0
4
Trust prediction accuracy improves significantly when trust evidence is treated as distinct channels rather than a single undifferentiated input.
Forget view consistency tricks – language-driven 3D editing leaps forward by explicitly modeling semantic relationships between 2D edits and 3D Gaussians.
Resolving semantic conflicts between synonymous prompts and across categories dramatically improves the stability and accuracy of open-vocabulary semantic segmentation, all without requiring any additional training.
