Track new results across pure and applied mathematics.
Search papers, labs, and topics across Lattice.
3
0
4
0
No single large model dominates in parametric CAD modeling, revealing significant trade-offs in executability and visual-semantic identity.
VisCAD-M1 outperforms existing models in CAD design by effectively bridging the gap between user intent and executable design, achieving a new state of the art.
Early-stage solutions can reliably inform final outcomes, leading to a 56.9% reduction in the primal gap for MILP problems.