Search papers, labs, and topics across Lattice.
2
0
3
LLMs can be trained to learn from their own multi-turn optimization history, achieving substantial gains in similarity-constrained molecular property improvement.
Generating topologically novel drug scaffolds no longer requires sacrificing 3D pharmacophore geometry, achieving 11.7% greater 2D divergence alongside 7.3% tighter 3D shape alignment purely through inference-time trajectory editing.
