Search papers, labs, and topics across Lattice.
3
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.
Achieving an average binding score of -8.85 kcal/mol, conDitar-dev not only excels in binding affinity but also optimizes for critical drug developability properties, setting a new standard in computational drug design.
