Machine Learning-Aided Small-Molecule Virtual Screening: Recent Advances and Future Perspectives
We comprehensively review how AI and machine learning are reshaping small-molecule virtual screening, spanning AI-driven scoring functions, efficient search algorithms, and the paradigm shift toward generative de novo molecular design.
Sep 1, 2026
Elite-Weighted Supervised Fine-tuning for Goal-Directed Molecular Optimization
We introduce Elite-Weighted Supervised Fine-tuning (EW-SFT), which passes reward through elite selection and updates the model with its own pretraining loss, yielding a single optimizer that transfers across autoregressive, masked-diffusion, and discrete-flow molecular generators.
Aug 31, 2026