Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
When Molecular Similarity Works: Property Cliffs Reveal Hidden Errors
Di Hu, Kun Li, Haojie Rao +6
Accurate prediction of molecular properties underpins drug discovery and material design, yet even state-of-the-art models remain vulnerable to localized failure modes that aggrega…
cs.LG2026
Learning to Select Source Domains: Proxy-Rewarded Policy Optimization for Molecular OOD Generalization
Zhuohao Lin, Kun Li, Jiameng Chen +4
Molecular property prediction under severe out-of-distribution (OOD) shifts remains challenging because conventional scaffold splits can retain local structural similarity between…