List your company

Multi-objective molecular optimization (BDP) on MuMOInstruct (unseen instruction)

31Success Rate (SR)SFT
0.4248.36216.324.238Mar 6, 2026

Evaluation results

MethodLinks
SFT2026.033126.18.1
RePO2026.0319.857.211.3
GRPOinitialization=None2026.0314.872.710.8
GRPOinitialization=SFT init2026.039.214.71.4
Base Model2026.035.214.30.7
Distill-SFT2026.031.69.90.2