List your company

Molecular Property Optimization on high mw high qed

2.84Normalized RewardRL
0.240.9151.592.265Apr 16, 2026

Evaluation results

MethodLinks
RLRL training budget=20002026.042.84
RLRL training budget=10002026.041.26
π(·|y*)2026.040.7
Reward Weighted Classifier-Free Guidance (RCFG)Inference-time sampling budget |YS|=642026.040.59
Reward Weighted Classifier-Free Guidance (RCFG)Inference-time sampling budget |YS|=162026.040.58
Reward Weighted Classifier-Free Guidance (RCFG)Inference-time sampling budget |YS|=322026.040.58
Reward Weighted Classifier-Free Guidance (RCFG)Inference-time sampling budget |YS|=82026.040.55
Reward Weighted Classifier-Free Guidance (RCFG)Inference-time sampling budget |YS|=42026.040.47
RLRL training budget=5002026.040.41
Reward Weighted Classifier-Free Guidance (RCFG)Inference-time sampling budget |YS|=22026.040.34