Molecular Property Optimization on gpcr like
85Normalized Rewardπ(·|y*)
Evaluation results
| Method | Links | |
|---|---|---|
| π(·|y*)2026.04 | 85 | |
| Reward Weighted Classifier-Free Guidance (RCFG)Inference-time sampling budget |YS|=642026.04 | 54 | |
| Reward Weighted Classifier-Free Guidance (RCFG)Inference-time sampling budget |YS|=322026.04 | 53 | |
| RLRL training budget=20002026.04 | 49 | |
| Reward Weighted Classifier-Free Guidance (RCFG)Inference-time sampling budget |YS|=162026.04 | 42 | |
| Reward Weighted Classifier-Free Guidance (RCFG)Inference-time sampling budget |YS|=82026.04 | 34 | |
| RLRL training budget=10002026.04 | 32 | |
| Reward Weighted Classifier-Free Guidance (RCFG)Inference-time sampling budget |YS|=42026.04 | 22 | |
| RLRL training budget=5002026.04 | 10 | |
| Reward Weighted Classifier-Free Guidance (RCFG)Inference-time sampling budget |YS|=22026.04 | 2 |