Molecular Property Optimization on low mw high potency
0.47Normalized RewardRL
Evaluation Results
| Method | Links | |
|---|---|---|
| RLRL training budget=20002026.04 | 0.47 | |
| Reward Weighted Classifier-Free Guidance (RCFG)Inference-time sampling budget |YS|=162026.04 | 0.45 | |
| Reward Weighted Classifier-Free Guidance (RCFG)Inference-time sampling budget |YS|=322026.04 | 0.44 | |
| Reward Weighted Classifier-Free Guidance (RCFG)Inference-time sampling budget |YS|=642026.04 | 0.44 | |
| π(·|y*)2026.04 | 0.41 | |
| RLRL training budget=10002026.04 | 0.41 | |
| Reward Weighted Classifier-Free Guidance (RCFG)Inference-time sampling budget |YS|=82026.04 | 0.39 | |
| Reward Weighted Classifier-Free Guidance (RCFG)Inference-time sampling budget |YS|=42026.04 | 0.3 | |
| RLRL training budget=5002026.04 | 0.3 | |
| Reward Weighted Classifier-Free Guidance (RCFG)Inference-time sampling budget |YS|=22026.04 | 0.15 |