Molecular Property Optimization on 3d complex
97Normalized Rewardπ(·|y*)
Evaluation Results
| Method | Links | |
|---|---|---|
| π(·|y*)2026.04 | 97 | |
| RLRL training budget=20002026.04 | 92 | |
| RLRL training budget=10002026.04 | 90 | |
| RLRL training budget=5002026.04 | 73 | |
| Reward Weighted Classifier-Free Guidance (RCFG)Inference-time sampling budget |YS|=642026.04 | 68 | |
| Reward Weighted Classifier-Free Guidance (RCFG)Inference-time sampling budget |YS|=322026.04 | 63 | |
| Reward Weighted Classifier-Free Guidance (RCFG)Inference-time sampling budget |YS|=162026.04 | 62 | |
| Reward Weighted Classifier-Free Guidance (RCFG)Inference-time sampling budget |YS|=82026.04 | 53 | |
| Reward Weighted Classifier-Free Guidance (RCFG)Inference-time sampling budget |YS|=42026.04 | 39 | |
| Reward Weighted Classifier-Free Guidance (RCFG)Inference-time sampling budget |YS|=22026.04 | 19 |