| Paper | Code | HD-Score | RC | ModelName | ReleaseDate |
|---|---|---|---|---|---|
| DriveZero: End-to-End Driving Beyond Human Demonstrations | ✓ Link | 46.6 | DriveZero-Scale | 2026-09-05 | |
| SimVTA: Simulation-Grounded Video-Trajectory Alignment for Driving World Action Models | ✓ Link | 38.8 | 51.5 | SimVTA (extra data) | 2026-10-09 |
| Beyond Imitation: Learning Safe End-to-End Autonomous Driving from Hard Negatives | ✓ Link | 34.8 | 46.2 | LTFv7 | 2026-05-19 |
| HAD: Combining Hierarchical Diffusion with Metric-Decoupled RL for End-to-End Driving | 30.8 | 47.5 | HAD-L | 2026-04-04 | |
| Do Better Visual Representations Always Lead to Better End-to-End Autonomous Driving? | ✓ Link | 28.6 | DiffusionDrive-ViRA | 2026-10-07 |