NTR: Neural Token Reconstruction for Scene Token Bottleneck in End-to-EndDriving
Overview
This research proposes NTR, a representation learning framework that improves the compact visual representation learning and planning performance in perception-free end-to-end driving by directly constraining the scene-token bottleneck through self-distillation masked latent reconstruction and semantic priors. The method achieves state-of-the-art results on three public autonomous driving benchmarks.
From arXiv Robotics — research abstracts
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Reported quantity · RFS: 8.0461 other · Basis not reported
“tion heads. All auxiliary reconstruction components are removed at inference time, leaving the deployed planner unchanged. NTR achieves state-of-the-art performance on three public autonomous driving benchmarks, including 8.0461 RFS on Waymo E2E and 94.1 PDMS / 90.9 EPDMS on NavSim1&2. The learned scene tokens exhibit lower pairwise redundancy and higher effective rank, indicating that effective bottleneck supervisio”
Exact source · revision 1Source owner not reported
Reported quantity · PDMS: 94.1 other · Basis not reported
“tion heads. All auxiliary reconstruction components are removed at inference time, leaving the deployed planner unchanged. NTR achieves state-of-the-art performance on three public autonomous driving benchmarks, including 8.0461 RFS on Waymo E2E and 94.1 PDMS / 90.9 EPDMS on NavSim1&2. The learned scene tokens exhibit lower pairwise redundancy and higher effective rank, indicating that effective bottleneck supervisio”
Exact source · revision 1Source owner not reported
Reported quantity · EPDMS: 90.9 other · Basis not reported
“tion heads. All auxiliary reconstruction components are removed at inference time, leaving the deployed planner unchanged. NTR achieves state-of-the-art performance on three public autonomous driving benchmarks, including 8.0461 RFS on Waymo E2E and 94.1 PDMS / 90.9 EPDMS on NavSim1&2. The learned scene tokens exhibit lower pairwise redundancy and higher effective rank, indicating that effective bottleneck supervisio”
Exact source · revision 1Source owner not reported
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalNTR: Neural Token Reconstruction for Scene Token Bottleneck in End-to-End Driving
This research proposes NTR, a representation learning framework that improves the compact visual representation learning and planning performance in perception-free end-to-end driving by directly constraining the scene-token bottleneck through self-distillation masked latent reconstruction and semantic priors. The method achieves state-of-the-art results on three public autonomous driving benchmarks.
Event coverage history
Current attention 3·Peak within the comparable range 3（2026-10-31 17:00 UTC）·Change within the comparable range over 24 hours –
The trend compares participants observed continuously; its scope may be narrower than current attention totals. Hover or click to explore hourly observations, or use the left and right arrow keys.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).