端到端驾驶论文趋势 2023–2026

主要结论

• 端到端驾驶论文从 2023 年的 33 篇增长到 2026 年的 58 篇，三年间扩大到约 1.8 倍。
• CVPR 是发端到端驾驶论文最多的会议，2023–2026 年共 71 篇，占四个会议总量的 44%。
• 交叉方向里涨得最快的是多模态大模型：同时属于两个主题的论文从 2023 年的 0 篇增至 2026 年的 11 篇。
• 在「自动驾驶」的 5 个主题里，它的 2026 年论文数排第 5；同组增长最快的运动规划是 2.4 倍，端到端驾驶是 1.8 倍。

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

• NeurIPS 2026AlignDrive: Aligned Lateral-Longitudinal Planning for End-to-End Autonomous Driving
• ICML 2026Hide&Seek: Learning to Explain in an End-to-End Differentiable Network
• ICLR 2026RAP: 3D Rasterization Augmented End-to-End Planning
• CVPR 2026Bias at the End of the Score
• NeurIPS 2025Embodied Cognition Augmented End2End Autonomous Driving
• ICML 2025GuidedQuant: Large Language Model Quantization via Exploiting End Loss Guidance
• ICLR 2025MGMapNet: Multi-Granularity Representation Learning for End-to-End Vectorized HD Map Construction
• CVPR 2025Bridging Past and Future: End-to-End Autonomous Driving with Historical Prediction and Planning
• NeurIPS 2024Bench2Drive: Towards Multi-Ability Benchmarking of Closed-Loop End-To-End Autonomous Driving
• ICML 2024Learning Exceptional Subgroups by End-to-End Maximizing KL-Divergence
• ICLR 2024DV-3DLane: End-to-end Multi-modal 3D Lane Detection with Dual-view Representation
• CVPR 2024HIMap: HybrId Representation Learning for End-to-end Vectorized HD Map Construction
• NeurIPS 2023[Re] End-to-end Algorithm Synthesis with Recurrent Networks: Logical Extrapolation Without Overthinking
• ICML 2023End-to-end Differentiable Clustering with Associative Memories
• ICLR 2023E3Bind: An End-to-End Equivariant Network for Protein-Ligand Docking
• CVPR 2023End-to-End Vectorized HD-Map Construction With Piecewise Bezier Curve
• NeurIPS 2026On the Existence of Uniformly Optimal Policies in MDPs under Epistemic Uncertainty
• ICML 2026RoCA: Robust Cross-Domain End-to-End Autonomous Driving
• ICLR 2026THE END OF MANUAL DECODING: TOWARDS TRULY END-TO-END LANGUAGE MODELS
• CVPR 2026LEAD Minimizing Learner-Expert Asymmetry in End-to-End Driving

全部端到端驾驶论文

共 15 篇，第 1 / 1 页

1. NeurIPS 2026$\chi$-Bench: Can AI Agents Automate End-to-End, Long-Horizon, Policy-Rich Healthcare Workflows?
2. NeurIPS 2026AlignDrive: Aligned Lateral-Longitudinal Planning for End-to-End Autonomous Driving
3. NeurIPS 2026BankerToolBench: Evaluating AI Agents in End-to-End Investment Banking Workflows
4. NeurIPS 2026Beyond Masked Sparsity: SNACK Enables Truly Sparse Neural Networks on GPU
5. NeurIPS 2026Closed Loop Dynamic Driving Data Mixture for Real-Synthetic Co-Training
6. NeurIPS 2026DriveMind: Mind-Evolving Belief Tracking for Closed-Loop Autonomous Driving
7. NeurIPS 2026DriveSpatial: A Benchmark for Spatiotemporal Intelligence in VLMs for Autonomous Driving
8. NeurIPS 2026Driving on Memory
9. NeurIPS 2026HiFloat4 Format for End-To-End Reinforcement Learning Post-Training of Large Language Models
10. NeurIPS 2026LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
11. NeurIPS 2026On the Existence of Uniformly Optimal Policies in MDPs under Epistemic Uncertainty
12. NeurIPS 2026TopoCurve: Geometry-Aware Topology Reasoning via Bézier Curves in Autonomous Driving
13. NeurIPS 2026Towards Generalizable Data Valuation: Learning an End-to-end Deep Model to Compute Shapley Values
14. NeurIPS 2026Trajectory Evaluation via Rollout-Free World Model for End-to-end Autonomous Driving
15. NeurIPS 2026TwinFlux: One-Step Discrete-Continuous Flow for End-to-End Autonomous Driving

常见问题

2023–2026 年四大会议一共有多少篇端到端驾驶论文？

共 161 篇，按年份分别是 2023 年 33 篇、2024 年 31 篇、2025 年 39 篇、2026 年 58 篇。

NeurIPS 2026 有多少篇端到端驾驶论文？

NeurIPS 2026 有 15 篇端到端驾驶论文，上一届是 18 篇。

ICLR 2026 有多少篇端到端驾驶论文？

ICLR 2026 有 12 篇端到端驾驶论文，上一届是 5 篇。

ICML 2026 有多少篇端到端驾驶论文？

ICML 2026 有 4 篇端到端驾驶论文，上一届是 4 篇。

CVPR 2026 有多少篇端到端驾驶论文？

CVPR 2026 有 27 篇端到端驾驶论文，上一届是 12 篇。

哪个会议的端到端驾驶论文最多？

CVPR，2023–2026 年共 71 篇。