驾驶仿真论文趋势 2023–2026

主要结论

• 驾驶仿真论文从 2023 年的 969 篇增长到 2026 年的 2,200 篇，三年间扩大到约 2.3 倍。
• NeurIPS 是发驾驶仿真论文最多的会议，2023–2026 年共 2,111 篇，占四个会议总量的 36%。
• 交叉方向里涨得最快的是扩散模型：同时属于两个主题的论文从 2023 年的 27 篇增至 2026 年的 205 篇。
• 在「自动驾驶」的 5 个主题里，它的 2026 年论文数排第 1；同组增长最快的运动规划是 2.4 倍，驾驶仿真是 2.3 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 2026$SE(2)$-Aware Conditional Distribution Transport for Vehicle Trajectory Generation
• ICML 2026A Penalty Approach For Differentiation Through Black-box Quadratic Programming Solvers
• ICLR 2026A Schrödinger Eigenfunction Method for Long-Horizon Stochastic Optimal Control
• CVPR 2026A2GC Asymmetric Aggregation with Geometric Constraints for Locally Aggregated Descriptors
• NeurIPS 2025A compressive-expressive communication framework for compositional representations
• ICML 2025A Near-Optimal Single-Loop Stochastic Algorithm for Convex Finite-Sum Coupled Compositional Optimization
• ICLR 2025A Truncated Newton Method for Optimal Transport
• CVPR 20253D-SLNR: A Super Lightweight Neural Representation for Large-scale 3D Mapping
• NeurIPS 2024[Re] CUDA: Curriculum of Data Augmentation for Long‐tailed Recognition
• ICML 2024$H$-Consistency Guarantees for Regression
• ICLR 2024$\texttt{NAISR}$: A 3D Neural Additive Model for Interpretable Shape Representation
• CVPR 2024Decentralized Directed Collaboration for Personalized Federated Learning
• NeurIPS 2023[Re] FOCUS: Flexible Optimizable Counterfactual Explanations for Tree Ensembles
• ICML 2023$H$-Consistency Bounds for Pairwise Misranking Loss Surrogates
• ICLR 2023A Convergent Single-Loop Algorithm for Relaxation of Gromov-Wasserstein in Graph Data
• CVPR 20233DAvatarGAN: Bridging Domains for Personalized Editable Avatars
• NeurIPS 2026A Bitter Lesson for Data Filtering
• ICML 2026A Queueing-Theoretic Framework for Stability Analysis of LLM Inference with KV Cache Memory Constraints
• ICLR 2026Bayesian Neural Networks for Functional ANOVA Model
• CVPR 2026Active Perceptual Inference A Corticothalamic-Inspired Dynamic Nested Recurrent Network for

全部驾驶仿真论文

共 5,881 篇，第 1 / 118 页

1. CVPR 20263D-Fixer Coarse-to-Fine In-place Completion for 3D Scenes from a Single
2. CVPR 20263DReflecNet A Large-Scale Dataset for 3D Reconstruction of Reflective Transparent
3. CVPR 20264D Primitive-Mache Glueing Primitives for Persistent 4D Scene Reconstruction
4. CVPR 20264DWorldBench A Comprehensive Evaluation Framework for 3D4D World Generation Models
5. CVPR 2026A Closed-Form Solution for Debiasing Vision-Language Models with Utility Guarantees
6. CVPR 2026A Debiased Reconstruction-based Framework for Training-Free Detection of AI-Generated Images
7. CVPR 2026A More Word-like Image Tokenization for MLLMs
8. CVPR 2026A Supervised Multi-task Framework for Joint cryo-ET Restoration Enabled by
9. CVPR 2026A2GC Asymmetric Aggregation with Geometric Constraints for Locally Aggregated Descriptors
10. CVPR 2026Action-Geometry Prediction with 3D Geometric Prior for Bimanual Manipulation
11. CVPR 2026Action-Sketcher From Reasoning to Action via Visual Sketches for Robotic
12. CVPR 2026Active Perceptual Inference A Corticothalamic-Inspired Dynamic Nested Recurrent Network for
13. CVPR 2026ActiveAD Planning-Oriented Active Learning for End-to-End Autonomous Driving
14. CVPR 2026ActiveVLA Injecting Active Perception into Vision-Language-Action Models for Precise 3D
15. CVPR 2026ActivityForensics A Comprehensive Benchmark for Localizing Manipulated Activity in Videos
16. CVPR 2026AdaBet Gradient-free Layer Selection for Efficient Training of Deep Neural
17. CVPR 2026Adapter Shield A Unified Framework with Built-in Authentication for Preventing
18. CVPR 2026Adaptive Confidence Regularization for Multimodal Failure Detection
19. CVPR 2026AdaRadar Rate Adaptive Spectral Compression for Radar-based Perception
20. CVPR 2026AdaSFormer Adaptive Serialized Transformers for Monocular Semantic Scene Completion from
21. CVPR 2026AdaSpot Spend Resolution Where It Matters for Precise Event Spotting
22. CVPR 2026AdaSVD Singular Value Decomposition with Adaptive Mechanisms for Large Multimodal
23. CVPR 2026AeroDGS Physically Consistent Dynamic Gaussian Splatting for Single-Sequence Aerial 4D
24. CVPR 2026AeroGS Scale-Aware Gaussian Splatting for Pose-Free Dynamic UAV Scene Reconstruction
25. CVPR 2026AffordGen Generating Diverse Demonstrations for Generalizable Object Manipulation with Affordance
26. CVPR 2026Agent4FaceForgery Multi-Agent LLM Framework for Realistic Face Forgery Detection
27. CVPR 2026Agile Deliberation Concept Deliberation for Subjective Visual Classification
28. CVPR 2026AIMDepth Asymmetric Image-Event Mamba for Monocular Depth Estimation
29. CVPR 2026AirSim360 A Panoramic Simulation Platform within Drone View
30. CVPR 2026Align Once to Explain Feature Alignment for Scalable B-cosification of
31. CVPR 2026All-in-One Slider for Attribute Manipulation in Diffusion Models
32. CVPR 2026AMap Distilling Future Priors for Ahead-Aware Online HD Map Construction
33. CVPR 2026An Instance-Centric Panoptic Occupancy Prediction Benchmark for Autonomous Driving
34. CVPR 2026Anchor-Guided Gradient Alignment for Incomplete Multimodal Learning
35. CVPR 2026Annotation-Efficient Coreset Selection for Context-dependent Segmentation
36. CVPR 2026ApET Approximation-Error Guided Token Compression for Efficient VLMs
37. CVPR 2026Arcadia Toward a Full-Lifecycle Framework for Embodied Lifelong Learning
38. CVPR 2026ARES Unifying Asymmetric RGB-Event Stereo for Probabilistic Scene Flow Estimation
39. CVPR 2026ART Articulated Reconstruction Transformer
40. CVPR 2026Artiverse A Diverse and Physically Grounded Dataset for Articulated Objects
41. CVPR 2026Assignment-Driven Hash Learning in a Hyper-Semantic Space for On-the-Fly Category
42. CVPR 2026Attribute-Preserving Pseudo-Labeling for Diffusion-Based Face Swapping
43. CVPR 2026Authorize-on-Demand Dynamic Authorization with Legality-Aware Intellectual Property Protection for VLMs
44. CVPR 2026AVGGT Rethinking Global Attention for Accelerating VGGT
45. CVPR 2026Balanced Hierarchical Contrastive Learning with Decoupled Queries for Fine-grained Object
46. CVPR 2026BALM A Model-Agnostic Framework for Balanced Multimodal Learning under Imbalanced
47. CVPR 2026Batch Loss Score for Dynamic Data Pruning
48. CVPR 2026BeautyGRPO Aesthetic Alignment for Face Retouching via Dynamic Path Guidance
49. CVPR 2026Beyond CLS Token Query-Driven Token-Level Forgery Purification for Generalizable Deepfake
50. CVPR 2026Beyond Fixed Formulas Data-Driven Linear Predictor for Efficient Diffusion Models

常见问题

2023–2026 年四大会议一共有多少篇驾驶仿真论文？

共 5,882 篇，按年份分别是 2023 年 969 篇、2024 年 1,308 篇、2025 年 1,405 篇、2026 年 2,200 篇。

NeurIPS 2026 有多少篇驾驶仿真论文？

NeurIPS 2026 有 940 篇驾驶仿真论文，上一届是 542 篇。

ICLR 2026 有多少篇驾驶仿真论文？

ICLR 2026 有 313 篇驾驶仿真论文，上一届是 228 篇。

ICML 2026 有多少篇驾驶仿真论文？

ICML 2026 有 363 篇驾驶仿真论文，上一届是 275 篇。

CVPR 2026 有多少篇驾驶仿真论文？

CVPR 2026 有 584 篇驾驶仿真论文，上一届是 360 篇。

哪个会议的驾驶仿真论文最多？

NeurIPS，2023–2026 年共 2,111 篇。