驾驶仿真论文趋势 2023–2026
闭环仿真
统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 5,882 篇被归入该主题的论文。
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。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 219 | 182 | 218 | 350 | 969 |
| 2024 | 410 | 176 | 358 | 364 | 1,308 |
| 2025 | 542 | 228 | 275 | 360 | 1,405 |
| 2026 | 940 | 313 | 363 | 584 | 2,200 |
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 1,405 篇，第 18 / 29 页
- ICML 2025UnHiPPO: Uncertainty-aware Initialization for State Space Models
- ICML 2025Unified Screening for Multiple Diseases
- ICML 2025Uniform Mean Estimation for Heavy-Tailed Distributions via Median-of-Means
- ICML 2025UniSim: A Unified Simulator for Time-Coarsened Dynamics of Biomolecules
- ICML 2025Universal Biological Sequence Reranking for Improved De Novo Peptide Sequencing
- ICML 2025Unnatural Languages Are Not Bugs but Features for LLMs
- ICML 2025Variance-Reduced Forward-Reflected-Backward Splitting Methods for Nonmonotone Generalized Equations
- ICML 2025VinePPO: Refining Credit Assignment in RL Training of LLMs
- ICML 2025Volume-Aware Distance for Robust Similarity Learning
- ICML 2025WAVE: Weighted Autoregressive Varying Gate for Time Series Forecasting
- ICML 2025WGFormer: An SE(3)-Transformer Driven by Wasserstein Gradient Flows for Molecular Ground-State Conformation Prediction
- ICML 2025When Will It Fail?: Anomaly to Prompt for Forecasting Future Anomalies in Time Series
- ICML 2025WOMD-Reasoning: A Large-Scale Dataset for Interaction Reasoning in Driving
- NeurIPS 2025$\boldsymbol{\lambda}$-Orthogonality Regularization for Compatible Representation Learning
- NeurIPS 20251000+ FPS 4D Gaussian Splatting for Dynamic Scene Rendering
- NeurIPS 20253DPE-Gaze:Unlocking the Potential of 3D Facial Priors for Generalized Gaze Estimation
- NeurIPS 202570% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float (DFloat11)
- NeurIPS 2025A Clean Slate for Offline Reinforcement Learning
- NeurIPS 2025A CLT for Polynomial GNNs on Community-Based Graphs
- NeurIPS 2025A compressive-expressive communication framework for compositional representations
- NeurIPS 2025A Computationally Viable Numerical Gradient-based Technique for Optimal Covering Problems
- NeurIPS 2025A Controllable Examination for Long-Context Language Models
- NeurIPS 2025A Driving-Style-Adaptive Framework for Vehicle Trajectory Prediction
- NeurIPS 2025A Fair Federated Learning Method for Handling Client Participation Probability Inconsistencies in Heterogeneous Environments
- NeurIPS 2025A Latent Multilayer Graphical Model For Complex, Interdependent Systems
- NeurIPS 2025A Learning-Augmented Dynamic Programming Approach for Orienteering Problem with Time Windows
- NeurIPS 2025A Physics-preserved Transfer Learning Method for Differential Equations
- NeurIPS 2025A Practical Guide for Incorporating Symmetry in Diffusion Policy
- NeurIPS 2025A Pre-training Framework for Relational Data with Information-theoretic Principles
- NeurIPS 2025A Single-Loop First-Order Algorithm for Linearly Constrained Bilevel Optimization
- NeurIPS 2025A Single-Loop Gradient Algorithm for Pessimistic Bilevel Optimization via Smooth Approximation
- NeurIPS 2025A Single-Swap Local Search Algorithm for k-Means of Lines
- NeurIPS 2025A Stable Whitening Optimizer for Efficient Neural Network Training
- NeurIPS 2025A Sustainable AI Economy Needs Data Deals That Work for Generators
- NeurIPS 2025A Temporal Difference Method for Stochastic Continuous Dynamics
- NeurIPS 2025A Theoretical Framework for Grokking: Interpolation followed by Riemannian Norm Minimisation
- NeurIPS 2025A unified framework for establishing the universal approximation of transformer-type architectures
- NeurIPS 2025A Unified Framework for Variable Selection in Model-Based Clustering with Missing Not at Random
- NeurIPS 2025Accelerated Evolving Set Processes for Local PageRank Computation
- NeurIPS 2025Accelerating Block Coordinate Descent for LLM Finetuning via Landscape Expansion
- NeurIPS 2025Accelerating data-driven algorithm selection for combinatorial partitioning problems
- NeurIPS 2025Accelerating Visual-Policy Learning through Parallel Differentiable Simulation
- NeurIPS 2025ACCO: Accumulate While You Communicate for Communication-Overlapped Sharded LLM Training
- NeurIPS 2025AccuQuant: Simulating Multiple Denoising Steps for Quantizing Diffusion Models
- NeurIPS 2025Accurate KV Cache Eviction via Anchor Direction Projection for Efficient LLM Inference
- NeurIPS 2025Act to See, See to Act: Diffusion-Driven Perception-Action Interplay for Adaptive Policies
- NeurIPS 2025Activation-Guided Consensus Merging for Large Language Models
- NeurIPS 2025Active Measurement: Efficient Estimation at Scale
- NeurIPS 2025Activity Pruning for Efficient Spiking Neural Networks
- NeurIPS 2025Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference
在 Claude、Cursor 里直接问这个趋势
接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。
可以直接复制这句话问 AI
用 paperlist 查驾驶仿真在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？
AI 会调用的工具：get_topic_stats {"topic": "simulation-for-driving"}
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。