世界模型论文趋势 2023–2026

主要结论

• 世界模型论文从 2023 年的 23 篇增长到 2026 年的 250 篇，三年间扩大到约 11 倍。
• NeurIPS 是发世界模型论文最多的会议，2023–2026 年共 159 篇，占四个会议总量的 37%。
• 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 1 篇增至 2026 年的 34 篇。
• 在「前沿系统」的 4 个主题里，它的 2026 年论文数排第 4；同组增长最快的AI 智能体是 12 倍，世界模型是 11 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 2026A Hierarchical World Model for Driving
• ICML 2026A Deep Learning Model of Mental Rotation Informed by Interactive VR Experiments
• ICLR 2026Astra: General Interactive World Model with Autoregressive Denoising
• CVPR 2026Active Intelligence in Video Avatars via Closed-loop World Modeling
• NeurIPS 2025COME: Adding Scene-Centric Forecasting Control to Occupancy World Model
• ICML 2025A Causal World Model Underlying Next Token Prediction: Exploring GPT in a Controlled Environment
• ICLR 2025AdaWM: Adaptive World Model based Planning for Autonomous Driving
• CVPR 2025DIO: Decomposable Implicit 4D Occupancy-Flow World Model
• NeurIPS 2024A Data-Centric Perspective on Evaluating Machine Learning Models for Tabular Data
• ICML 20243D-VLA: A 3D Vision-Language-Action Generative World Model
• ICLR 2024Copilot4D: Learning Unsupervised World Models for Autonomous Driving via Discrete Diffusion
• CVPR 2024DriveWorld: 4D Pre-trained Scene Understanding via World Models for Autonomous Driving
• NeurIPS 2023Action Inference by Maximising Evidence: Zero-Shot Imitation from Observation with World Models
• ICML 2023Do Embodied Agents Dream of Pixelated Sheep: Embodied Decision Making using Language Guided World Modelling
• ICLR 2023Dynamic Update-to-Data Ratio: Minimizing World Model Overfitting
• NeurIPS 2026A World Model of Radiologist Reading for Medical Image Representation Learning
• ICML 2026Behavior-Invariant Task Representation Learning with Transformer-based World Models for Offline Meta-Reinforcement Learning
• ICLR 2026Building spatial world models from sparse transitional episodic memories
• CVPR 2026Chain of World World Model Thinking in Latent Motion
• NeurIPS 2025DMWM: Dual-Mind World Model with Long-Term Imagination

全部世界模型论文

共 23 篇，第 1 / 1 页

1. ICLR 2023Dynamic Update-to-Data Ratio: Minimizing World Model Overfitting
2. ICLR 2023Interaction-Based Disentanglement of Entities for Object-Centric World Models
3. ICLR 2023MoDem: Accelerating Visual Model-Based Reinforcement Learning with Demonstrations
4. ICLR 2023On the Feasibility of Cross-Task Transfer with Model-Based Reinforcement Learning
5. ICLR 2023Transformer-based World Models Are Happy With 100k Interactions
6. ICLR 2023Transformers are Sample-Efficient World Models
7. ICLR 2023Value Memory Graph: A Graph-Structured World Model for Offline Reinforcement Learning
8. ICML 2023Do Embodied Agents Dream of Pixelated Sheep: Embodied Decision Making using Language Guided World Modelling
9. ICML 2023Go Beyond Imagination: Maximizing Episodic Reachability with World Models
10. ICML 2023Multi-View Masked World Models for Visual Robotic Manipulation
11. NeurIPS 2023Action Inference by Maximising Evidence: Zero-Shot Imitation from Observation with World Models
12. NeurIPS 2023CQM: Curriculum Reinforcement Learning with a Quantized World Model
13. NeurIPS 2023Facing Off World Model Backbones: RNNs, Transformers, and S4
14. NeurIPS 2023Imagine the Unseen World: A Benchmark for Systematic Generalization in Visual World Models
15. NeurIPS 2023Language Models Meet World Models: Embodied Experiences Enhance Language Models
16. NeurIPS 2023Learning Dynamic Attribute-factored World Models for Efficient Multi-object Reinforcement Learning
17. NeurIPS 2023Learning World Models with Identifiable Factorization
18. NeurIPS 2023Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Planning
19. NeurIPS 2023Multi Time Scale World Models
20. NeurIPS 2023Pre-training Contextualized World Models with In-the-wild Videos for Reinforcement Learning
21. NeurIPS 2023STORM: Efficient Stochastic Transformer based World Models for Reinforcement Learning
22. NeurIPS 2023Task-aware world model learning with meta weighting via bi-level optimization
23. NeurIPS 2023When Demonstrations meet Generative World Models: A Maximum Likelihood Framework for Offline Inverse Reinforcement Learning

常见问题

2023–2026 年四大会议一共有多少篇世界模型论文？

共 425 篇，按年份分别是 2023 年 23 篇、2024 年 46 篇、2025 年 106 篇、2026 年 250 篇。

NeurIPS 2026 有多少篇世界模型论文？

NeurIPS 2026 有 85 篇世界模型论文，上一届是 42 篇。

ICLR 2026 有多少篇世界模型论文？

ICLR 2026 有 56 篇世界模型论文，上一届是 24 篇。

ICML 2026 有多少篇世界模型论文？

ICML 2026 有 69 篇世界模型论文，上一届是 27 篇。

CVPR 2026 有多少篇世界模型论文？

CVPR 2026 有 40 篇世界模型论文，上一届是 13 篇。

哪个会议的世界模型论文最多？

NeurIPS，2023–2026 年共 159 篇。