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 98 篇，第 1 / 2 页

1. ICLR 2026Astra: General Interactive World Model with Autoregressive Denoising
2. ICLR 2026Building spatial world models from sparse transitional episodic memories
3. ICLR 2026Code World Models for General Game Playing
4. ICLR 2026Composition of Memory Experts for Diffusion World Models
5. ICLR 2026ConsisDrive: Identity-Preserving Driving World Models for Video Generation by Instance Mask
6. ICLR 2026Context and Diversity Matter: The Emergence of In-Context Learning in World Models
7. ICLR 2026Ctrl-World: A Controllable Generative World Model for Robot Manipulation
8. ICLR 2026Deep SPI: Safe Policy Improvement via World Models
9. ICLR 2026DriveVLA-W0: World Models Amplify Data Scaling Law in Autonomous Driving
10. ICLR 2026DrivingGen: A Comprehensive Benchmark for Generative Video World Models in Autonomous Driving
11. ICLR 2026Dual-Scale World Models for LLM Agents towards Hard-Exploration Problems
12. ICLR 2026Efficient Reinforcement Learning by Guiding World Models with Non-Curated Data
13. ICLR 2026Empowering Multi-Robot Cooperation via Sequential World Models
14. ICLR 2026ENACT: Evaluating Embodied Cognition with World Modeling of Egocentric Interaction
15. ICLR 2026FantasyWorld: Geometry-Consistent World Modeling via Unified Video and 3D Prediction
16. ICLR 2026FideDiff: Efficient Diffusion Model for High-Fidelity Image Motion Deblurring
17. ICLR 2026From Observations to Events: Event-Aware World Models for Reinforcement Learning
18. ICLR 2026Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling
19. ICLR 2026Horizon Imagination: Efficient On-Policy Rollout in Diffusion World Models
20. ICLR 2026Latent Particle World Models: Self-supervised Object-centric Stochastic Dynamics Modeling
21. ICLR 2026Learning Human Habits with Rule-Guided Active Inference
22. ICLR 2026Learning Massively Multitask World Models for Continuous Control
23. ICLR 2026Learning Physics-Grounded 4D Dynamics with Neural Gaussian Force Fields
24. ICLR 2026Learning to Be Uncertain: Pre-training World Models with Horizon-Calibrated Uncertainty
25. ICLR 2026Mapping Overlaps in Benchmarks through Perplexity in the Wild
26. ICLR 2026Mixture-of-World Models: Scaling Multi-Task Reinforcement Learning with Modular Latent Dynamics
27. ICLR 2026Object-Centric World Models from Few-Shot Annotations for Sample-Efficient Reinforcement Learning
28. ICLR 2026OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling
29. ICLR 2026One Life to Learn: Inferring Symbolic World Models for Stochastic Environments from Unguided Exploration
30. ICLR 2026One Model for All Tasks: Leveraging Efficient World Models in Multi-Task Planning
31. ICLR 2026Open-Set Semantic Gaussian Splatting SLAM with Expandable Representation
32. ICLR 2026R-WoM: Retrieval-augmented World Model For Computer-use Agents
33. ICLR 2026R2-Dreamer: Redundancy-Reduced World Models without Decoders or Augmentation
34. ICLR 2026ResWorld: Temporal Residual World Model for End-to-End Autonomous Driving
35. ICLR 2026Rethinking Driving World Model as Synthetic Data Generator for Perception Tasks
36. ICLR 2026ROGA: Scaling Generalist Agents for Office Productivity Tasks via Tool Generation
37. ICLR 2026Rolling Forcing: Autoregressive Long Video Diffusion in Real Time
38. ICLR 2026Scalable In-Context Q-Learning
39. ICLR 2026Self-Supervised Learning from Structural Invariance
40. ICLR 2026Sparse Imagination for Efficient Visual World Model Planning
41. ICLR 2026Speech World Model: Causal State–Action Planning with Explicit Reasoning for Speech
42. ICLR 2026TD-JEPA: Latent-predictive Representations for Zero-Shot Reinforcement Learning
43. ICLR 2026Test-Time Mixture of World Models for Embodied Agents in Dynamic Environments
44. ICLR 2026Towards Bridging the Gap between Large-Scale Pretraining and Efficient Finetuning for Humanoid Control
45. ICLR 2026Towards Spatial Supersensing in Video
46. ICLR 2026Unified 3D Scene Understanding Through Physical World Modeling
47. ICLR 2026Unified Vision-Language-Action Model
48. ICLR 2026VCWorld: A Biological World Model for Virtual Cell Simulation
49. ICLR 2026Verification of the Implicit World Model in a Generative Model via Adversarial Sequences
50. ICLR 2026Vid2World: Crafting Video Diffusion Models to Interactive World Models

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。