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 159 篇，第 1 / 4 页

1. NeurIPS 2026A Hierarchical World Model for Driving
2. NeurIPS 2026A World Model of Radiologist Reading for Medical Image Representation Learning
3. NeurIPS 2026Active Learning for Gaussian Process Regression Under Self-Induced Boltzmann Weights
4. NeurIPS 2026ActO: Extracting Action Representations from MLLM Embeddings for Video World Models
5. NeurIPS 2026AdaWM: Few-Shot Adaptation of World Models to Unseen Dynamical Regimes
6. NeurIPS 2026Addressable Memory for Video World Models
7. NeurIPS 2026AEON: Unifying Video and 3D World Models
8. NeurIPS 2026Agent2World: Learning to Generate Symbolic World Models via Adaptive Multi-Agent Feedback
9. NeurIPS 2026AmbiguousWorld: Benchmarking and Resolving Ambiguous Instructions in Video World Models
10. NeurIPS 2026AnchorWorld: Embodied Egocentric World Simulation with View-based Evolution Customization
11. NeurIPS 2026Audible World Models: Spatially Aware Sound Generation for 3D Worlds
12. NeurIPS 2026Autoregressive Diffusion World Models for Off-Policy Evaluation of LLM Agents
13. NeurIPS 2026Axiomatic World Modeling for Physics Reasoning
14. NeurIPS 2026Baba in Wonderland: Online Self-Supervised Dynamics Discovery for Executable World Models
15. NeurIPS 2026Beyond Prediction: Steering VLM Agents with Retrospective World Modeling
16. NeurIPS 2026Bridging Scene Generation and Planning: Driving with World Model via Unifying Vision and Motion Representation
17. NeurIPS 2026Code2World: A GUI World Model via Renderable Code Generation
18. NeurIPS 2026Counterfactual Debugging the World Model Transfer Gap
19. NeurIPS 2026CounterStrike-1K: A Multi-Perspective Dataset of Professional Gameplay for World Modeling
20. NeurIPS 2026CoWorld-VLA: Thinking in a Multi-Expert World Model for Autonomous Driving
21. NeurIPS 2026Decomposed Graded Verifier for Generative World Modeling
22. NeurIPS 2026Do Enterprise Systems Need Learned World Models? The Importance of Context to Infer Dynamics
23. NeurIPS 2026Drift-Resistant Navigation World Model with Anchored Epipolar Guidance
24. NeurIPS 2026DRILL: Training World Models to Improve Policies, Not Predict Pixels
25. NeurIPS 2026DriveDreamer-Policy: A Geometry-Grounded World-Action Model for Unified Generation and Planning
26. NeurIPS 2026DriveFuture: Future-Aware Latent World Models for Autonomous Driving
27. NeurIPS 2026ECHO: Terminal Agents Learn World Models for Free
28. NeurIPS 2026EO-WM: A Physically Informed World Model for Probabilistic Earth Observation Forecasting
29. NeurIPS 2026EpicWorldModel: Exploration-driven Planning with Latent World Models
30. NeurIPS 2026Feedback World Model Enables Precise Guidance of Diffusion Policy
31. NeurIPS 2026From Anti-Forgetting to Fast Adaptation: Continual Reinforcement Learning with World Models
32. NeurIPS 2026From Zero to Hero: Training-Free Custom Concept Spawning in World Models
33. NeurIPS 2026HAI: Hierarchical Anchored Interaction for Multi-View Bimanual World Models
34. NeurIPS 2026HalluWorld: A Controlled Benchmark for Hallucination via Reference World Models
35. NeurIPS 2026HaM-World: Soft-Hamiltonian World Models with Selective Memory for Planning
36. NeurIPS 2026Hybrid Neural World Models for Physical Dynamics
37. NeurIPS 2026ICAT: Incident-Case–Grounded Adaptive Testing for Physical-Risk Prediction in Embodied World Models
38. NeurIPS 2026Imagine, Don't Narrate: The Generative Bottleneck in World Models of Interaction Dynamics
39. NeurIPS 2026Imperfect World Models are Exploitable
40. NeurIPS 2026Joint Learning of Hierarchical Neural Options and Abstract World Model
41. NeurIPS 2026K-PWM: Control-Oriented Structured World Models under Partial Observation
42. NeurIPS 2026Language-Conditioned World Modeling for Visual Navigation
43. NeurIPS 2026Latent Video Prediction for World Modeling: An Evaluation Uncovering Intriguing Favorable Evidence
44. NeurIPS 2026LatentUM: Unleashing the Potential of Interleaved Cross-Modal Reasoning via a Latent-Space Unified Model
45. NeurIPS 2026Learning Agentic World Vision-Language-Action Models for Autonomous Driving
46. NeurIPS 2026Learning POMDP World Models from Observations with Language-Model Priors
47. NeurIPS 2026Learning Task-Centric World Models from Visual Foundations
48. NeurIPS 2026Learning Visual Feature-Based World Models via Residual Latent Action
49. NeurIPS 2026LEIA: Learned Environment for Interactive Architected Materials
50. NeurIPS 2026LongScape: Advancing Long-Horizon Embodied World Models with Context-Aware MoE

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。