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 250 篇，第 2 / 5 页

51. ICLR 2026Dual-Scale World Models for LLM Agents towards Hard-Exploration Problems
52. ICLR 2026Efficient Reinforcement Learning by Guiding World Models with Non-Curated Data
53. ICLR 2026Empowering Multi-Robot Cooperation via Sequential World Models
54. ICLR 2026ENACT: Evaluating Embodied Cognition with World Modeling of Egocentric Interaction
55. ICLR 2026FantasyWorld: Geometry-Consistent World Modeling via Unified Video and 3D Prediction
56. ICLR 2026FideDiff: Efficient Diffusion Model for High-Fidelity Image Motion Deblurring
57. ICLR 2026From Observations to Events: Event-Aware World Models for Reinforcement Learning
58. ICLR 2026Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling
59. ICLR 2026Horizon Imagination: Efficient On-Policy Rollout in Diffusion World Models
60. ICLR 2026Latent Particle World Models: Self-supervised Object-centric Stochastic Dynamics Modeling
61. ICLR 2026Learning Human Habits with Rule-Guided Active Inference
62. ICLR 2026Learning Massively Multitask World Models for Continuous Control
63. ICLR 2026Learning Physics-Grounded 4D Dynamics with Neural Gaussian Force Fields
64. ICLR 2026Learning to Be Uncertain: Pre-training World Models with Horizon-Calibrated Uncertainty
65. ICLR 2026Mapping Overlaps in Benchmarks through Perplexity in the Wild
66. ICLR 2026Mixture-of-World Models: Scaling Multi-Task Reinforcement Learning with Modular Latent Dynamics
67. ICLR 2026Object-Centric World Models from Few-Shot Annotations for Sample-Efficient Reinforcement Learning
68. ICLR 2026OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling
69. ICLR 2026One Life to Learn: Inferring Symbolic World Models for Stochastic Environments from Unguided Exploration
70. ICLR 2026One Model for All Tasks: Leveraging Efficient World Models in Multi-Task Planning
71. ICLR 2026Open-Set Semantic Gaussian Splatting SLAM with Expandable Representation
72. ICLR 2026R-WoM: Retrieval-augmented World Model For Computer-use Agents
73. ICLR 2026R2-Dreamer: Redundancy-Reduced World Models without Decoders or Augmentation
74. ICLR 2026ResWorld: Temporal Residual World Model for End-to-End Autonomous Driving
75. ICLR 2026Rethinking Driving World Model as Synthetic Data Generator for Perception Tasks
76. ICLR 2026ROGA: Scaling Generalist Agents for Office Productivity Tasks via Tool Generation
77. ICLR 2026Rolling Forcing: Autoregressive Long Video Diffusion in Real Time
78. ICLR 2026Scalable In-Context Q-Learning
79. ICLR 2026Self-Supervised Learning from Structural Invariance
80. ICLR 2026Sparse Imagination for Efficient Visual World Model Planning
81. ICLR 2026Speech World Model: Causal State–Action Planning with Explicit Reasoning for Speech
82. ICLR 2026TD-JEPA: Latent-predictive Representations for Zero-Shot Reinforcement Learning
83. ICLR 2026Test-Time Mixture of World Models for Embodied Agents in Dynamic Environments
84. ICLR 2026Towards Bridging the Gap between Large-Scale Pretraining and Efficient Finetuning for Humanoid Control
85. ICLR 2026Towards Spatial Supersensing in Video
86. ICLR 2026Unified 3D Scene Understanding Through Physical World Modeling
87. ICLR 2026Unified Vision-Language-Action Model
88. ICLR 2026VCWorld: A Biological World Model for Virtual Cell Simulation
89. ICLR 2026Verification of the Implicit World Model in a Generative Model via Adversarial Sequences
90. ICLR 2026Vid2World: Crafting Video Diffusion Models to Interactive World Models
91. ICLR 2026Video-GPT via Next Clip Diffusion
92. ICLR 2026ViMo: A Generative Visual GUI World Model for App Agents
93. ICLR 2026WIMLE: Uncertainty‑Aware World Models with IMLE for Sample‑Efficient Continuous Control
94. ICLR 2026WMPO: World Model-based Policy Optimization for Vision-Language-Action Models
95. ICLR 2026WorldGym: World Model as An Environment for Policy Evaluation
96. ICLR 2026WoW!: World Models in a Closed-Loop World
97. ICML 2026A Deep Learning Model of Mental Rotation Informed by Interactive VR Experiments
98. ICML 2026Agent Learning via Early Experience
99. ICML 2026Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning
100. ICML 2026Behavior-Invariant Task Representation Learning with Transformer-based World Models for Offline Meta-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。