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 106 篇，第 2 / 3 页

51. ICML 2025Novelty Detection in Reinforcement Learning with World Models
52. ICML 2025PIGDreamer: Privileged Information Guided World Models for Safe Partially Observable Reinforcement Learning
53. ICML 2025PISA Experiments: Exploring Physics Post-Training for Video Diffusion Models by Watching Stuff Drop
54. ICML 2025PlaySlot: Learning Inverse Latent Dynamics for Controllable Object-Centric Video Prediction and Planning
55. ICML 2025Reward-free World Models for Online Imitation Learning
56. ICML 2025Scaling Laws for Pre-training Agents and World Models
57. ICML 2025SENSEI: Semantic Exploration Guided by Foundation Models to Learn Versatile World Models
58. ICML 2025SOLD: Slot Object-Centric Latent Dynamics Models for Relational Manipulation Learning from Pixels
59. ICML 2025Time-Aware World Model for Adaptive Prediction and Control
60. ICML 2025Trajectory World Models for Heterogeneous Environments
61. ICML 2025Video-Enhanced Offline Reinforcement Learning: A Model-Based Approach
62. ICML 2025What Has a Foundation Model Found? Inductive Bias Reveals World Models
63. ICML 2025When do neural networks learn world models?
64. ICML 2025World Model Implanting for Test-time Adaptation of Embodied Agents
65. NeurIPS 2025Agents Robust to Distribution Shifts Learn Causal World Models Even Under Mediation
66. NeurIPS 2025Bootstrap Off-policy with World Model
67. NeurIPS 2025COME: Adding Scene-Centric Forecasting Control to Occupancy World Model
68. NeurIPS 2025DMWM: Dual-Mind World Model with Long-Term Imagination
69. NeurIPS 2025DyMoDreamer: World Modeling with Dynamic Modulation
70. NeurIPS 2025Dyn-O: Building Structured World Models with Object-Centric Representations
71. NeurIPS 2025Dynamics-Aligned Latent Imagination in Contextual World Models for Zero-Shot Generalization
72. NeurIPS 2025DynamicVerse: A Physically-Aware Multimodal Framework for 4D World Modeling
73. NeurIPS 2025EDELINE: Enhancing Memory in Diffusion-based World Models via Linear-Time Sequence Modeling
74. NeurIPS 2025From Forecasting to Planning: Policy World Model for Collaborative State-Action Prediction
75. NeurIPS 2025Image as a World: Generating Interactive World from Single Image via Panoramic Video Generation
76. NeurIPS 2025Learning 3D Persistent Embodied World Models
77. NeurIPS 2025Learning and Planning Multi-Agent Tasks via an MoE-based World Model
78. NeurIPS 2025Learning Interactive World Model for Object-Centric Reinforcement Learning
79. NeurIPS 2025Learning World Models for Interactive Video Generation
80. NeurIPS 2025Leveraging Conditional Dependence for Efficient World Model Denoising
81. NeurIPS 2025Martian World Model: Controllable Video Synthesis with Physically Accurate 3D Reconstructions
82. NeurIPS 2025MindJourney: Test-Time Scaling with World Models for Spatial Reasoning
83. NeurIPS 2025OSVI-WM: One-Shot Visual Imitation for Unseen Tasks using World-Model-Guided Trajectory Generation
84. NeurIPS 2025Overcoming Challenges of Long-Horizon Prediction in Driving World Models
85. NeurIPS 2025PlayerOne: Egocentric World Simulator
86. NeurIPS 2025PoE-World: Compositional World Modeling with Products of Programmatic Experts
87. NeurIPS 2025Program Synthesis via Test-Time Transduction
88. NeurIPS 2025Raw2Drive: Reinforcement Learning with Aligned World Models for End-to-End Autonomous Driving (in CARLA v2)
89. NeurIPS 2025Revisiting Multi-Agent World Modeling from a Diffusion-Inspired Perspective
90. NeurIPS 2025RLVR-World: Training World Models with Reinforcement Learning
91. NeurIPS 2025RoboScape: Physics-informed Embodied World Model
92. NeurIPS 2025SAMPO: Scale-wise Autoregression with Motion Prompt for Generative World Models
93. NeurIPS 2025seq-JEPA: Autoregressive Predictive Learning of Invariant-Equivariant World Models
94. NeurIPS 2025Social World Model-Augmented Mechanism Design Policy Learning
95. NeurIPS 2025SPARTAN: A Sparse Transformer World Model Attending to What Matters
96. NeurIPS 2025StateSpaceDiffuser: Bringing Long Context to Diffusion World Models
97. NeurIPS 2025Text-to-Decision Agent: Offline Meta-Reinforcement Learning from Natural Language Supervision
98. NeurIPS 2025Towards foundational LiDAR world models with efficient latent flow matching
99. NeurIPS 2025VAGEN: Reinforcing World Model Reasoning for Multi-Turn VLM Agents
100. NeurIPS 2025Vector Quantization in the Brain: Grid-like Codes in 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。