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 2 / 2 页

51. ICLR 2026Video-GPT via Next Clip Diffusion
52. ICLR 2026ViMo: A Generative Visual GUI World Model for App Agents
53. ICLR 2026WIMLE: Uncertainty‑Aware World Models with IMLE for Sample‑Efficient Continuous Control
54. ICLR 2026WMPO: World Model-based Policy Optimization for Vision-Language-Action Models
55. ICLR 2026WorldGym: World Model as An Environment for Policy Evaluation
56. ICLR 2026WoW!: World Models in a Closed-Loop World
57. ICLR 2025AdaWM: Adaptive World Model based Planning for Autonomous Driving
58. ICLR 2025COMBO: Compositional World Models for Embodied Multi-Agent Cooperation
59. ICLR 2025Discrete Codebook World Models for Continuous Control
60. ICLR 2025Drama: Mamba-Enabled Model-Based Reinforcement Learning Is Sample and Parameter Efficient
61. ICLR 2025Dream to Manipulate: Compositional World Models Empowering Robot Imitation Learning with Imagination
62. ICLR 2025Dreamweaver: Learning Compositional World Models from Pixels
63. ICLR 2025Efficient Exploration and Discriminative World Model Learning with an Object-Centric Abstraction
64. ICLR 2025Empowering LLM Agents with Zero-Shot Optimal Decision-Making through Q-learning
65. ICLR 2025Enhancing End-to-End Autonomous Driving with Latent World Model
66. ICLR 2025FLIP: Flow-Centric Generative Planning as General-Purpose Manipulation World Model
67. ICLR 2025FOSP: Fine-tuning Offline Safe Policy through World Models
68. ICLR 2025Hierarchical World Models as Visual Whole-Body Humanoid Controllers
69. ICLR 2025Language Agents Meet Causality -- Bridging LLMs and Causal World Models
70. ICLR 2025Learning Transformer-based World Models with Contrastive Predictive Coding
71. ICLR 2025Learning View-invariant World Models for Visual Robotic Manipulation
72. ICLR 2025MMWorld: Towards Multi-discipline Multi-faceted World Model Evaluation in Videos
73. ICLR 2025Open-World Reinforcement Learning over Long Short-Term Imagination
74. ICLR 2025PWM: Policy Learning with Multi-Task World Models
75. ICLR 2025Scaling Offline Model-Based RL via Jointly-Optimized World-Action Model Pretraining
76. ICLR 2025Semi-Supervised Vision-Centric 3D Occupancy World Model for Autonomous Driving
77. ICLR 2025Simple, Good, Fast: Self-Supervised World Models Free of Baggage
78. ICLR 2025VisualPredicator: Learning Abstract World Models with Neuro-Symbolic Predicates for Robot Planning
79. ICLR 2025Web Agents with World Models: Learning and Leveraging Environment Dynamics in Web Navigation
80. ICLR 2025World Model on Million-Length Video And Language With Blockwise RingAttention
81. ICLR 2024Copilot4D: Learning Unsupervised World Models for Autonomous Driving via Discrete Diffusion
82. ICLR 2024Grounding Multimodal Large Language Models to the World
83. ICLR 2024Learning Hierarchical World Models with Adaptive Temporal Abstractions from Discrete Latent Dynamics
84. ICLR 2024Locality Sensitive Sparse Encoding for Learning World Models Online
85. ICLR 2024MAMBA: an Effective World Model Approach for Meta-Reinforcement Learning
86. ICLR 2024Mastering Memory Tasks with World Models
87. ICLR 2024Neurosymbolic Grounding for Compositional World Models
88. ICLR 2024Reward-Free Curricula for Training Robust World Models
89. ICLR 2024Robust agents learn causal world models
90. ICLR 2024SafeDreamer: Safe Reinforcement Learning with World Models
91. ICLR 2024TD-MPC2: Scalable, Robust World Models for Continuous Control
92. ICLR 2023Dynamic Update-to-Data Ratio: Minimizing World Model Overfitting
93. ICLR 2023Interaction-Based Disentanglement of Entities for Object-Centric World Models
94. ICLR 2023MoDem: Accelerating Visual Model-Based Reinforcement Learning with Demonstrations
95. ICLR 2023On the Feasibility of Cross-Task Transfer with Model-Based Reinforcement Learning
96. ICLR 2023Transformer-based World Models Are Happy With 100k Interactions
97. ICLR 2023Transformers are Sample-Efficient World Models
98. ICLR 2023Value Memory Graph: A Graph-Structured World Model for Offline 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。