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 3 / 4 页

101. NeurIPS 2025Leveraging Conditional Dependence for Efficient World Model Denoising
102. NeurIPS 2025Martian World Model: Controllable Video Synthesis with Physically Accurate 3D Reconstructions
103. NeurIPS 2025MindJourney: Test-Time Scaling with World Models for Spatial Reasoning
104. NeurIPS 2025OSVI-WM: One-Shot Visual Imitation for Unseen Tasks using World-Model-Guided Trajectory Generation
105. NeurIPS 2025Overcoming Challenges of Long-Horizon Prediction in Driving World Models
106. NeurIPS 2025PlayerOne: Egocentric World Simulator
107. NeurIPS 2025PoE-World: Compositional World Modeling with Products of Programmatic Experts
108. NeurIPS 2025Program Synthesis via Test-Time Transduction
109. NeurIPS 2025Raw2Drive: Reinforcement Learning with Aligned World Models for End-to-End Autonomous Driving (in CARLA v2)
110. NeurIPS 2025Revisiting Multi-Agent World Modeling from a Diffusion-Inspired Perspective
111. NeurIPS 2025RLVR-World: Training World Models with Reinforcement Learning
112. NeurIPS 2025RoboScape: Physics-informed Embodied World Model
113. NeurIPS 2025SAMPO: Scale-wise Autoregression with Motion Prompt for Generative World Models
114. NeurIPS 2025seq-JEPA: Autoregressive Predictive Learning of Invariant-Equivariant World Models
115. NeurIPS 2025Social World Model-Augmented Mechanism Design Policy Learning
116. NeurIPS 2025SPARTAN: A Sparse Transformer World Model Attending to What Matters
117. NeurIPS 2025StateSpaceDiffuser: Bringing Long Context to Diffusion World Models
118. NeurIPS 2025Text-to-Decision Agent: Offline Meta-Reinforcement Learning from Natural Language Supervision
119. NeurIPS 2025Towards foundational LiDAR world models with efficient latent flow matching
120. NeurIPS 2025VAGEN: Reinforcing World Model Reasoning for Multi-Turn VLM Agents
121. NeurIPS 2025Vector Quantization in the Brain: Grid-like Codes in World Models
122. NeurIPS 2025Video World Models with Long-term Spatial Memory
123. NeurIPS 2025WALL-E: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents
124. NeurIPS 2025World Models as Reference Trajectories for Rapid Motor Adaptation
125. NeurIPS 2025World Models Should Prioritize the Unification of Physical and Social Dynamics
126. NeurIPS 2025WorldModelBench: Judging Video Generation Models As World Models
127. NeurIPS 2025Zero-shot World Models via Search in Memory
128. NeurIPS 2024A Data-Centric Perspective on Evaluating Machine Learning Models for Tabular Data
129. NeurIPS 2024Diffusion for World Modeling: Visual Details Matter in Atari
130. NeurIPS 2024DrivingDojo Dataset: Advancing Interactive and Knowledge-Enriched Driving World Model
131. NeurIPS 2024Evaluating the World Model Implicit in a Generative Model
132. NeurIPS 2024Generating Code World Models with Large Language Models Guided by Monte Carlo Tree Search
133. NeurIPS 2024GenRL: Multimodal-foundation world models for generalization in embodied agents
134. NeurIPS 2024Grounded Answers for Multi-agent Decision-making Problem through Generative World Model
135. NeurIPS 2024In-Context Symmetries: Self-Supervised Learning through Contextual World Models
136. NeurIPS 2024iVideoGPT: Interactive VideoGPTs are Scalable World Models
137. NeurIPS 2024Learning World Models for Unconstrained Goal Navigation
138. NeurIPS 2024Leveraging Separated World Model for Exploration in Visually Distracted Environments
139. NeurIPS 2024Making Offline RL Online: Collaborative World Models for Offline Visual Reinforcement Learning
140. NeurIPS 2024Meta-DT: Offline Meta-RL as Conditional Sequence Modeling with World Model Disentanglement
141. NeurIPS 2024Operator World Models for Reinforcement Learning
142. NeurIPS 2024PIVOT-R: Primitive-Driven Waypoint-Aware World Model for Robotic Manipulation
143. NeurIPS 2024Policy-shaped prediction: avoiding distractions in model-based reinforcement learning
144. NeurIPS 2024Simplifying Latent Dynamics with Softly State-Invariant World Models
145. NeurIPS 2024Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllability
146. NeurIPS 2024WorldCoder, a Model-Based LLM Agent: Building World Models by Writing Code and Interacting with the Environment
147. NeurIPS 2023Action Inference by Maximising Evidence: Zero-Shot Imitation from Observation with World Models
148. NeurIPS 2023CQM: Curriculum Reinforcement Learning with a Quantized World Model
149. NeurIPS 2023Facing Off World Model Backbones: RNNs, Transformers, and S4
150. NeurIPS 2023Imagine the Unseen World: A Benchmark for Systematic Generalization in Visual 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。