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 3 / 5 页

101. ICML 2026Benchmarking World-Model Learning with Environment-Level Queries
102. ICML 2026Beyond Language Modeling: An Exploration of Multimodal Pretraining
103. ICML 2026Beyond Pixel Histories: World Models with Persistent 3D State
104. ICML 2026Boosting World Models Learning via Latent-Space Value Alignment
105. ICML 2026Building Social World Model with Large Language Models
106. ICML 2026Causal-JEPA: Learning World Models through Object-Level Latent Masking
107. ICML 2026Co-Evolving Latent Action World Models
108. ICML 2026CoIRL-AD: Collaborative-Competitive Imitation-Reinforcement Learning in Latent World Models for Autonomous Driving
109. ICML 2026Compositional Planning with Jumpy World Models
110. ICML 2026Cross-Embodiment Robot Foundation World Models with Latent Actions
111. ICML 2026DDP-WM: Disentangled Dynamics Prediction for Efficient World Models
112. ICML 2026DeepSight: Long-Horizon World Modeling via Latent States Prediction for End-to-End Autonomous Driving
113. ICML 2026DiLA: Disentangled Latent Action World Models
114. ICML 2026DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos
115. ICML 2026DriveWorld-VLA: Unified Latent-Space World Modeling with Vision–Language–Action for Autonomous Driving
116. ICML 2026DynaVieW: Schema-Guided World Modeling for Understanding Hierarchical Visual Dynamics
117. ICML 2026EmWorld: Emotion World Model with Latent State Evolution for Scenario-Incremental Dynamic Facial Expression Recognition
118. ICML 2026Evaluating Newtonian Mechanics in Video Generative Models with Real Physical Systems
119. ICML 2026Factored Latent Action World Models
120. ICML 2026FAST-AR: Fast Autoregressive Video Diffusion and World Models with Temporal Cache Compression and Sparse Attention
121. ICML 2026Flow Equivariant World Models: Structured Memory for Dynamic Environments
122. ICML 2026From Kepler to Newton: Inductive Biases Guide Learned World Models in Transformers
123. ICML 2026Future Dynamic 3D Reconstruction: A 3D World Model with Disentangled Ego-Motion
124. ICML 2026Generative Visual Code Mobile World Models
125. ICML 2026Identifiable Token Correspondence for World Models
126. ICML 2026Infinite-World: Scaling Interactive World Models to 1000-Frame Horizons via Pose-Free Hierarchical Memory
127. ICML 2026Interpreting Physics in Video World Models
128. ICML 2026iWorld-Bench: A Benchmark for Interactive World Models with a Unified Action Generation Framework
129. ICML 2026Learning Disentangled Multi-Agent World Model for Decentralized Control
130. ICML 2026Learning Latent Action World Models in the Wild
131. ICML 2026Learning Multi-Timescale Abstractions for Hierarchical Combinatorial Planning
132. ICML 2026Learning Reward–Cost Balance in Safe RL via Score-Based World Models
133. ICML 2026Learning Task-Sufficient World Models by Synergizing Agentic Exploration and Structured Modeling
134. ICML 2026LithoDreamer: A Physics-Informed World Model for Multi-Stage Computational Lithography
135. ICML 2026LIVE: Long-horizon Interactive Video World Modeling
136. ICML 2026MetaOthello: A Controlled Study of Multiple World Models in Transformers
137. ICML 2026Mind Dreamer: Untethering Imagination via Active Causal Intervention on Latent Manifolds
138. ICML 2026Multi-view Consistent Latent Action Learning for World Modeling and Control
139. ICML 2026MVISTA-4D: View-Consistent 4D World Model with Test-Time Action Inference for Robotic Manipulation
140. ICML 2026Olaf-World: Orienting Latent Actions for Video World Modeling
141. ICML 2026ORBIT: A Prognostic World Model for Ocular Reasoning Based on Imagined Trajectories
142. ICML 2026Parallel Stochastic Gradient-Based Planning for World Models
143. ICML 2026PathWise: Planning through World Model for Automated Heuristic Design via Self-Evolving LLMs
144. ICML 2026Physics from Video: Identifiability of Time-Invariant Second-Order ODEs under Minimal Trajectory Conditions
145. ICML 2026Policy-Driven World Model Adaptation for Robust Offline Model-based Reinforcement Learning
146. ICML 2026RoboFlow4D: A Lightweight Flow World Model Toward Real-Time Flow-Guided Robotic Manipulation
147. ICML 2026SC$^{2}$-WM: A Self-Correcting World Model with Closed-Loop Feedback for Vision-and-Language Navigation in Continuous Environments
148. ICML 2026Scaling Real-World Robot Policy Evaluation via Discrete Diffusion World Model
149. ICML 2026Self-supervised Hierarchical Visual Reasoning with World Model
150. ICML 2026Structure Abstraction and Generalization in a Hippocampal-Entorhinal Inspired World Model

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。